@Preamble{
"\input bibnames.sty"
# "\hyphenation{Chem-u-du-gun-ta Kou-ba-ra-kis San-kar-a-na-ray-a-nan Yan-kel-o-vich}"
}
@String{ack-nhfb = "Nelson H. F. Beebe,
University of Utah,
Department of Mathematics, 110 LCB,
155 S 1400 E RM 233,
Salt Lake City, UT 84112-0090, USA,
Tel: +1 801 581 5254,
FAX: +1 801 581 4148,
e-mail: \path|beebe@math.utah.edu|,
\path|beebe@acm.org|,
\path|beebe@computer.org| (Internet),
URL: \path|https://www.math.utah.edu/~beebe/|"}
@String{j-TOIS = "ACM Transactions on Information Systems"}
@String{pub-ACM = "ACM Press"}
@String{pub-ACM:adr = "New York, NY 10036, USA"}
@Article{Allen:1989:ENN,
author = "R. B. Allen",
title = "Editorial: a New Name --- {ACM Transactions on
Information Systems}",
journal = j-TOIS,
volume = "7",
number = "1",
pages = "1--2",
month = jan,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 16:21:56 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "With this issue the Transactions becomes the ACM
Transaction on Information Systems (TOIS). In addition,
TOIS' charter has been expanded to formally include the
field of Information Retrieval. These changes affirm
the broad scope that the journal has been pursuing in
recent years. As before, a wide variety of perspectives
on information systems will be considered, including
topics such as user and organizational interfaces, data
models, system organization, knowledge bases, and new
media. Of course, TOIS will also continue to examine
the uses and impact of information systems. Thus,
papers in areas such as electronic publishing,
interactive video services, large text archives, UIMSs,
intelligent tutoring systems, and cooperative work are
encouraged. TOIS is primarily a research journal with
an emphasis on quality and originality, as well as
relevance. Moreover, TOIS has a Practice and Experience
Section for papers that present novel insights without
the usual rigor of Research Contributions. Together,
the Associate Editors and I are committed to keeping
TOIS the premier publication in its field. We will also
strive to make TOIS a testbed for new information
systems.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Stotts:1989:PNB,
author = "P. David Stotts and Richard Furuta",
title = "{Petri} Net Based Hypertext: Document Structure with
Browsing Semantics",
journal = j-TOIS,
volume = "7",
number = "1",
pages = "3--29",
month = jan,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We present a formal definition of the Trellis model of
hypertext and describe an authoring and browsing
prototype called $\alpha$ Trellis that is based on the
model. The Trellis model not only represents the
relationships that tie individual pieces of information
together into a document (i.e., the adjacencies), but
specifies the browsing semantics to be associated with
the hypertext as well (i.e., the manner in which the
information is to be visited and presented). The model
is based on Petri nets, and is a generalization of
existing directed graph-based forms of hypertext. The
Petri net basis permits more powerful specification of
what is to be displayed when a hypertext is browsed and
permits application of previously developed Petri net
analysis techniques to verify properties of the
hypertext. A number of useful hypertext constructs,
easily described in the Trellis model, are presented.
These include the synchronization of simultaneous
traversals of separate paths through a hypertext, the
incorporation of access controls into a hypertext
(i.e., specifying nodes that can be proven to be
accessible only to certain classes of browsers), and
construction of multiple specialized (tailored)
versions from a single hypertext.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Maryland",
affiliationaddress = "College Park, MD, USA",
classification = "723; 903",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Access controls; Browsing semantics; Browsing
Semantics; Computation by abstract devices; Database
Systems; Design; Formal models; Hypertext; Inf. storage
and retrieval; Information Retrieval; Information
Science; Languages; Miscellaneous; Models of
computation; Petri nets; Petri Nets; Synchronization;
Systems and software; Text processing; Theory; Trellis
Model; Trellis model of hypertext",
}
@Article{Egan:1989:FDE,
author = "Dennis E. Egan and Joel R. Remde and Louis M. Gomez
and Thomas K. Landauer and Jennifer Eberhardt and Carol
C. Lochbaum",
title = "Formative Design-Evaluation of {SuperBook}",
journal = j-TOIS,
volume = "7",
number = "1",
pages = "30--57",
month = jan,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "SuperBook is a hypertext browsing system designed to
improve the usability of conventional documents. This
work is a case study of formative design-evaluation.
Behavioral evaluation of the first version of SuperBook
showed how design factors and user strategies affected
search and established baseline performance measures
with printed text. The second version of SuperBook was
implemented with the goal of improving search accuracy
and speed. User strategies that had proved effective in
the first study were made very easy and attractive to
use. System response time for common operations was
greatly improved. Behavioral evaluation of the new
SuperBook demonstrated its superiority to printed text
and suggested additional improvements that were
incorporated into `MiteyBook,' a SuperBook
implementation for PC-size screens. Search with
MiteyBook proved to be approximately 25 percent faster
and 25 percent more accurate than that obtained with a
conventional printed book.",
acknowledgement = ack-nhfb,
affiliation = "Bellcore",
affiliationaddress = "Morristown, NJ, USA",
classification = "723; 903",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Database Systems; Documentation; Evaluation; Human
factors; Hypertext; Inf. storage and retrieval;
Information Retrieval; Information Retrieval Systems;
Information Science; Information search; Information
systems applications; Models and principles; Office
automation; SuperBook; Systems and software;
User/machine systems",
wwwauthor = "D. E. Egan and J. R. Remde and J. M. Gomez and T. K.
Landauer and J. Eberhardt and C. C. Lochbaum",
}
@Article{Utting:1989:COH,
author = "Kenneth Utting and Nicole Yankelovich",
title = "Context and Orientation in Hypermedia Networks",
journal = j-TOIS,
volume = "7",
number = "1",
pages = "58--84",
month = jan,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The core of hypermedia's power lies in the complex
networks of links that can be created within and
between documents. However, these networks frequently
overwhelm the user and become a source of confusion.
Within Intermedia, we have developed the Web View --- a
tool for viewing and navigating such networks with a
minimum of user confusion and disorientation. The key
factors in the Web View's success are a display that
combines a record of the user's path through the
network with a map of the currently available links; a
scope line that summarizes the number of documents and
links in the network; and a set of commands that permit
the user to open documents directly from the Web
View.",
acknowledgement = ack-nhfb,
affiliation = "Brown Univ",
affiliationaddress = "Providence, RI, USA",
classification = "723; 903",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Database Systems; Human factors; Hypermedia Networks;
Hypermedia systems; Hypertext systems; Inf. storage and
retrieval; Information Retrieval; Information Science;
Network browsers; Sys. and software; Web View",
wwwauthor = "N. Yankelovich and K. Utting",
}
@Article{Tompa:1989:DMF,
author = "Frank Wm. Tompa",
title = "A Data Model for Flexible Hypertext Database Systems",
journal = j-TOIS,
volume = "7",
number = "1",
pages = "85--100",
month = jan,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Hypertext and other page-oriented databases cannot
be-schematized in the same manner as record-oriented
databases. As a result, most hypertext database
implicitly employ a data model based on a simple,
unrestricted graph. This paper presents a hypergraph
model for maintaining page-oriented database in such a
way that some of the functionality traditionally
provided by database schemes can be available to
hypertext database. In particular, the model formalizes
identification of commonality in the structure,
set-at-a-time database access, and definition of
user-specific views. An efficient implementation of the
model is also discussed.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Waterloo",
affiliationaddress = "Waterloo, Ont, Can",
classification = "723; 903",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data manipulation languages (DML); Data models; Data
Models; Database management; Database Systems; Design;
Directed Hypergraphs; Directed hypergraphs; Hypertext;
Information Retrieval; Information Science; Information
storage; Information storage and retrieval; Languages;
Logical design; Text Management; Text management;
Videotex databases",
}
@Article{Sciore:1989:OS,
author = "Edward Sciore",
title = "Object Specialization",
journal = j-TOIS,
volume = "7",
number = "2",
pages = "103--122",
month = apr,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Specialization hierarchies typically are treated as
type-level constructs and are used to define various
inheritance mechanisms. In this paper we consider
specialization at the level of objects. We show that
doing so creates a more flexible and powerful notion of
inheritance by allowing objects to define their own
inheritance path. Object specialization can also be
used to model certain forms of versioning, implement
data abstraction, and provide a `classless'
prototype-based language interface to the user.",
acknowledgement = ack-nhfb,
affiliation = "Boston Univ",
affiliationaddress = "Boston, MA, USA",
classification = "723",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Computer Interfaces; Computer
Programming Languages; Database management; Database
Systems; Deduction and theorem proving; Delegation;
Design; Inheritance; Language constructs; Language
Constructs; Languages; Object Oriented Database;
Object-oriented database; Programming languages;
Specialization Hierarchies; Theory",
wwwpages = "103--123",
}
@Article{Guting:1989:ASO,
author = "Ralf Hartmut Guting and Roberto Zicari and David M.
Choy",
title = "An Algebra for Structured Office Documents",
journal = j-TOIS,
volume = "7",
number = "2",
pages = "123--157",
month = apr,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We describe a data model for structured office
information objects, which we generically call
`documents,' and a practically useful algebraic
language for the retrieval and manipulation of such
objects. Documents are viewed as hierarchical
structures; their layout (presentation) aspect is to be
treated separately. The syntax and semantics of the
language are defined precisely in terms of the formal
model, an extended relational algebra. The proposed
approach has several new features, some of which are
particularly useful for the management of office
information. The data model is based on nested
sequences of tuples rather than nested relations.
Therefore, sorting and sequence operations and the
explicit handling of duplicates can be described by the
model. Furthermore, this is the first model based on a
many-sorted instead of a one-sorted algebra, which
means that atomic data values as well as nested
structures are objects of the algebra. As a
consequence, arithmetic operations, aggregate
functions, and so forth can be treated inside the
model.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Dortmund",
affiliationaddress = "Dortmund, West Ger",
classification = "723",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data models; Data Models; Database applications;
Database management; Database Systems; Extended
relational algebra; Forms processing; Information
systems applications; Languages; Logical design;
Management; Many-sorted algebra; Miscellaneous; Nested
relations; Office automation; Office Automation; Query
languages; Query Languages; Relational; Relational
Algebra; Structured document; Theory; Tuple sequences",
}
@Article{Lee:1989:PSF,
author = "Dik Lun Lee and Chun-Wu Leng",
title = "Partitioned Signature Files: Design Issues and
Performance Evaluation",
journal = j-TOIS,
volume = "7",
number = "2",
pages = "158--180",
month = apr,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "A signature file acts as a filtering mechanism to
reduce the amount of text that needs to be searched for
a query. Unfortunately, the signature file itself must
be exhaustively searched, resulting in degraded
performance for a large file size. We propose to use a
deterministic algorithm to divide a signature file into
partitions, each of which contains signatures with the
same `key.' The signature keys in a partition can be
extracted and represented as the partition's key. The
search can then be confined to the subset of partitions
whose keys match the query key. Our main concern here
is to study methods for obtaining the keys and their
performance in terms of their ability to reduce the
search space. We outline the criteria for evaluating
partitioning schemes. Three algorithms are described
and studied. An analytical study of the performance of
the algorithms is provided, and the results are
verified with simulation.",
acknowledgement = ack-nhfb,
affiliation = "Ohio State Univ",
affiliationaddress = "Columbus, OH, USA",
classification = "723; 903",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Access method; Access methods; Codes; Computer
Programming--Algorithms; Computer Simulation; Data
Processing--File Organization; Database management;
Database Systems; Design; Document retrieval; Inf.
storage and retrieval; Information retrieval;
Information Retrieval; Information Science; Information
systems applications; Library automation; Office
automation; Parallel search; Parallel Search;
Partitioned Signature Files; Performance; Performance
evaluation; Physical design; Superimposed coding;
Superimposed Coding; Surrogate file; Symbolic; Text
editing; Text processing; Text retrieval",
wwwtitle = "Partitioned Signature File: Design Issues and
Performance Evaluation",
}
@Article{Croft:1989:EIS,
author = "W. B. Croft",
title = "Editorial: Introduction to the Special Issue",
journal = j-TOIS,
volume = "7",
number = "3",
pages = "181--182",
month = jul,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 16:21:56 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "This Special Issue contains selected papers from the
SIGIR Conference on Research and Development in
Information Retrieval held at Cambridge, Massachusetts
in June, 1989. The papers were selected by the program
committee and revised for publication in TOIS.
Information retrieval is a diverse field of research,
and the areas covered at this conference include formal
models, search strategies, hypermedia, storage
structures, evaluation, natural language processing,
interfaces, and knowledge-based architectures. The
unifying goal of this research is the efficient and
effective retrieval of complex, multimedia objects,
with a primary focus on text documents.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Fuhr:1989:OPR,
author = "Norbert Fuhr",
title = "Optimum Polynomial Retrieval Functions Based on the
Probability Ranking Principle",
journal = j-TOIS,
volume = "7",
number = "3",
pages = "183--204",
month = jul,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "We show that any approach to developing optimum
retrieval functions is based on two kinds of
assumptions: first, a certain form of representation
for documents and requests, and second, additional
simplifying assumptions that predefine the type of the
retrieval function. We describe an approach for the
development of optimum polynomial retrieval functions.
We give experimental results for the application of
this approach to documents with weighted indexing as
well as to documents with complex representations. In
contrast to other probabilistic models, our approach
yields estimates of the actual probabilities, it can
handle very complex representations of documents and
requests, and it can be easily applied to multivalued
relevance scales.",
acknowledgement = ack-nhfb,
affiliation = "Technische Hochschule Darmstadt",
affiliationaddress = "Darmstadt, West Ger",
classification = "903; 922",
conference = "SIGIR Conference on Research and Development in
Information Retrieval",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Approximation; Complex Document Representation;
Complex document representation; Content analysis and
indexing; Indexing methods; Information Retrieval
Systems; Information Science --- Information Retrieval;
Information search and retrieval; Information storage
and retrieval; Least squares approximation; Linear
Retrieval Functions; Linear retrieval functions;
Multivalued Relevance Scales; Multivalued relevance
scales; Numerical analysis; Optimum Retrieval;
Probabilistic Indexing; Probabilistic indexing;
Probabilistic retrieval; Probability; Probability
Ranking Principle; Probability ranking principle;
Retrieval methods Experimentation; Theory",
meetingaddress = "Cambridge, MA, USA",
meetingdate = "Jun 1989",
meetingdate2 = "06/89",
wwwtitle = "Optimal Polynomial Retrieval Functions Based on the
Probability Ranking Principle",
}
@Article{Raghavan:1989:CIR,
author = "Vijay V. Raghavan and Gwang S. Jung and Peter
Bollmann",
title = "A Critical Investigation of Recall and Precision as
Measures of Retrieval System Performance",
journal = j-TOIS,
volume = "7",
number = "3",
pages = "205--229",
month = jul,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "Recall and precision are often used to evaluate the
effectiveness of information retrieval systems. They
are easy to define if there is a single query and if
the retrieval result generated for the query is a
linear ordering. However, when the retrieval results
are weakly ordered, in the sense that several documents
have an identical retrieval status value with respect
to a query, some probabilistic notion of precision has
to be introduced. We systematically investigate the
various problems and issues associated with the use of
recall and precision as measures of retrieval system
performance. Our motivation is to provide a comparative
analysis of methods available for defining precision in
a probabilistic sense and to promote a better
understanding of the various issues involved in
retrieval performance evaluation.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Southwestern Louisiana",
affiliationaddress = "Lafayette, LA, USA",
classification = "903; 922",
conference = "SIGIR Conference on Research and Development in
Information Retrieval",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Evaluation measures; Expected precision; Expected
Search Length; Expected search length; Experimentation;
Fallout; General; Generality; Inf. storage and
retrieval; Information Retrieval; Information
retrieval; Information Retrieval Systems ---
Evaluation; Information Science; Information search and
retrieval; Information storage and retrieval;
Measurement; Miscellaneous; Performance; Performance
measurement; Precision; Probabilistic Notion;
Probability; Probability of relevance; Recall;
Retrieval models; Retrieval Models; Retrieval System
Performance; Stopping criterion; Systems evaluation;
Theory",
meetingaddress = "Cambridge, MA, USA",
meetingdate = "Jun 1989",
meetingdate2 = "06/89",
}
@Article{Klein:1989:STR,
author = "Shmuel T. Klein and Abraham Bookstein and Scott
Deerwester",
title = "Storing Text Retrieval Systems on {CD-ROM}.
Compression and Encryption Considerations",
journal = j-TOIS,
volume = "7",
number = "3",
pages = "230--245",
month = jul,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "The emergence of the CD-ROM as a storage medium for
full-text databases raises the question of the maximum
size database that can be contained by this medium. As
an example, the problem of storing the Tr{\'e}sor de la
Langue Fran{\c{c}}aise on a CD-ROM is examined.
Pertinent approaches to compression of the various
files are reviewed, and the compression of the text is
related to the problem of data encryption:
Specifically, it is shown that, under simple models of
text generation, Huffman encoding produces a bit-string
indistinguishable from a representation of coin
flips.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Chicago",
affiliationaddress = "Chicago, IL, USA",
classification = "723; 741; 903",
conference = "SIGIR Conference on Research and Development in
Information Retrieval",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Arts and humanities; Bit-maps; cd-rom;
CD-ROM; Coding and information theory; Computer
applications; Cryptography; Data; Data encryption; Data
Encryption; Data Storage; Full-Text Storage; Full-text
storage; Huffman Coding; Huffman coding; Inf. storage
and retrieval; Information Retrieval Systems ---
Database Systems; Information storage; Information
Theory --- Data Compression; Optical; Security; Storage
Devices; Text Retrieval Systems",
meetingaddress = "Cambridge, MA, USA",
meetingdate = "Jun 1989",
meetingdate2 = "06/89",
wwwtitle = "String Text Retrieval Systems on {CD-ROM}: Compression
and Encryption Considerations",
}
@Article{Smith:1989:KBS,
author = "Philip J. Smith and Steven J. Shute and Deb Galdes and
Mark H. Chignell",
title = "Knowledge-Based Search Tactics for an Intelligent
Intermediary System",
journal = j-TOIS,
volume = "7",
number = "3",
pages = "246--270",
month = jul,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "Research on the nature of knowledge-based systems for
bibliographic information retrieval is summarized.
Knowledge-based search tactics are then considered in
terms of their role in the functioning of a
semantically based search system for bibliographic
information retrieval, EP-X. This system uses such
tactics to actively assist users in defining or
refining their topics of interest. It does so by
applying these tactics to a knowledge base describing
topics in a particular domain and to a database
describing the contents of individual documents in
terms of these topics. This paper, then, focuses on the
two central concepts behind EP-X: semantically based
search and knowledge-based search tactics.",
acknowledgement = ack-nhfb,
affiliation = "The Ohio State Univ",
affiliationaddress = "Columbus, OH, USA",
classification = "723; 903",
conference = "SIGIR Conference on Research and Development in
Information Retrieval",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial Intelligence; Artificial intelligence;
Bibliographic Information Retrieval; Bibliographic
information retrieval; Database Systems; Document
Retrieval; Document retrieval; Frames and scripts;
Human factors; Inf. storage and retrieval; Information
Retrieval; Information Retrieval Systems --- Computer
Aided Analysis; Information Science; Information search
and retrieval; Knowledge Representation; Knowledge
representation formalisms and methods; Knowledge-Based
Search; Knowledge-based search tactics; Knowledge-Based
Systems; Knowledge-based systems; Models and
principles; Search process; Semantically Based Search;
Semantically based search; User/machine systems",
meetingaddress = "Cambridge, MA, USA",
meetingdate = "Jun 1989",
meetingdate2 = "06/89",
wwwtitle = "Knowledge-Based Search Tactics for an Intelligent
Intermediary",
}
@Article{Campagnoni:1989:IRU,
author = "F. R. Campagnoni and Kate Ehrlich",
title = "Information Retrieval Using a Hypertext-Based Help
System",
journal = j-TOIS,
volume = "7",
number = "3",
pages = "271--291",
month = jul,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "A study was conducted on information retrieval using a
commercial hypertext-based help system. It was found
that the predominant search strategy was `browsing',
rather than employing the indexes. Individuals with
better spatial visualization skills were faster at
retrieving information than those with poorer spatial
visualization skills. These results support previous
studies that have found a strong preference by users
for browsing in hypertext systems and extend those
findings to a new domain (help), a different type of
user interface, and a different information
architecture.",
acknowledgement = ack-nhfb,
affiliation = "Sun Microsystems, Inc",
affiliationaddress = "Billerica, MA, USA",
classification = "723; 903",
conference = "SIGIR Conference on Research and Development in
Information Retrieval",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer Graphics --- Interactive; Documentation;
Graphical User Interfaces; Help Systems; Help systems;
Human factors; Hypertext; Individual differences; Inf.
storage and retrieval; Information Retrieval;
Information Retrieval Systems --- Online Searching;
Information Science; Information Search; Information
search and retrieval; Models and principles; Search
process; Spatial Visualization; User/machine systems;
Visualization",
meetingaddress = "Cambridge, MA, USA",
meetingdate = "Jun 1989",
meetingdate2 = "06/89",
wwwauthor = "F. R. Campagnoi and K. Ehrlich",
}
@Article{Metzler:1989:COP,
author = "Douglas P. Metzler and Stephanie W. Haas",
title = "The Constituent Object Parser: Syntactic Structure
Matching for Information Retrieval",
journal = j-TOIS,
volume = "7",
number = "4",
pages = "292--316",
month = oct,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The Constituent Object Parser is a shallow syntactic
parser designed to produce dependency tree
representations of syntactic structure that can be used
to specify the intended meanings of a sentence more
precisely than can the key terms of the sentence alone.
It is intended to improve the precision/ recall
performance of information retrieval and similar text
processing applications by providing more powerful
matching procedures. The dependency tree representation
and the relationship between the intended use of this
parser and its design is described, and several
problems concerning the processing and ambiguous
structures are discussed.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Pittsburgh",
affiliationaddress = "Pittsburgh, PA, USA",
classification = "721; 723; 903",
conference = "SIGIR Conference on Research and Development in
Information Retrieval",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Automata Theory --- Grammars;
Content analysis and indexing; Dependency-based
parsing; Design; Inf. storage and retrieval;
Information Retrieval; Information Retrieval Systems;
Information Science; Information storage and retrieval;
Language Parsing; Language parsing and understanding;
Linguistic processing; Linguistic Processing; Natural
language processing; Natural Language Processing;
Precision; Query Formulation; Query formulation;
Relevancy judgments; Retrieval models; Search and
retrieval; Selection process; Syntactic Structure
Matching; Text Analysis; Text analysis",
meetingaddress = "Cambridge, MA, USA",
meetingdate = "Jun 1989",
meetingdate2 = "06/89",
}
@Article{Olson:1989:WHC,
author = "Margrethe H. Olson",
title = "Work at Home for Computer Professionals. Current
Attitudes and Future Prospects",
journal = j-TOIS,
volume = "7",
number = "4",
pages = "317--338",
month = oct,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The article reports on two studies of work at home: a
quasi-experimental field study of organizational
telecommuting pilot programs, and an attitude survey
comparing computer professionals who work at home to
employees doing similar jobs in traditional office
settings. The results of the field study demonstrated
that working in the home had little impact on employee
performance; however, supervisors were not comfortable
with remote workers and preferred their employees to be
on site. In the survey, work in the home was related to
lower job satisfaction, lower organizational
commitment, and higher role conflict. The survey also
included computer professionals who worked at home in
addition to the regular work day. The author suggests
that performing additional unpaid work in the home
after regular work hours may be an important trend that
merits further investigation. The studies demonstrate
that while computer and communications technology have
the potential to relax constraints on information work
in terms of space and time, in today's traditional work
environments, corporate culture and management style
limit acceptance of telecommuting as a substitute for
office work.",
acknowledgement = ack-nhfb,
affiliation = "New York Univ",
affiliationaddress = "New York, NY, USA",
classification = "716; 718; 723; 901; 912",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computers; Computers and society; Computing
Profession; Employment; Human factors; Management;
Occupations; Office Automation; Organizational impacts;
Performance; Personal; Personnel; Social issues;
Technology--Economic and Sociological Effects;
Telecommunication; Telecommuting; The computing
profession",
wwwtitle = "Remote Work and Information Technology: Impacts on
Organizations and Individuals",
}
@Article{Afsarmanesh:1989:EOO,
author = "Hamideh Afsarmanesh and Dennis McLeod",
title = "The {3DIS}: An Extensible, Object-Oriented Information
Management Environment",
journal = j-TOIS,
volume = "7",
number = "4",
pages = "339--377",
month = oct,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The 3-Dimensional Information Space (3DIS) is an
extensible object-oriented framework for information
management. It is specifically oriented toward
supporting the database requirements for data-intensive
information system applications in which (1)
information objects of various levels of abstraction
and modalities must be accommodated, (2) descriptive
and structural information (metadata) is rich and
dynamic, and (3) users who are not database experts
must be able to design, manipulate, and evolve
databases. In response to these needs, the 3DIS
provides an approach in which data and the descriptive
information about data are handled uniformly in an
extensible framework. The 3DIS provides a simple,
geometric, and formal representation of data which
forms a basis for understanding, defining, and
manipulating databases. Several prototype
implementations based upon the 3DIS have been designed
and implemented and are in experimental use.",
acknowledgement = ack-nhfb,
affiliation = "California State Univ",
affiliationaddress = "Carson, CA, USA",
classification = "723",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Data models; Database management; Database
Systems; Design; Extensible database systems;
Extensible Database Systems; Information Management;
Information systems applications; Knowledge
representation; Languages; Logical design; Management;
Object-oriented databases; Object-Oriented Databases;
Office automation; Office Automation; Office automation
systems; Office Information Systems; Schema and
subschema; Systems",
}
@Article{Pernici:1989:CTA,
author = "B. Pernici and F. Barbic and M. G. Fugini and R.
Maiocchi and J. R. Rames and C. Rolland",
title = "{C-TODOS}: An Automatic Tool for Office System
Conceptual Design",
journal = j-TOIS,
volume = "7",
number = "4",
pages = "378--419",
month = oct,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Designers of office information systems, which share
various features with information systems and software
development, need to carefully consider special issues
such as document and communication flows, user roles,
user interfaces, and available technology. The ESPRIT
Project, Automatic Tools for Designing Office
Information Systems (TODOS), proposes an integrated
environment for office design with tools for
requirements collection and analysis, conceptual
design, rapid prototyping, and architecture selection.
C-TODOS, the conceptual design support tool developed
within TODOS, is presented in this paper. The purpose
of C-TODOS is to give the designer tools for supporting
conceptual modeling activities with the goal of
obtaining correct, consistent, and good quality
office-functional specifications. This paper presents
C-TODOS within the TODOS development environment and
describes the basic features of the tool: the TODOS
Conceptual Model, the Specification Database, and the
Modeling, Query and Consistency Checking Modules. The
use of C-TODOS, through illustration of the development
of a test case, and possible future research are
discussed.",
acknowledgement = ack-nhfb,
affiliation = "Politecnico di Milano",
affiliationaddress = "Milan, Italy",
classification = "723",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Analysis and design of systems; C-TODOS; Computer
Software--Design; Database management; Design; Design
method; Design tool; Documentation; Information
Systems; Languages; Logical design; Management of
computing and information systems; Methodologies;
Office Automation; Office automation systems; Office
Information Systems; Query languages;
Requirements/specifications; Schema and subschema;
Semantic model; Semantic query language; Software
development; Software engineering; Software management;
Specification database; Tools",
}
@Article{Lee:1990:PSV,
author = "Jintae Lee and Thomas W. Malone",
title = "Partially Shared Views: a Scheme for Communicating
among Groups that Use Different Type Hierarchies",
journal = j-TOIS,
volume = "8",
number = "1",
pages = "1--26",
month = jan,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Many computer systems are based on various types of
messages, forms, or other objects. When users of such
systems need to communicate with people who use
different object types, some kind of translation is
necessary. In this paper, we explore the space of
general solutions to this translation problem and
propose a scheme that synthesizes these solutions. A
key insight of the analysis is that partially shared
type hierarchies allow `foreign' object types to be
automatically translated into their nearest common
`ancestor' types. The partial interoperability attained
in this way makes possible flexible standards from
which people can benefit from whatever agreements they
do have without having to agree on everything. Even
though our examples deal primarily with extension to
the Object Lens system, the analysis suggests how other
kinds of systems, such as EDI applications, might
exploit specialization hierarchies of object types to
simplify the translation problem.",
acknowledgement = ack-nhfb,
affiliation = "Massachusetts Inst of Technology",
affiliationaddress = "Cambridge, MA, USA",
classification = "722; 723",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Applications and expert systems; Artificial
intelligence; Communication; Communications
applications; Computer Software; Computer Supported
Cooperative Work; Computer supported cooperative work;
Computer Systems; Data; Design; Digital; Distributed;
Distributed systems; Electronic mail; Files; General;
Hierarchical systems; Information Lens; Information
systems; Information systems applications; Languages;
Management; Management of computing and information
systems; Modules and interfaces; Object Lens; Object
Lens System; Object Types; Office automation; Operating
systems; Organization and design; Organization and
structure; Partially Shared Views; Partially shared
views; Software configuration management; Software
engineering; Software libraries; Software management;
Standardization; System management; Tools and
techniques",
wwwtitle = "How Can Groups Communicate when They Use Different
Languages",
}
@Article{Bookstein:1990:CIT,
author = "Abraham Bookstein and Shmuel T. Klein",
title = "Compression, Information Theory, and Grammars: a
Unified Approach",
journal = j-TOIS,
volume = "8",
number = "1",
pages = "27--49",
month = jan,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We propose the notion of a formal grammar as a
flexible model of text generation that encompasses most
of the models offered before as well as, in principle,
extending the possibility of compression to a much more
general class of languages. Assuming a general model of
text generation, a derivation is given of the well
known Shannon entropy formula, making possible a theory
of information based upon text representation rather
than on communication. The ideas are shown to apply to
a number of commonly used text models. Finally, we
focus on a Markov model of text generation, suggest an
information theoretic measure of similarity between two
probability distributions, and develop a clustering
algorithm based on this measure. This algorithm allows
us to cluster Markov states and thereby base our
compression algorithm on a smaller number of
probability distributions than would otherwise have
been required. A number of theoretical consequences of
this approach to compression are explored, and a
detailed example is given.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Chicago",
affiliationaddress = "Chicago, IL, USA",
classification = "721; 723; 922",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Artificial intelligence; Automata
Theory--Grammars; Codes; Coding and information theory;
Computer Programming--Algorithms; Data; Data compaction
and compression; Data Compression; Huffman coding;
Huffman Coding; Information storage; Information
storage and retrieval; Information theory; Information
Theory; Language Generation; Markov model of language
generation; Markov Models; Models and principles;
Natural language processing; Probability--Random
Processes; Symbolic--Encoding; Systems and information
theory; Theory",
}
@Article{Hammainen:1990:DFM,
author = "Heikki Hammainen and Eero Eloranta and Jari
Alasuvanto",
title = "Distributed Form Management",
journal = j-TOIS,
volume = "8",
number = "1",
pages = "50--76",
month = jan,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "An open architecture for distributed form management
is described. The model employs object-orientation in
describing organizational units as well as individual
users as entities with uniform external interfaces.
Each entity is represented by an autonomous user agent
which operates on local and migrating forms. The form
concept encapsulates data, layout, and rules into a
unified object which is the basic unit of presentation,
processing, storage, and communication. All
functionality of the system appears in rules of form
classes and all data in instances of these form
classes. This approach applies the techniques of
computer supported cooperative work to provide a
flexible mechanism for interpersonal, intraoffice, and
interoffice procedures. The main challenge is to
organize the collaboration without affecting the
autonomy of individual user agents. In this respect,
the contribution of the model is the mechanism for form
migration. The dynamic integration of forms into
different agents is solved with the coordinated
interchange of form classes. A specific inheritance
scheme provides the desired flexibility by separating
the interrelated private and public form operations
within each agent. The paper first describes the
architecture by starting from a single agent and moving
progressively towards a set of cooperating agents. Then
an agent implementation called PAGES is described,
experiences reported, and the open issues discussed. A
typical distributed ordering procedure is used as an
example throughout the text.",
acknowledgement = ack-nhfb,
affiliation = "Helsinki Univ of Technology",
affiliationaddress = "Espoo, Finl",
classification = "723",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Communications applications; Computer Architecture;
Computer Supported Cooperative Work; Computer supported
cooperative work; Computer Systems;
Computer-communication networks; Database management;
Digital--Distributed; Distr. applications; Distr.
systems; Distributed Form Management; Electronic mail;
Form Management; Form management; Human factors;
Information systems applications; Management;
Object-orientation; Office automation; Office
Automation; Performance; Systems; User agent",
}
@Article{Watters:1990:THB,
author = "Carolyn Watters and Michael A. Shepherd",
title = "A Transient Hypergraph-based Model for Data Access",
journal = j-TOIS,
volume = "8",
number = "2",
pages = "77--102",
month = apr,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Two major methods of accessing data in current
database systems are querying and browsing. The more
traditional query method returns an answer set that may
consist of data values (DBMS), items containing the
answer (full text), or items referring the user to
items containing the answer (bibliographic). Browsing
within a database, as best exemplified by hypertext
systems, consists of viewing a database item and
linking to related items on the basis of some attribute
or attribute value. A model of data access has been
developed that supports both query and browse access
methods. The model is based on hypergraph
representation of data instances. The hyperedges and
nodes are manipulated through a set of operators to
compose new nodes and to instantiate new links
dynamically, resulting in transient hypergraphs. These
transient hypergraphs are virtual structures created in
response to user queries, and lasting only as long as
the query session. The model provides a framework for
general data access that accommodates user-directed
browsing and querying, as well as traditional models of
information and data retrieval, such as the Boolean,
vector space, and probabilistic models. Finally, the
relational database model is shown to provide a
reasonable platform for the implementation of this
transient hypergraph-based model of data access.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Data access model; Data items; Data manipulation; Data
models; Data structures; Database management; Design;
Hypertext; Inf. storage and retrieval; Information
storage; Logic design; Transient hypergraphs; Virtual
structures",
wwwauthor = "C. Watters and M. A. Sheperd",
}
@Article{Moss:1990:DMP,
author = "J. Eliot B. Moss",
title = "Design of the {Mneme} Persistent Object Store",
journal = j-TOIS,
volume = "8",
number = "2",
pages = "103--139",
month = apr,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
wwwtitle = "Design of the Mmeme Persistent Object Store",
}
@Article{Shasha:1990:NTB,
author = "Dennis Shasha and Tsong-Li Wang",
title = "New Techniques for Best-Match Retrieval",
journal = j-TOIS,
volume = "8",
number = "2",
pages = "140--158",
month = apr,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "A scheme to answer best-match queries from a file
containing a collection of objects is described. A
best-match query is to find the objects in the file
that are closest (according to some (dis)similarity
measure) to a given target. Previous work [5, 33]
suggests that one can reduce the number of comparisons
required to achieve the desired results using the
triangle inequality, starting with a data structure for
the file that reflects some precomputed intrafile
distances. We generalize the technique to allow the
optimum use of any given set of precomputed intrafile
distances. Some empirical results are presented which
illustrate the effectiveness of our scheme, and its
performance relative to previous algorithms.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Algorithms; Analysis of algorithms and problem
complexity; Artificial intelligence; Best match;
Database management; Distance metrics; File searching;
Heuristics; Information search and retrieval;
Information storage and retrieval; Lower bounds;
Matching; Miscellaneous; Nonnumerical algorithms and
problems; Performance; Query processing; Search
process; Sorting and searching; Systems; Theory;
Topology; Upper bounds",
}
@Article{Morrissey:1990:IIU,
author = "J. M. Morrissey",
title = "Imprecise Information and Uncertainty in Information
Systems",
journal = j-TOIS,
volume = "8",
number = "2",
pages = "159--180",
month = apr,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Information systems exist to model, store, and
retrieve all types of data. Problems arise when some of
the data are missing or imprecisely known or when an
attribute is not applicable to a particular object. A
consistent and useful treatment of such exceptions is
necessary. The approach taken here is to allow any
attribute value to be a regular precise value, a string
denoting that the value is missing, a string denoting
that the attribute is not applicable, or an imprecise
value. The imprecise values introduce uncertainty into
query evaluation, since it is no longer obvious which
objects should be retrieved. To handle the uncertainty,
two set of objects are retrieved in response to every
query: the set of objects that are known to satisfy
with complete certainty and the set that possibly
satisfies the query with various degrees of
uncertainty. Two methods of estimating this
uncertainty, based on information theory, are proposed.
The measure of uncertainty is used to rank objects for
presentation to a user.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Database management; Design; Incomplete information;
Inf. theory; Management; Models and principles; Null
values; Query evaluation; Query processing; Sys. and
information theory; Systems; Uncertainty",
}
@Article{Hartson:1990:UUO,
author = "H. Rex Hartson and Antonio C. Siochi and Deborah Hix",
title = "The {UAN}: a User-Oriented Representation for Direct
Manipulation Interface Designs",
journal = j-TOIS,
volume = "8",
number = "3",
pages = "181--203",
month = jul,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Many existing interface representation techniques,
especially those associated with UIMS, are
constructional and focused on interface implementation,
and therefore do not adequately support a user-centered
focus. But it is in the behavioral domain of the user
that interface designers and evaluators do their work.
We are seeking to complement constructional methods by
providing a tool-supported technique capable of
specifying the behavioral aspects of an interactive
system-the tasks and the actions a user performs to
accomplish those tasks. In particular, this paper is a
practical introduction to use of the User Action
Notation (UAN), a task- and user-oriented notation for
behavioral representation of asynchronous, direct
manipulation interface designs. Interfaces are
specified in UAN as a quasihierarchy of asynchronous
tasks. At the lower levels, user actions are associated
with feedback and system state changes. The notation
makes use of visually onomatopoeic symbols and is
simple enough to read with little instruction. UAN is
being used by growing numbers of interface developers
and researchers. In addition to its design role,
current research is investigating how UAN can support
production and maintenance of code and documentation.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Behavioral design; Constructional design; Design;
Human factors; Human-computer interface; Languages;
Representation; Representation of interfaces;
Requirements/specifications; Software engineering; Task
analysis; Tools and techniques; User interface; User
interfaces",
}
@Article{Wiecha:1990:TRD,
author = "Charles Wiecha and William Bennett and Stephen Boies
and John Gould and Sharon Greene",
title = "{ITS}: a Tool for Rapidly Developing Interactive
Applications",
journal = j-TOIS,
volume = "8",
number = "3",
pages = "204--236",
month = jul,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The ITS architecture separates applications into four
layers. The action layer implements back-end
application functions. The dialog layer defines the
content of the user interface, independent of its
style. Content specifies the objects included in each
frame of the interface, the flow of control among
frames, and what actions are associated with each
object. The style rule layer defines the presentation
and behavior of a family of interaction techniques.
Finally, the style program layer implements primitive
toolkit objects that are composed by the rule layer
into complete interaction techniques. This paper
describes the architecture in detail, compares it with
previous User Interface Management Systems and
toolkits, and describes how ITS is being used to
implement the visitor information system for EXPO'92.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Computer graphics; Design; Device independence;
Ergonomics; General; Human factors; Information systems
applications; Interaction techniques; Languages;
Management; Management of computing and information
systems; Management systems; Methodology and
techniques; Models and principles; Project and people
management; Software development; Software engineering;
Software libraries; Software maintenance; Software
management; Standardization; Systems analysis and
design; Systems development; Tools and techniques; User
interface; User interfaces; User/machine systems",
}
@Article{Vlissides:1990:UFB,
author = "John M. Vlissides and Mark A. Linton",
title = "{Unidraw}: a Framework for Building Domain-Specific
Graphical Editors",
journal = j-TOIS,
volume = "8",
number = "3",
pages = "237--268",
month = jul,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Unidraw is a framework for creating graphical editors
in domains such as technical and artistic drawing,
music composition, and circuit design. The Unidraw
architecture simplifies the construction of these
editors by providing programming abstractions that are
common across domains. Unidraw defines four basic
abstractions: components encapsulate the appearance and
behavior of objects, tools support direct manipulation
of components, commands define operations on
components, and external representations define the
mapping between components and the file format
generated by the editor. Unidraw also supports multiple
views, graphical connectivity, and dataflow between
components. This paper describes the Unidraw design,
implementation issues, and three experimental
domain-specific editors we have developed with Unidraw:
a drawing editor, a user interface builder, and a
schematic capture system. Our results indicate a
substantial reduction in implementation time and effort
compared with existing tools.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Application packages; Computer applications; Computer
graphics; Computer-aided design (CAD); Computer-aided
engineering; Design; Direct manipulation user
interfaces; Graphical constraints; Graphics utilities;
Human factors; Object-oriented graphical editors;
Software engineering; Software libraries; Tools and
techniques; User interfaces",
}
@Article{Hudson:1990:ISF,
author = "Scott E. Hudson and Shamim P. Mohamed",
title = "Interactive Specification of Flexible User Interface
Displays",
journal = j-TOIS,
volume = "8",
number = "3",
pages = "269--288",
month = jul,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "One of the problems with conventional UIMSs is that
very often there is no graphical way to specify
interfaces. This paper describes OPUS, the user
interface editor of the Penguims UIMS. This system
allows the presentation component of graphical user
interfaces to be specified interactively in a graphical
notation without explicit programming. The Penguims
UIMS supports an underlying model of computation based
loosely on spreadsheets. In particular, it supports
incremental computations based on a system of equations
(one-way constraints) over a set of named values
(spreadsheet cells). These equations are used to
provide immediate feedback at all levels of the
interface. They are used to incrementally determine the
position and dynamic appearance of the individual
interactor objects that make up the interface. They are
also used to connect the presentation directly to
underlying application data thereby supporting semantic
feedback. The OPUS user interface editor employs a
special graphical notation for specifying the
presentation component of a user interface. This
notation allows the power of the underlying
computational model to be expressed simply and quickly.
The resulting presentations are very flexible in
nature. They can automatically respond to changes in
the size and position of display objects and can
directly support derivation of their appearance from
application data objects.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Computer graphics; Constraint systems; Direct
manipulation; End-user programming; Human factors;
Interactive; Interface builders; Languages; Methodology
and techniques; Miscellaneous; Programming
environments; Rapid prototyping; Software engineering;
Tools and techniques; User interface management
systems; User interfaces",
}
@Article{Myers:1990:NMH,
author = "Brad A. Myers",
title = "A New Model for Handling Input",
journal = j-TOIS,
volume = "8",
number = "3",
pages = "289--320",
month = jul,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Although there has been important progress in models
and packages for the output of graphics to computer
screens, there has been little change in the way that
input from the mouse, keyboard, and other input devices
is handled. New graphics standards are still using a
fifteen-year-old model even though it is widely
accepted as inadequate, and most modern window managers
simply return a stream of low-level, device-dependent
input events. This paper presents a new model that
handles input devices for highly interactive, direct
manipulation, graphical user interfaces, which could be
used in future toolkits, window managers, and graphics
standards. This model encapsulates interactive
behaviors into a few ``Interactor'' object types.
Application programs can then create instances of these
Interactor objects which hide the details of the
underlying window manager events. In addition,
Interactors allow a clean separation between the input
handling, the graphics, and the application programs.
This model has been extensively used as part of the
Garnet system and has proven to be convenient,
efficient, and easy to learn.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Computer graphics; Direct manipulation; Human factors;
Input devices; Interaction; Interaction techniques;
Methodology and techniques; Model-view controller;
Object-oriented design; Software engineering; Tools and
techniques; User interface management systems; User
interfaces",
}
@Article{Mylopoulos:1990:TRK,
author = "John Mylopoulos and Alex Borgida and Matthias Jarke
and Manolis Koubarakis",
title = "Telos: Representing Knowledge About Information
Systems",
journal = j-TOIS,
volume = "8",
number = "4",
pages = "325--362",
month = oct,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We describe Telos, a language intended to support the
development of information systems. The design
principles for the language are based on the premise
that information system development is knowledge
intensive and that the primary responsibility of any
language intended for the task is to be able to
formally represent the relevant knowledge. Accordingly,
the proposed language is founded on concepts from
knowledge representation. Indeed, the language is
appropriate for representing knowledge about a variety
of worlds related to an information system, such as the
subject world (application domain), the usage world
(user models, environments), the system world (software
requirements, design), and the development world
(teams, methodologies). We introduce the features of
the language through examples, focusing on those
provided for describing metaconcepts that can then be
used to describe knowledge relevant to a particular
information system. Telos' features include an
object-centered framework which supports aggregation,
generalization, and classification; a novel treatment
of attributes; an explicit representation of time; and
facilities for specifying integrity constraints and
deductive rules. We review actual applications of the
language through further examples, and we sketch a
formalization of the language.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Artificial intelligence; Belief time; Class; Deductive
rules; Design; General; History time; Instance;
Integrity constraints; Knowledge base; Knowledge
representation formalisms and methods; Languages;
Management of computing and information systems;
Metaclass; Methodologies; Models and principles;
Predicate logic; Proposition; Representation;
Representation languages; Requirements/specifications;
Semantic networks; Software development; Software
engineering; Software management; Temporal knowledge",
wwwpages = "363--386",
wwwtitle = "{Telos}: a Language for Representing Knowledge About
Information Systems",
}
@Article{Kwok:1990:ECT,
author = "K. L. Kwok",
title = "Experiments with a Component Theory of Probabilistic
Information Retrieval Based on Single Terms as Document
Components",
journal = j-TOIS,
volume = "8",
number = "4",
pages = "363--386",
month = oct,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "A component theory of information retrieval using
single content terms as component for queries and
documents was reviewed and experimented with. The
theory has the advantages of being able to (1)
bootstrap itself, that is, define initial term weights
naturally based on the fact that items are
self-relevant; (2) make use of within-item term
frequencies; (3) account for query-focused and
document-focused indexing and retrieval strategies
cooperatively; and (4) allow for component-specific
feedback if such information is available. Retrieval
results with four collections support the effectiveness
of all the first three aspects, except for predictive
retrieval. At the initial indexing stage, the retrieval
theory performed much more consistently across
collections than Croft's model and provided results
comparable to Salton's tf*idf approach. An inverse
collection term frequency (ICTF) formula was also
tested that performed much better than the inverse
document frequency (IDF). With full feedback
retrospective retrieval, the component theory performed
substantially better than Croft's, because of the
highly specific nature of document-focused feedback.
Repetitive retrieval results with partial relevance
feedback mirrored those for the retrospective. However,
for the important case of predictive retrieval using
residual ranking, results were not unequivocal.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Content analysis and indexing; Document-focused and
query-focused relevance feedback; Experimentation;
Indexing and retrieval; Indexing methods; Inf. storage
and retrieval; Information search and retrieval;
Information storage and retrieval; Inverse collection
term frequency weighting; Inverse document frequency
weighting; Probabilistic indexing; Probabilistic
retrieval; Ranking and weighting of composite objects;
Retrieval models; Theory",
wwwpages = "325-362",
}
@Article{Straube:1990:QQP,
author = "Dave D. Straube and M. Tamer {\"O}zsu",
title = "Queries and Query Processing in Object-Oriented
Database Systems",
journal = j-TOIS,
volume = "8",
number = "4",
pages = "387--430",
month = oct,
year = "1990",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Object-oriented database management systems (OODBMS)
combine the data abstraction and computational models
of object-oriented programming languages with the query
and performance capabilities of database management
systems. A concise, formal data model for OODBMS has
not been universally accepted, preventing detailed
investigation of various system issues such as query
processing. We define a data model that captures the
essence of classification-based object-oriented systems
and formalize concepts such as object identity,
inheritance, and methods. The main topic of the paper
is the presentation of a query processing methodology
complete with an object calculus and a closed object
algebra. Query processing issues such as query safety
and object calculus to object algebra translation are
discussed in detail. The paper concludes with a
discussion of equivalence-preserving transformation
rules for object algebra expressions.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Abstract data types; Algorithms; Data models; Data
types and structures; Database management; Design;
Language constructs; Languages; Logical design; Modules
and packages; Object algebra; Object calculus;
Object-oriented databases; Programming languages; Query
languages; Query processing; Query transformation
rules; Systems",
wwwauthor = "D. D. Straube and M. T. Ozsu",
wwwpages = "387-428",
wwwtitle = "Queriers and Query Processing in Object-Oriented
Database Systems",
}
@Article{Ford:1991:OPH,
author = "Daniel Alexander Ford and Stavros Christodoulakis",
title = "Optimal Placement of High Probability Randomly
Retrieved Blocks on {CLV} Optical Discs",
journal = j-TOIS,
volume = "9",
number = "1",
pages = "1--30",
month = jan,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Optimal data placement on a CLV (Constant Linear
Velocity) format optical disc has as an objective the
minimization of the expected access cost of data
retrieval from the disc when the probabilities of
access of data items may be different. The problem of
optimal data placement for optical discs is both more
important and more difficult than the corresponding
problem on magnetic disks. A good data placement on
optical discs is more important because data sets on
optical discs such as WORM and CD ROM cannot be
modified or moved once they are placed on the disc.
Currently, even rewritable optical discs are best
suited for applications that are archival in nature.
The problem of optimal data placement on CLV format
optical discs is more difficult, mainly because the
useful storage space is not uniformly distributed
across the disc surface (along a radius). This leads to
a complicated positional performance trade-off not
present for magnetic disks. We present a model that
encompasses all the important aspects of the placement
problem on CLV format optical discs. The model takes
into account the nonuniform distribution of useful
storage, the dependency of the rotational delay on disc
position, a parameterized seek cost function for
optical discs, and the varying access probabilities of
data items. We show that the optimal placement of
high-probability blocks satisfies a unimodality
property. Based on this observation, we solve the
optimal placement problem. We then study the impact of
the relative weights of the problem parameters and show
that the optimal data placement may be very different
from the optimal data placement on magnetic disks. We
also validate our model and analysis and give an
algorithm for computing the placement of disc
sectors.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Access methods; CD-ROM; Clustering; CLV; Constant
linear velocity; Data placement; Database management;
Design; Design styles; Information search and
retrieval; Information storage and retrieval;
Management; Mass storage; MCAV; MCLV; Memory
structures; Operating systems; Optical discs; Optical
disks; Performance; Physical database design; Physical
design; Retrieval performance; Secondary storage
devices; Storage management",
wwwauthor = "S. Christodoulakis and D. A. Ford",
}
@Article{Kim:1991:DOO,
author = "Won Kim and Nat Ballou and Jorge F. Garza and Darrell
Woelk",
title = "A Distributed Object-Oriented Database System
Supporting Shared and Private Databases",
journal = j-TOIS,
volume = "9",
number = "1",
pages = "31--51",
month = jan,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "ORION-2 is a commercially available, federated,
object-oriented database management system designed and
implemented at MCC. One major architectural innovation
in ORION-2 is the coexistence of a shared database and
a number of private databases. The shared database is
accessible to all authorized users of the system, while
each private database is accessible to only the user
who owns it. A distributed database system with a
shared database and private databases for individual
users is a natural architecture for data-intensive
application environments on a network of workstations,
notably computer-aided design and engineering systems.
This paper discusses the benefits and limitations of
such a system and explores the impact of such an
architecture on the semantics and implementation of
some of the key functions of a database system, notably
queries, database schema, and versions. Although the
issues are discussed in the context of an
object-oriented data model, the results (at least
significant portions thereof) are applicable to
database systems supporting other data models.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Client-server architecture; Database management;
Design; Distr. systems; Experimentation; Federated
databases; Object-oriented databases; Sys.",
wwwauthor = "W. Kim and N. Ballou and J. F. Garza and D. Woelk",
}
@Article{Mak:1991:EPP,
author = "Victor Wing-Kit Mak and Chu Lee Kuo and Ophir
Frieder",
title = "Exploiting Parallelism in Pattern Matching: An
Information Retrieval Application",
journal = j-TOIS,
volume = "9",
number = "1",
pages = "52--74",
month = jan,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We propose a document-searching architecture based on
high-speed hardware pattern matching to increase the
throughput of an information retrieval system. We also
propose a new parallel VLSI pattern-matching algorithm
called the Data Parallel Pattern Matching (DPPM)
algorithm, which serially broadcasts and compares the
pattern to a block of data in parallel. The DPPM
algorithm utilizes the high degree of integration of
VLSI technology to attain very high-speed processing
through parallelism. Performance of the DPPM has been
evaluated both analytically and by simulation. Based on
the simulation statistics and timing analysis on the
hardware design, a search rate of multiple gigabytes
per second is achievable using
2-$\lbrace$micro$\rbrace$m CMOS technology. The
potential performance of the proposed
document-searching architecture is also analyzed using
the simulation statistics of the DPPM algorithm.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Algorithms; Algorithms implemented in hardware;
Analysis of algorithms and problem complexity;
Arithmetic and logic structures; Computer systems
organization; Data; Design; Design studies; Design
styles; DPPM; Files; Information search and retrieval;
Information storage and retrieval; Integrated circuits;
Modeling techniques; Multiple data stream architecture;
Nonnumerical algorithms and problems; Parallel; Pattern
matcher; Pattern matching; Performance; Performance of
systems; Processor architectures; Search process;
Selection process; SIMD; Sorting and searching;
Sorting/searching; Types and design styles; VLSI",
}
@Article{Aiken:1991:IES,
author = "Milam W. Aiken and Olivia R. Liu Sheng and Douglas R.
Vogel",
title = "Integrating Expert Systems With Group Decision Support
Systems",
journal = j-TOIS,
volume = "9",
number = "1",
pages = "75--95",
month = jan,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Expert systems are powerful tools that serve as
adjuncts to decision making and have found wide
applicability in a variety of areas. Integrating expert
systems with group decision support systems has the
potential to enhance the quality and efficiency of
group communication, negotiation, and collaborative
work. This paper examines possible synergies between
the two technologies and provides a survey of current
partially-integrated systems. Finally, a prototype
design of a highly-integrated system is described with
directions for further research.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Applications and expert systems; Artificial
intelligence; Communications applications; Expert
systems; Group decision support systems; Inf. systems
applications; Knowledge-based systems",
}
@Article{Allen:1991:ECH,
author = "Robert B. Allen",
title = "Editorial: Computer-Human Interaction and {ACM TOIS}",
journal = j-TOIS,
volume = "9",
number = "2",
pages = "97--98",
month = apr,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Human Interaction.",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Card:1991:MAD,
author = "Stuart K. Card and Jock D. Mackinlay and George G.
Robertson",
title = "A Morphological Analysis of the Design Space of Input
Devices",
journal = j-TOIS,
volume = "9",
number = "2",
pages = "99--122",
month = apr,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Human Interaction.",
URL = "http://www.acm.org:80",
abstract = "The market now contains a bewildering variety of input
devices for communication from humans to computers.
This paper discusses a means to systematize these
devices through morphological design space analysis, in
which different input device designs are taken as
points in a parametrically described design space. The
design space is characterized by finding methods to
generate and test design points. In a previous paper,
we discussed a method for generating the space of input
device designs using primitive and compositional
movement operators. This allowed us to propose a
taxonomy of input devices. In this paper, we summarize
the generation method and explore the use of device
footprint and Fitts's law as a test. We then use
calculations to reason about the design space.
Calculations are used to show why the mouse is a more
effective device than the headmouse and where in the
design space there is likely to be a more effective
device than the mouse.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Computer applications; Computer-aided design;
Computer-aided engineering; Design; Design knowledge
systematization; Design rationale; Design space; Human
factors; Input devices; Models and principles;
Morphological analysis; Semantics; User/machine
systems",
wwwtitle = "The Design Space of Input Devices",
}
@Article{Fischer:1991:RCC,
author = "Gerhard Fischer and Andreas C. Lemke and Thomas
Mastaglio and Anders I. Morch",
title = "The Role of Critiquing in Cooperative Problem
Solving",
journal = j-TOIS,
volume = "9",
number = "2",
pages = "123--151",
month = apr,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Human Interaction.",
URL = "http://www.acm.org:80",
abstract = "Cooperative problem-solving systems help users design
solutions themselves as opposed to having solutions
designed for them. Critiquing -- presenting a reasoned
opinion about a user's product or action -- is a major
activity of a cooperative problem-solving system.
Critics make the constructed artifact ``talk back'' to
the user. Conditions under which critics are more
appropriate than autonomous expert systems are
discussed. Critics should be embedded in integrated
design environments along with other components, such
as an argumentative hypertext system, a specification
component, and a catalog. Critics support learning as a
by-product of problem solving. The major subprocesses
of critiquing are goal acquisition, product analysis,
critiquing strategies, adaptation capability,
explanation and argumentation, and advisory capability.
The generality of the critiquing approach is
demonstrated by discussing critiquing systems developed
in our group and elsewhere. Limitations of many current
critics include their inability to learn about specific
user goals and their intervention strategies.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Computer applications; Computer uses in education;
Computer-aided design; Computer-aided engineering;
Computers and education; Cooperative problem-solving
systems; Critics; Critiquing; Design; Design
environments; High-functionality computer systems;
Human factors; Inf. storage and retrieval; Information
search and retrieval; Intelligent support systems;
Models and principles; User/machine systems",
}
@Article{Jacob:1991:UEM,
author = "Robert J. K. Jacob",
title = "The Use of Eye Movements in Human-Computer Interaction
Techniques: What You Look At Is What You Get",
journal = j-TOIS,
volume = "9",
number = "2",
pages = "152--169",
month = apr,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Human Interaction.",
URL = "http://www.acm.org:80",
abstract = "In seeking hitherto-unused methods by which users and
computers can communicate, we investigate the
usefulness of eye movements as a fast and convenient
auxiliary user-to-computer communication mode. The
barrier to exploiting this medium has not been
eye-tracking technology but the study of interaction
techniques that incorporate eye movements into the
user-computer dialogue in a natural and unobtrusive
way. This paper discusses some of the human factors and
technical considerations that arise in trying to use
eye movements as an input medium, describes our
approach and the first eye movement-based interaction
techniques that we have devised and implemented in our
laboratory, and reports our experiences and
observations on them.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Design; Eye movements; Eye tracking; Human factors;
Human-computer interaction; Information interfaces and
presentation; Input; Input devices and strategies;
Interaction styles; Models and principles; Software
engineering; State transition diagram; Tools and
techniques; UIMS; User interface management system;
User interfaces; User/machine systems",
}
@Article{Tang:1991:VVI,
author = "John C. Tang and Scott L. Minneman",
title = "{VideoDraw}: a Video Interface for Collaborative
Drawing",
journal = j-TOIS,
volume = "9",
number = "2",
pages = "170--184",
month = apr,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Human Interaction.",
URL = "http://www.acm.org:80",
abstract = "This paper describes VideoDraw, a shared drawing tool,
and the process by which it is being designed and
developed. VideoDraw is a video-based prototype tool
that provides a shared ``virtual sketchbook'' among two
or more collaborators. It not only allows the
collaborators to see each others' drawings, but also
conveys the accompanying hand gestures and the process
of creating and using those drawings. Its design stems
from studying how people collaborate using shared
drawing spaces. Design implications raised by those
studies were embodied in a prototype, which was
subsequently observed in use situations. Further
research studying the use of VideoDraw (in comparison
with other collaborative media) will lead to a better
understanding of collaborative drawing activity and
inform the continued technical development of tools to
support collaborative drawing.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Collaborative systems; Communications applications;
Computer graphics; Computer-communication networks;
Design; Distr. applications; Distr. systems;
Distributed/network graphics; Gestural interfaces;
Graphics systems; Information systems applications;
Shared drawing; Teleconferencing; User interface; Video
technology; Work practice analysis",
}
@Article{Croft:1991:E,
author = "W. Bruce Croft",
title = "Editorial",
journal = j-TOIS,
volume = "9",
number = "3",
pages = "185--186",
month = jul,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Turtle:1991:EIN,
author = "Howard Turtle and W. Bruce Croft",
title = "Evaluation of an Inference Network=based Retrieval
Model",
journal = j-TOIS,
volume = "9",
number = "3",
pages = "187--222",
month = jul,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "The use of inference networks to support document
retrieval is introduced. A network-based retrieval
model is described and compared to conventional
probabilistic and Boolean models. The performance of a
retrieval system based on the inference network model
is evaluated and compared to performance with
conventional retrieval models.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Document retrieval; Experimentation; General; Inf.
storage and retrieval; Inference networks; Information
search and retrieval; Information storage and
retrieval; Miscellaneous; Network retrieval models;
Performance; Retrieval models; Theory",
}
@Article{Fuhr:1991:PLA,
author = "Norbert Fuhr and Chris Buckley",
title = "A Probabilistic Learning Approach for Document
Indexing",
journal = j-TOIS,
volume = "9",
number = "3",
pages = "223--248",
month = jul,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "We describe a method for probabilistic document
indexing using relevance feedback data that has been
collected from a set of queries. Our approach is based
on three new concepts: (1) Abstraction from specific
terms and documents, which overcomes the restriction of
limited relevance information for parameter estimation.
(2) Flexibility of the representation, which allows the
integration of new text analysis and knowledge-based
methods in our approach as well as the consideration of
document structures or different types of terms. (3)
Probabilistic learning or classification methods for
the estimation of the indexing weights making better
use of the available relevance information. Our
approach can be applied under restrictions that hold
for real applications. We give experimental results for
five test collections which show improvements over
other methods.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Approximation; Artificial intelligence; Complex
document representation; Content analysis and indexing;
Experimentation; Indexing methods; Information search
and retrieval; Information storage and retrieval;
Learning; Least squares approximation; Linear indexing
functions; Linear retrieval functions; Numerical
analysis; Parameter learning; Probabilistic indexing;
Probabilistic retrieval; Relevance descriptions;
Retrieval models; Theory",
}
@Article{Gauch:1991:SIA,
author = "Susan Gauch and John B. Smith",
title = "Search Improvement via Automatic Query Reformulation",
journal = j-TOIS,
volume = "9",
number = "3",
pages = "249--280",
month = jul,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "Users of online retrieval systems experience many
difficulties, particularly with search tactics. User
studies have indicated that searchers use vocabulary
incorrectly and do not take full advantage of iteration
to improve their queries. To address these problems, an
expert system for online search assistance was
developed. This prototype augments the searching
capabilities of novice users by providing automatic
query reformulation to improve the search results, and
automatic ranking of the retrieved passages to speed
the identification of relevant information. Users'
search performance using the expert system was compared
with their search performance on their own, and their
search performance using an online thesaurus. The
following conclusions were reached: (1) the expert
system significantly reduced the number of queries
necessary to find relevant passages compared with the
user searching alone or with the thesaurus. (2) The
expert system produced marginally significant
improvements in precision compared with the user
searching on their own. There was no significant
difference in the recall achieved by the three system
configurations. (3) Overall, the expert system ranked
relevant passages above irrelevant passages.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Applications and expert systems; Artificial
intelligence; Expert systems; Full-text information
retrieval; Human factors; Inf. storage and retrieval;
Information search and retrieval; Models and
principles; Online search assistance; Query
reformulation; Search process; Textbases; User/machine
system",
}
@Article{Fox:1991:OPM,
author = "Edward A. Fox and Qi Fan Chen and Amjad M. Daoud and
Lenwood S. Heath",
title = "Order Preserving Minimal Perfect Hash Functions and
Information Retrieval",
journal = j-TOIS,
volume = "9",
number = "3",
pages = "281--308",
month = jul,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Research and Development in
Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "Rapid access to information is essential for a wide
variety of retrieval systems and applications. Hashing
has long been used when the fastest possible direct
search is desired, but is generally not appropriate
when sequential or range searches are also required.
This paper describes a hashing method, developed for
collections that are relatively static, that supports
both direct and sequential access. The algorithms
described give hash functions that are optimal in terms
of time and hash table space utilization, and that
preserve any a priori ordering desired. Furthermore,
the resulting order-preserving minimal perfect hash
functions (OPMPHFs) can be found using time and space
that are linear in the number of keys involved; this is
close to optimal.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Access methods; Algorithms; Content analysis and
indexing; Data; Data storage representations; Database
management; Dictionary structure; Experimentation; File
organization; Hash table representations; Indexing;
Indexing methods; Information storage; Information
storage and retrieval; Inverted file structures;
Minimal perfect hashing; Perfect hashing; Physical
design; Random graph",
}
@Article{Siochi:1991:CAU,
author = "Antonio C. Siochi and Roger W. Ehrich",
title = "Computer Analysis of User Interfaces Based on
Repetition in Transcripts of User Sessions",
journal = j-TOIS,
volume = "9",
number = "4",
pages = "309--335",
month = oct,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "It is generally acknowledged that the production of
quality user interfaces requires a thorough
understanding of the user and that this involves
evaluating the interface by observing the user working
with the system, or by performing human factors
experiments. Such methods traditionally involve the use
of videotape, protocol analysis, critical incident
analysis, etc. These methods require time consuming
analyses and may be invasive. In addition, the data
obtained through such methods represent a relatively
small portion of the use of a system. An alternative
approach is to record all user input and system output
(i.e., log the user session). Such transcripts can be
collected automatically and noninvasively over a long
period of time. Unfortunately this produces voluminous
amounts of data. There is therefore a need for tools
and techniques that allow an evaluator to identify
potential performance and usability problems from such
data. It is hypothesized that repetition of user
actions is an important indicator of potential user
interface problems. This research reports on the use of
the repetition indicator as a means of studying user
session transcripts in the evaluation of user
interfaces. The paper discusses the interactive tool
constructed, the results of an extensive application of
the technique in the evaluation of a large
image-processing system, and extensions and refinements
to the technique. Evidence suggests that the hypothesis
is justified and that such a technique is convincingly
useful.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Evaluation/methodology; Human factors; Inf. interfaces
and presentation; Maximal repeating patterns;
Measurement; Repeated usage patterns; Software
engineering; Tools and techniques; Transcript analysis;
Usability; User interface evaluation; User interface
management systems; User interfaces",
}
@Article{Zezula:1991:DPS,
author = "P. Zezula and F. Rabitti and P. Tiberio",
title = "Dynamic Partitioning of Signature Files",
journal = j-TOIS,
volume = "9",
number = "4",
pages = "336--369",
month = oct,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The signature file access method has proved to be a
convenient indexing technique, in particular for text
data. Because it can deal with unformatted data, many
application domains have shown interest in signature
file techniques, e.g., office information systems,
statistical and logic databases. We argue that
multimedia databases should also take advantage of this
method, provided convenient storage structures for
organizing signature files are available. Our main
concern here is the dynamic organization of signatures
based on a partitioning paradigm called Quick Filter. A
signature file is partitioned by a hashing function and
the partitions are organized by linear hashing.
Thorough performance evaluation of the new scheme is
provided, and it is compared with single-level and
multilevel storage structures. Results show that quick
filter is economical in space and very convenient for
applications dealing with large files of dynamic data,
and where user queries result in signatures with high
weights. These characteristics are particularly
interesting for multimedia databases, where integrated
access to attributes, text and images must be
provided.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Access methods; Data; Database management; Design;
Dynamic data; File organization; Files; Hashing;
Information retrieval; Information storage; Information
storage and retrieval; Information systems
applications; Multimedia data; Office automation;
Organization / structure; Performance; Performance
evaluation; Physical design; Signature file
partitioning",
}
@Article{Hart:1991:ION,
author = "Paul Hart and Deborah Estrin",
title = "Inter-Organization Networks, Computer Integration, and
Shifts in Interdependence: The Case of the
Semiconductor Industry",
journal = j-TOIS,
volume = "9",
number = "4",
pages = "370--398",
month = oct,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Inter-organization computer networks (IONs) provide
significant opportunities for improving coordination
between firms engaged in mutually dependent activities.
A field study of the use and impact of IONs in the
semiconductor industry is presented in this paper.
Eighty-two interviews were conducted in twelve firms
(seven semiconductor producers and five merchant mask
shops) providing data on current as well as anticipated
ION use. We found that greater efficiencies are
possible when IONs are used as substitutes for
conventional media. But more effective ION use is
achievable when internal computer integration within
participating firms is implemented. The implication of
this otherwise straightforward observation is that
firms using computer networks only as a substitute for
conventional methods of exchange will not achieve the
degree of inter-organization coordination IONs can
support. However, while IONs improve coordination and
reduce some production and transaction costs, they
simultaneously increase certain costs associated with
establishing and maintaining contracts with customers.
These costs are new dependencies. Dependencies emerge
from using IONs to access computer resources, and
information generated by those resources, located in
other firms. In this way IONs increase
interorganization coordination and vulnerability
simultaneously. The long term implication of ION
adoption is that their use shifts the nature of
interdependence between participating firms.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Communications applications; Computer applications;
Computer integration; Computer system implementation;
Computer-communication networks; Computers and society;
Computers in other systems; Consumer products;
Electronic mail; Gate arrays; Information systems
applications; Integrated circuits; Inter-organization
computer networks; Inter-organization relationships;
Management; Management of computing and information
systems; Miscellaneous; Network management; Network
operations; Organizational impacts; Performance;
Project and people management; Standard cells; Systems
development; Types and design styles",
wwwpages = "399-419",
wwwtitle = "Inter-Organization Networks, Computer Integration,
Shift in Interdependence: The Case of the Semiconductor
Industry",
}
@Article{Kacmar:1991:PPO,
author = "Charles J. Kacmar and John J. Leggett",
title = "{PROXHY}: a Process-Oriented Extensible Hypertext
Architecture",
journal = j-TOIS,
volume = "9",
number = "4",
pages = "399--419",
month = oct,
year = "1991",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
http://liinwww.ira.uka.de/bibliography/Database/Graefe.html;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "This paper describes the design and prototypical
implementation of an architecture for hypertext systems
which is based on the process and object-oriented
models of computation. Hypertext services are provided
to applications through object-based distributed
processes which interact using interprocess
communication facilities. By merging the process,
object-oriented, and hypertext models, hypertext data
and functionality can be separated from applications
and distributed across a network. This architecture
allows links to cross application boundaries and
diverse applications to be integrated under a common
hypertext model. The paper describes the architecture
and application requirements for operating in this
environment. PROXHY, a prototypical implementation of
the architecture, is also discussed.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Computer-communication networks; Database management;
Design; Distr. applications; Distr. systems;
Distributed systems; Document preparation; Hypermedia
system architecture; Hypertext navigation and maps;
Hypertext/hypermedia; Information interfaces and
presentation; Information storage and retrieval;
Interactive system; Management; Multimedia information
systems; Object-oriented programming; Operating
systems; Organization and design; Programming
techniques; Systems; Systems and software; Text
processing",
}
@Article{Jarke:1992:DEE,
author = "M. Jarke and J. Mylopoulos and J. W. Schmidt and Y.
Vassiliou",
title = "{DAIDA}: An Environment for Evolving Information
Systems",
journal = j-TOIS,
volume = "10",
number = "1",
pages = "1--50",
month = jan,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We present a framework for the development of
information systems based on the premise that the
knowledge that influences the development process needs
to somehow be captured, represented, and managed if the
development process is to be rationalized. Experiences
with a prototype environment developed in ESPRIT
project DAIDA demonstrate the approach. The project has
implemented an environment based on state-of-the-art
languages for requirements modeling, design and
implementation of information systems. In addition, the
environment offers tools for aiding the mapping process
from requirements to design and then to implementation,
also for representing decisions reached during the
development process. The development process itself is
represented explicitly within the system, thus making
the DAIDA development framework easier to comprehend,
use, and modify.",
acknowledgement = ack-nhfb,
affiliation = "RWTH Aachen",
affiliationaddress = "Aachen, Ger",
classification = "723.1; 723.1.1; 723.2; 723.3; 903.3; 921",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computational methods; Computer aided software
engineering; Computer programming languages; Computer
software; Computer software selection and evaluation;
Conformal mapping; Data dictionary; Data structures;
Database systems; Design languages; Information
retrieval systems; Information science; Knowledge based
systems; Management information systems; Mapping
assistant; Multilevel specification; Quality assurance;
Repository; Software information system; Software
process model; Software quality assurance",
wwwtitle = "{DAIDA}: a Knowledge-Based Environment for Developing
Information Systems",
}
@Article{Gemmell:1992:PDS,
author = "Jim Gemmell and Stavros Christodoulakis",
title = "Principles of Delay Sensitive Multi-media Data Storage
and Retrieval",
journal = j-TOIS,
volume = "10",
number = "1",
pages = "51--90",
month = jan,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "This paper establishes some fundamental principles for
the retrieval and storage of delay-sensitive multimedia
data. Delay-sensitive data include digital audio,
animations, and video. Retrieval of these data types
from secondary storage has to satisfy certain time
constraints in order to be acceptable to the user. The
presentation is based on digital audio in order to
provide intuition to the reader, although the results
are applicable to all delay-sensitive data. A
theoretical framework is developed for the real-time
requirements of digital audio playback. We show how to
describe these requirements in terms of the consumption
rate of the audio data and the nature of the
data-retrieval rate from secondary storage. Making use
of this framework, bounds are derived for buffer space
requirements for certain common retrieval scenarios.
Storage placement strategies for multichannel
synchronized data are then categorized and examined.
The results presented in this paper are basic to any
playback of delay-sensitive data and should assist the
multimedia system designer in estimating hardware
requirements and in evaluating possible design
choices.",
acknowledgement = ack-nhfb,
affiliation = "Simon Fraser Univ",
affiliationaddress = "Burnaby, BC, Can",
classification = "716.1; 723.2; 723.3; 741.3; 752.2; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Continuous media; Data processing; Data recording;
Data storage equipment; Database systems; Delay
sensitive data; Digital audio playback; Digital signal
processing; Image processing; Information retrieval
systems; Multimedia information systems; Parameter
estimation; Real time systems; Stereophonic
recordings",
}
@Article{Want:1992:ABL,
author = "Roy Want and Andy Hopper and Veronica Falcao and
Jonathan Gibbons",
title = "The Active Badge Location System",
journal = j-TOIS,
volume = "10",
number = "1",
pages = "91--102",
month = jan,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "A novel system for the location of people in an office
environment is described. Members of staff wear badges
that transmit signals providing information about their
location to a centralized location service, through a
network of sensors. The paper also examines alternative
location techniques, system design issues and
applications, particularly relating to telephone call
routing. Location systems raise concerns about the
privacy of an individual, and these issues are also
addressed.",
acknowledgement = ack-nhfb,
affiliation = "Olivetti Research Ltd",
affiliationaddress = "Cambridge, Engl",
classification = "716.1; 718.1; 722.3; 723.2; 723.3; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Active badges; Computer networks; Data communication
equipment; Data communication systems; Database
systems; Digital communication systems; Information
retrieval systems; Location; Location systems;
Multiplexing equipment; Office automation; Privacy
issues; Security of data; Sensors; Tagging systems",
}
@Article{Grudin:1992:CSF,
author = "Jonathan Grudin",
title = "Consistency, Standards, and Formal Approaches to
Interface Development and Evaluation: a Note on
{Wiecha}, {Bennett}, {Boies}, {Gould}, And {Greene}",
journal = j-TOIS,
volume = "10",
number = "1",
pages = "103--111",
month = jan,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wiecha:1992:UIC,
author = "Charles Wiecha",
title = "{ITS} and User Interface Consistency: a Response to
{Grudin}",
journal = j-TOIS,
volume = "10",
number = "1",
pages = "112--114",
month = jan,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Krovetz:1992:LAI,
author = "Robert Krovetz and W. Bruce Croft",
title = "Lexical Ambiguity and Information Retrieval",
journal = j-TOIS,
volume = "10",
number = "2",
pages = "115--141",
month = apr,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Lexical ambiguity is a pervasive problem in natural
language processing. However, little quantitative
information is available about the extent of the
problem or about the impact that it has on information
retrieval systems. We report on an analysis of lexical
ambiguity in information retrieval test collections and
on experiments to determine the utility of word
meanings for separating relevant from nonrelevant
documents. The experiments show that there is
considerable ambiguity even in a specialized database.
Word senses provide a significant separation between
relevant and nonrelevant documents, but several factors
contribute to determining whether disambiguation will
make an improvement in performance. For example,
resolving lexical ambiguity was found to have little
impact on retrieval effectiveness for documents that
have many words in common with the query. Other uses of
word sense disambiguation in an information retrieval
context are discussed.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Massachusetts",
affiliationaddress = "Amherst, MA, USA",
classification = "721.1; 723.2; 723.4; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Computational linguistics;
Data processing; Disambiguation; Indexing (of
information); Information retrieval systems; Lexical
ambiguity; Linguistics; Natural language processing
systems; Semantically based search; Terminology; Word
senses",
}
@Article{Botafogo:1992:SAH,
author = "Rodrigo A. Botafogo and Ehud Rivlin and Ben
Shneiderman",
title = "Structural Analysis of Hypertexts: Identifying
Hierarchies and Useful Metrics",
journal = j-TOIS,
volume = "10",
number = "2",
pages = "142--180",
month = apr,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Hypertext users often suffer from the `lost in
hyperspace' problem: disorientation from too many jumps
while traversing a complex network. One solution to
this problem is improved authoring to create more
comprehensible structures. This paper proposes several
authoring tools, based on hypertext structure analysis.
In many hypertext systems authors are encouraged to
create hierarchical structures, but when writing, the
hierarchy is lost because of the inclusion of
cross-reference links. The first part of this paper
looks at ways of recovering lost hierarchies and
finding new ones, offering authors different views of
the same hypertext. The second part helps authors by
identifying properties of the hypertext document.
Multiple metrics are developed including compactness
and stratum. Compactness indicates the intrinsic
connectedness of the hypertext, and stratum reveals to
what degree the hypertext is organized so that some
nodes must be read before others. Several existing
hypertexts are used to illustrate the benefits of each
technique. The collection of techniques provides a
multifaceted view of the hypertext, which should allow
authors to reduce undesired structural complexity and
create documents that readers can traverse more
easily.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Maryland",
affiliationaddress = "College Park, MD, USA",
classification = "461.4; 723.2; 903.3; 921",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer networks; Data reduction; Data structures;
Graph theory; Hierarchical systems; Human engineering;
Hypertext systems; Information retrieval; Man machine
systems; Metrics; User interfaces",
}
@Article{Carroll:1992:GAT,
author = "John M. Carroll and Mary Beth Rosson",
title = "Getting Around the Task-Artifact Cycle: How to Make
Claims and Design by Scenario",
journal = j-TOIS,
volume = "10",
number = "2",
pages = "181--212",
month = apr,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We are developing an `action science' approach to
human-computer interaction (HCI), seeking to better
integrate activities directed at understanding with
those directed at design. The approach leverages
development practices of current HCI with methods and
concepts to support a shift toward using broad and
explicit design rationale to reify where we are in a
design process, why we are there, and to guide
reasoning about where we might go from there. We
represent a designed artifact as the set of user
scenarios supported by that artifact and more finely by
causal schemas detailing the underlying psychological
rationale. These schemas, called claims, unpack
wherefores and whys of the scenarios. In this paper, we
stand back from several empirical projects to clarify
our commitments and practices.",
acknowledgement = ack-nhfb,
affiliation = "IBM Thomas J. Watson Research Cent",
affiliationaddress = "Yorktown Heights, NY, USA",
classification = "461.4; 723.5; 921",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer aided software engineering; Design rationale;
Human computer interaction (HCI); Human engineering;
Man machine systems; Mathematical models; Software
engineering; User interfaces",
}
@Article{Blake:1992:SOE,
author = "G. Elizabeth Blake and Tim Bray and Frank Wm. Tompa",
title = "Shortening the {OED}: {Experience} with a
Grammar-Defined Database",
journal = j-TOIS,
volume = "10",
number = "3",
pages = "213--232",
month = jul,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Textual databases with highly variable structure can
be usefully described by a grammar-defined model. One
example of such a text is the Oxford English
Dictionary. This paper describes a first attempt to
apply technology based on this model to a real problem.
A language called GOEDEL, which is a partial
implementation of a set of grammar-defined database
operators, was used to extract and alter a subset of
the OED in order to assist the editors in their
production of The Shorter Oxford English Dictionary.
The implementation of the pstring data structure to
describe a piece of text and the functions that operate
on this pstring are illustrated with some detailed
examples. The project was judged a success and the
resulting program used in production by the Oxford
University Press.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Waterloo",
affiliationaddress = "Waterloo, Ont, Can",
classification = "721.1; 723.2; 723.3; 903.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computational grammars; Computational linguistics;
Data structures; Database systems; Formal languages;
Goedel formal language; Grammar defined model; Oxford
English Dictionary; Parsed string; Pstring data
structure; Shorter Oxford English Dictionary;
Terminology; Text databases",
}
@Article{Palaniappan:1992:EFO,
author = "Murugappan Palaniappan and Nicole Yankelovich and
George Fitzmaurice and Anne Loomis and Bernard Haan and
James Coombs and Norman Meyrowitz",
title = "The Envoy Framework: An Open Architecture for Agents",
journal = j-TOIS,
volume = "10",
number = "3",
pages = "233--264",
month = jul,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The Envoy Framework addresses a need for
computer-based assistants or agents that operate in
conjunction with users' existing applications, helping
them perform tedious, repetitive, or time-consuming
tasks more easily and efficiently. Envoys carry out
missions for users by invoking envoy-aware applications
called operatives and inform users of mission results
via envoy-aware applications called informers. The
distributed, open architecture developed for Envoys is
derived from an analysis of the best characteristics of
existing agent systems. This architecture has been
designed as a model for how agent technology can be
seamlessly integrated into the electronic desktop. It
defines a set of application programmer's interfaces so
that developers may convert their software to
envoy-aware applications. A subset of the architecture
described in this paper has been implemented in an
Envoy Framework prototype.",
acknowledgement = ack-nhfb,
affiliation = "Brown Univ",
affiliationaddress = "Providence, RI, USA",
classification = "722.4; 723.1; 903.2; 903.3; 912.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Application programmer interface (api); Computer
architecture; Computer software; Computer systems
programming; Distributed computer systems; Distributed
open architecture; Envoy Framework; Information
dissemination; Information management; Information
retrieval; Software engineering; User agents; User
envoys; User informers; User interfaces; User
operatives; Work simplification",
wwwauthor = "M. Palaniappan and G. Fitzmaurice and N. Yankelovich
and George Fitzmaurice and Anne Loomis and Bernard Haan
and James Coombs and Norman Meyrowitz",
wwwtitle = "The {Envoy} System: An Open Architecture for Agents",
}
@Article{Ioannidis:1992:CLD,
author = "Yannis E. Ioannidis and Tomas Saulys and Andrew J.
Whitsitt",
title = "Conceptual Learning in Database Design",
journal = j-TOIS,
volume = "10",
number = "3",
pages = "265--293",
month = jul,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "This paper examines the idea of incorporating machine
learning algorithms into a database system for
monitoring its stream of incoming queries and
generating hierarchies with the most important concepts
expressed in those queries. The goal is for these
hierarchies to provide valuable input to the database
administrator for dynamically modifying the physical
and external schemas of a database for improved system
performance and user productivity. The criteria for
choosing the appropriate learning algorithms are
analyzed, and based on them, two such algorithms,
UNIMEM and COBWEB, are selected as the most suitable
ones for the task. Standard UNIMEM and COBWEB
implementations have been modified to support queries
as input. Based on the results of experiments with
these modified implementations, the whole approach
appears to be quite promising, especially if the
concept hierarchy from which the learning algorithms
start their processing is initialized with some of the
most obvious concepts captured in the database.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Wisconsin",
affiliationaddress = "Madison, WI, USA",
classification = "723.1; 723.3; 723.4; 921.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Adaptive database systems; Adaptive systems;
Algorithms; cobweb algorithm; Database schemas;
Database systems; Hierarchical systems; Learning
algorithms; Learning from examples; Learning systems;
Optimization; Performance; Query languages; UNIMEM
algorithm",
wwwauthor = "Y. E. Ioannidis and T. Saulys and A. J. Whittsitt",
}
@Article{Rada:1992:CTH,
author = "Roy Rada",
title = "Converting a Textbook to Hypertext",
journal = j-TOIS,
volume = "10",
number = "3",
pages = "294--315",
month = jul,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Traditional documents may be transformed into
hypertext by first reflecting the document's logical
markup in the hypertext (producing first-order
hypertext) and then by adding links not evident in the
document markup (producing second-order hypertext). In
our transformation of a textbook to hypertext, the
textbook is placed in an intermediate form based on a
semantic net and is then placed into the four hypertext
systems: Emacs-Info, Guide, HyperTies, and SuperBook.
The first-order Guide and SuperBook hypertexts reflect
a depth-first traversal of the semantic net, and the
Emacs-Info and HyperTies hypertexts reflect a
breadth-first traversal. The semantic net is augmented
manually, and then new traversal programs automatically
generate alternate outlines. An index based on word
patterns in the textbook is also automatically
generated for the second-order hypertext. Our suite of
programs has been applied to a published textbook, and
the resulting hypertexts are publicly available.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Liverpool",
affiliationaddress = "Liverpool, Engl",
classification = "461.4; 723.2; 723.5; 903.1; 903.2; 903.3; C6130D
(Document processing techniques); C6160Z (Other DBMS);
C7250 (Information storage and retrieval)",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer applications; Computer software; Data
processing; Document markup; Hierarchical systems;
Human computer interaction; Human engineering;
Hypermedia models; Hypertext; Indexing (of
information); Information dissemination; Information
retrieval systems; Man machine systems; Semantic net;
Software package Emacs Info; Software package Guides;
Software package HyperTies; Software package Superbook;
Textbooks",
wwwtitle = "Converting a Text to {Guide}, {HyperTies}, and
{Superbook}: Practice and Principles",
}
@Article{Mackinlay:1992:EUI,
author = "Jock Mackinlay and Jim Rhyne",
title = "Editorial: User Interface Software and Technology",
journal = j-TOIS,
volume = "10",
number = "4",
pages = "317--319",
month = oct,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pausch:1992:LLS,
author = "Randy Pausch and Matthew Conway and Robert DeLine",
title = "Lessons Learned from {SUIT}, the {Simple User
Interface Toolkit}",
journal = j-TOIS,
volume = "10",
number = "4",
pages = "320--344",
month = oct,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "In recent years, the computer science community has
realized the advantages of GUIs (Graphical User
Interfaces). Because high-quality GUIs are difficult to
build, support tools such as UIMSs, UI Toolkits, and
Interface Builders have been developed. Although these
tools are powerful, they typically make two
assumptions: first, that the programmer has some
familiarity with the GUI model, and second, that he is
willing to invest several weeks becoming proficient
with the tool. These tools typically operate only on
specific platforms, such as DOS, the Macintosh, or
UNIX/X-windows. The existing tools are beyond the reach
of most undergraduate computer science majors, or
professional programmers who wish to quickly build GUIs
without investing the time to become specialists in GUI
design. For this class of users, we developed SUIT, the
Simple User Interface Toolkit. SUIT is an attempt to
distill the fundamental components of an interface
builder and GUI toolkit, and to explain those concepts
with the tool itself, all in a short period of time. We
have measured that college juniors with no previous GUI
programming experience can use SUIT productively after
less than three hours. SUIT is a C subroutine library
which provides an external control UIMS, an interactive
layout editor, and a set of standard `widgets,' such as
sliders, buttons, and check boxes. SUIT-based
applications run transparently across the Macintosh,
DOS, and UNIX/X platforms. SUIT has been exported to
hundreds of external sites on the Internet. This paper
describes SUIT's architecture, the design decisions we
made during its development, and the lessons we learned
from extensive observations of over 120 users.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Virginia",
affiliationaddress = "Charlottesville, VA, USA",
classification = "461.4; 722.4; 723.1; 723.1.1; 723.2; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "C (programming language); Computer graphics; Computer
operating systems; Computer programming; Computer
science; Computer software; Computer software
portability; Graphical user interfaces; Human
engineering; Interactive computer systems;
Learnability; Learning systems; Pedagogy; Rapid
prototyping; Simple user interface toolkit (suit);
Software engineering; Software tools; User interface
toolkit; User interfaces",
wwwauthor = "R. Pausch and M. Conway and R. Deline",
}
@Article{Dewan:1992:HLF,
author = "Prasun Dewan and Rajiv Choudhary",
title = "A High-Level and Flexible Framework for Implementing
Multiuser User Interfaces",
journal = j-TOIS,
volume = "10",
number = "4",
pages = "345--380",
month = oct,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We have developed a high-level and flexible framework
for supporting the construction of multiuser user
interfaces. The framework is based on a generalized
editing interaction model, which allows users to view
programs as active data that can be concurrently edited
by multiple users. It consists of several novel
components including a refinement of both the Seeheim
UIMS architecture and the distributed graphics
architecture that explicitly addresses multiuser
interaction; the abstractions of shared active
variables and interaction variables, which allow users
and applications to exchange information; a set of
default collaboration rules designed to keep the
collaboration-awareness low in multiuser programs; and
a small but powerful set of primitives for overriding
these rules. The framework allows users to be
dynamically added and removed from a multiuser session,
different users to use different user interfaces to
interact with an application, the modules interacting
with a particular user to execute on the local
workstation, and programmers to incrementally trade
automation for flexibility. We have implemented the
framework as part of a system called Suite. This paper
motivates, describes, and illustrates the framework
using the concrete example of Suite, discusses how it
can be implemented in other kinds of systems, compares
it with related work, discusses its shortcomings, and
suggests directions for future work.",
acknowledgement = ack-nhfb,
affiliation = "Purdue Univ",
affiliationaddress = "West Lafayette, IN, USA",
classification = "461.4; 722.4; 723.1.1; 723.2; 723.3; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Administrative data processing; Computer architecture;
Computer graphics; Computer networks; Computer
programming languages; Computer supported cooperative
work; Distributed computer systems; Distributed
database systems; File editors; Flexibility; Groupware;
Human engineering; Interactive computer systems;
Multiprocessing systems; Multiuser user interfaces;
Text editing; User interface management systems; User
interfaces",
wwwtitle = "Coupling the User Interfaces of a Multi-User Program",
}
@Article{Bier:1992:ESB,
author = "Eric A. Bier",
title = "{EmbeddedButtons}: Supporting Buttons in Documents",
journal = j-TOIS,
volume = "10",
number = "4",
pages = "381--407",
month = oct,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "EmbeddedButtons is a library of routines and a runtime
kernel that support the integration of buttons into
document media, including text and graphics. Existing
document editors can be modified to participate in this
open architecture with the addition of a few simple
routines. Unlike many button systems that insert
special button objects into document media, this system
supports turning existing document objects into
buttons. As a consequence, buttons inherit all of the
attributes of normal document objects, and the
appearance of buttons can be edited using operations
already familiar to users. Facilities are provided for
linking buttons to application windows so that
documents can serve as application control panels.
Hence, user interface designers can lay out control
panels using familiar document editors rather than
special-purpose tools. Three classes of buttons have
been implemented, including buttons that pop up a menu
and buttons that store and display the value of a
variable. New button classes, editors, and applications
can be added at run time. Two editors, one for text and
one for graphics, currently participate in the
architecture.",
acknowledgement = ack-nhfb,
affiliation = "Xerox Palo Alto Research Cent",
affiliationaddress = "Palo Alto, CA, USA",
classification = "461.4; 722; 722.4; 723.1; 723.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Active documents; Computer architecture; Computer
graphics; Computer software; EmbeddedButtons; File
editors; Human engineering; Interaction techniques;
Interactive computer systems; Man machine systems;
Rapid prototyping; Software engineering; Subroutines;
Text editing; User interfaces",
}
@Article{Matsuoka:1992:GFB,
author = "Satoshi Matsuoka and Shin Takahashi and Tomihisa
Kamada and Akinori Yonezawa",
title = "A General Framework for Bidirectional Translation
between Abstract and Pictorial Data",
journal = j-TOIS,
volume = "10",
number = "4",
pages = "408--437",
month = oct,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The merits of direct manipulation are now widely
recognized. However, direct manipulation interfaces
incur high cost in their creation. To cope with this
problem, we present a model of bidirectional
translation between pictures and abstract application
data, and a prototype system, TRIP2, based on this
model. Using this model, general mapping from abstract
data to pictures and from pictures to abstract data is
realized merely by giving declarative mapping rules,
allowing fast and easy creation of direct manipulation
interfaces. We apply the prototype system to the
generation of the interfaces for kinship diagrams,
Graph Editors, E-R diagrams, and an Othello game.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Tokyo",
affiliationaddress = "Tokyo, Jpn",
classification = "721.1; 723.1; 723.2; 723.5; 741.3; 921",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Abstract application data; Algorithms; Bidirectional
translation; Computational methods; Computer graphics;
Data processing; Direct manipulation; File editors;
Human engineering; Human information processing;
Humanities computing; Image processing; Interactive
computer systems; Mathematical models; Prototype system
trip2; Software engineering; User interface management
systems; User interfaces; Visualization",
wwwauthor = "S. Takahashi and S. Matsuoka and A. Yonezawa and T.
Kamada",
wwwtitle = "A General Framework for Bi-directional Translation
between Abstract and Pictorial Data",
}
@Article{Kataoka:1992:MIO,
author = "Yutaka Kataoka and Masato Morisaki and Hiroshi
Kuribayashi and Hiroyoshi Ohara",
title = "A Model for Input and Output of Multilingual Text in a
Windowing Environment",
journal = j-TOIS,
volume = "10",
number = "4",
pages = "438--451",
month = oct,
year = "1992",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The layered multilingual input\slash output (I/O)
system we designed, based on typological studies of
major-language writing conventions, unifies common
features of such conventions to enable international
and local utilization. The internationalization layer
input module converts keystroke sequences to phonograms
and ideograms. The corresponding output module displays
position-independent and dependent characters. The
localization layer positions language-specific
functions outside the structure, integrating them as
tables used by finite automaton interpreters and
servers to add new languages and code sets without
recompilation. The I/O system generates and displays
stateful and stateless code sets, enabling interactive
language switching. Going beyond POSIX locale model
bounds, the system generates ISO 2022, ISO\slash DIS
10646 (1990), and Compound Text, defined for the
interchange encoding format in X11 protocols, for basic
polyglot text communication and processing. Able to
generate multilingual code sets, the I/O system clearly
demonstrates that code sets should be selected by
applications which have purposes beyond selecting one
element from a localization set. Functionality and
functions related to text manipulation in an operating
system (OS) must also be determined by such
applications. A subset of this I/O system was
implemented in the X window system as a basic use of
X11R5 I/O by supplying basic code set generation and
string manipulation to eliminate OS interference. To
ensure polyglot string manipulation, the I/O system
must clearly be implemented separately from an OS and
its limitations.",
acknowledgement = ack-nhfb,
affiliation = "Waseda Univ",
affiliationaddress = "Tokyo, Jpn",
classification = "722.4; 723.1; 723.1.1; 723.2; 902.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Codes (symbols); Computer operating systems; Computer
programming languages; Data processing; Data
structures; Encoding (symbols); Input output programs;
Interactive computer systems; Internationalization; iso
2022 standard; iso/dis 10646 (1990) standard;
Linguistics; Localization; Multilingual; Multiwindow;
Network protocols; Polyglot text; POSIX locale code;
Program interpreters; Standardization; X window
systems; X11 protocols",
}
@Article{Garzotto:1993:HMB,
author = "Franca Garzotto and Paolo Paolini and Daniel Schwabe",
title = "{HDM} --- {A} Model Based Approach to Hypertext
Application Design",
journal = j-TOIS,
volume = "11",
number = "1",
pages = "1--26",
month = jan,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Hypertext development should benefit from a
systematic, structured development, especially in the
case of large and complex applications. A structured
approach to hypertext development suggests the notion
of authoring-in-the-large. Authoring-in-the-large
allows the description of overall classes of
information elements and navigational structures of
complex applications without much concern with
implementation details, and in a system-independent
manner. The paper presents HDM (Hypertext Design
Model), a first step towards defining a general purpose
model for authoring-in-the-large. Some of the most
innovative features of HDM are: the notion of
perspective; the identification of different categories
of links (structural links, application links, and
perspective links) with different representational
roles; the distinction between hyperbase and access
structures; and the possibility of easily integrating
the structure of a hypertext application with its
browsing semantics. HDM can be used in different
manners: as a modeling device or as an implementation
device. As a modeling device, it supports producing
high level specifications of existing or
to-be-developed applications. As an implementation
device, it is the basis for designing tools that
directly support application development. One of the
central advantages of HDM in the design and practical
construction of hypertext applications is that the
definition of a significant number of links can be
derived automatically from a conceptual-design level
description. Examples of usage of HDM are also
included.",
acknowledgement = ack-nhfb,
affiliation = "Politecnico di Milano",
classification = "723.3; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data models; Database systems; Hypertext; Information
retrieval systems; Office automation",
}
@Article{Schnase:1993:SDM,
author = "John L. Schnase and John J. Leggett and David L. Hicks
and Ron L. Szabo",
title = "Semantic Data Modeling of Hypermedia Associations",
journal = j-TOIS,
volume = "11",
number = "1",
pages = "27--50",
month = jan,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Many important issues in the design and implementation
of hypermedia system functionality focus on the way
interobject connections are represented, manipulated,
and stored. A prototypic system called HB1 is being
designed to meet the storage needs of next-generation
hypermedia system architectures. HB1 is referred to as
a hyperbase management systems (HBMS) because it
supports, not only the storage and manipulation of
information, but the storage and manipulation of the
connectivity data that link information together to
form hypermedia. Among HB1's distinctions is its use of
a semantic network database system to manage physical
storage. Here, basic semantic modeling concepts as they
apply to hypermedia systems are reviewed, and
experiences using a semantic database system in HB1 are
discussed. Semantic data models attempt to provide more
powerful mechanisms for structuring objects than are
provided by traditional approaches. In HB1, it was
necessary to abstract interobject connectivity,
behaviors, and information for hypermedia. Building on
top pf a semantic database system facilitated such a
separation and made the structural aspects of
hypermedia conveniently accessible to manipulation.
This becomes particularly important in the
implementation of structure-related operations such as
structural queries. Our experience suggests that an
intergrated semantic object-oriented database paradigm
appears to be superior to purely relational, semantic,
or object-oriented methodologies for representing the
structurally complex interrelationships that arise in
hypermedia.",
acknowledgement = ack-nhfb,
affiliation = "CRSS Architects, Inc",
classification = "723.1; 723.3; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data models; Database systems; Information retrieval
systems; Management information systems; Object
oriented programming",
}
@Article{Rama:1993:ICR,
author = "D. V. Rama and Padmini Srinivasan",
title = "An Investigation of Content Representation Using Text
Grammars",
journal = j-TOIS,
volume = "11",
number = "1",
pages = "51--75",
month = jan,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We extend prior work on a model for natural language
text representation and retrieval using a linguistic
device called text grammar. We demonstrate the value of
this approach in accessing relevant items from a
collection of empirical abstracts in a medical domain.
The advantage, when compared to traditional keyword
retrieval, is that this approach is a significant move
towards knowledge representation and retrieval. Text
representation in this model includes keywords and
their conceptual roles in the text. In particular, it
involves extracting TOPIC predicates representing the
research issue addressed and DESIGN predicates
representing important methodological features of the
empirical study. Preliminary experimentation shows that
keywords exhibit a variety of text-grammar roles in a
test database. Second, as intuitively expected,
retrieval using TOPIC predicates identifies a smaller
subset of texts than Boolean retrieval does. These
empirical results along with the theoretical work
indicate that the representation and retrieval
strategies proposed have a significant potential.
Finally, EMPIRICIST,a prototype system, is described.
In it the text representation predicates are
implemented as a network while retrieval is through
constrained-spreading activation strategies.",
acknowledgement = ack-nhfb,
affiliation = "Bentley Coll",
classification = "723.5; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Indexing (of information); Information retrieval
systems; Natural language processing systems; Text
analysis",
}
@Article{Szczur:1993:TPT,
author = "Martha R. Szczur and Sylvia B. Sheppard",
title = "{TAE} Plus: Transportable Applications Environment
Plus: a User Interface Development Environment",
journal = j-TOIS,
volume = "11",
number = "1",
pages = "76--101",
month = jan,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The Transportable Applications Environment Plus (TAE
Plus${}^{TM}$) is a NASA-developed user interface
development environment (UIDE) for the rapid
prototyping, evaluation, implementation, and management
of user interfaces. TAE Plus provides an intuitive What
You see Is What You Get (WYSIWYG) WorkBench for
designing an application's user interface. The
WorkBench supports the creation and sequencing of
displays, including real-time, data-driven display
objects. Users can define context-sensitive help for a
target application. They can rehearse the user
interface and also generate code automatically. In
addition, TAE Plus contains application services for
the runtime manipulation and management of the user
interface. Based on Motif${}^{TM}$ and the MIT X Window
System${}^{TM}$, TAE Plus runs on a variety of Unix-or
VMS-based workstations. TAE Plus is an evolving system.
User-defined requirements and new technology guide the
development of each new version. Advances in virtual
operating systems, human factors, computer graphics,
command language design, standardization, and software
portability are monitored and incorporated as they
become available.",
acknowledgement = ack-nhfb,
affiliation = "NASA",
classification = "461.4; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Human engineering; Interfaces (computer); Prototyping;
Software development; Software engineering; User
interfaces",
wwwauthor = "M. R. Szezur and S. B. Sheppard",
wwwtitle = "{TAE Plus: Transportable Applications Environment
Plus}",
}
@Article{King:1993:DDI,
author = "Roger King and Michael Novak",
title = "Designing Database Interfaces with {DBface}",
journal = j-TOIS,
volume = "11",
number = "2",
pages = "105--132",
month = apr,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "DBface is a toolkit for designing interfaces to
object-oriented databases. It provides users with a set
of tools for building custom interfaces with minimal
programming. This is accomplished by combining
techniques from User Interface Management Systems
(UIMS) with a built-in knowledge about the specific
kinds of techniques used by object-oriented databases.
DBface allows users to create graphical constructs and
interactive techniques by taking advantage of an
object-oriented database environment and tools. Not
only can database tools be used for creating an
interface, but information about the interface being
built is stored within a database schema and is
syntactically consistent with all other schema
information. Thus, an interface can deal with data and
schema information, including information about another
interface. This allows for easy reusability of
graphical constructs such as data representations.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Colorado",
classification = "722; 723.1; 723.3; 723.4.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer programming; Database interfaces; Database
systems; Graphical interfaces; Interactive computer
graphics; Interfaces (computer); Knowledge based
systems; Object-oriented databases; User interfaces",
}
@Article{Ciaccia:1993:EAP,
author = "Paulo Ciaccia and Pavel Zezula",
title = "Estimating Accesses in Partitioned Signature File
Organizations",
journal = j-TOIS,
volume = "11",
number = "2",
pages = "133--142",
month = apr,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We show that performance of some basic methods for the
partitioning of signature files, namely Quick Filter
and Fixed Prefix, can be easily evaluated by means of a
closed formula. The approximation is based on
well-known results from probability theory, and, as
shown by simulations, introduces no appreciable errors
when compared with the exact, cumbersome formulas used
so far. Furthermore, we prove that the exact formulas
for the two methods coincide. Although this does not
imply that the two methods behave in the same way, it
sheds light on the way they could be compared.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Bologna",
affiliationaddress = "Italy",
classification = "721.1; 723.5; 903.3; 922.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Access estimation; Codes (symbols); Computer
simulation; File organization; Information retrieval;
Partitioned signature files; Probability; Probability
theory; Signature files",
wwwauthor = "P. Zezula and P. Ciaccia",
}
@Article{Can:1993:ICD,
author = "Fazli Can",
title = "Incremental Clustering for Dynamic Information
Processing",
journal = j-TOIS,
volume = "11",
number = "2",
pages = "143--164",
month = apr,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Clustering of very large document databases is useful
for both searching and browsing. The periodic updating
of clusters is required due to the dynamic nature of
databases. An algorithm for incremental clustering is
introduced. The complexity and cost analysis of the
algorithm together with an investigation of its
expected behavior are presented. Through empirical
testing it is shown that the algorithm achieves cost
effectiveness and generates statistically valid
clusters that are compatible with those of
reclustering. The experimental evidence shows that the
algorithm creates an effective and efficient retrieval
environment.",
acknowledgement = ack-nhfb,
affiliation = "Miami Univ",
classification = "723.2; 723.3; 903.3; 911.1; 922.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Browsing; Clustering; Cost accounting;
Cost effectiveness; Data processing; Database systems;
Document databases; Dynamic information processing;
Incremental clustering; Information retrieval;
Statistical methods; Statistically valid clusters",
}
@Article{Bansler:1993:RSA,
author = "J{\o}rgen P. Bansler and Keld B{\o}dker",
title = "A Reappraisal of Structured Analysis: Design in an
Organizational Context",
journal = j-TOIS,
volume = "11",
number = "2",
pages = "165--193",
month = apr,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We review Structured Analysis as presented by Yourdon
and DeMarco. First, we examine the implicit assumptions
embodied in the method about the nature of
organizations, work processes, and design. Following
this we present the results of an exploratory study,
conducted to find out how the method is applied in
practice. This study reveals that while some of the
tools of Structured Analysis --- notably the data flow
diagram --- are used and combined with other tools, the
designers do not follow the analysis and design
procedures prescribed by the method. Our findings
suggest that there is a gap between the way systems
development is portrayed in the normative technical
literature and the way in which is carried out.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Copenhagen",
classification = "721.1; 723.1; 723.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer programming; Computer software; Data flow
diagrams; Data processing; Structured analysis;
Structured programming; Work processes",
wwwtitle = "A Reappraisal of Structured Analysis",
}
@Article{Feiner:1993:EVW,
author = "Steven K. Feiner and Simon J. Gibbs",
title = "Editorial: Virtual Worlds",
journal = j-TOIS,
volume = "11",
number = "3",
pages = "195--196",
month = jul,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Virtual Worlds.",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Fitzmaurice:1993:VRP,
author = "George W. Fitzmaurice and Shumin Zhai and Mark H.
Chignell",
title = "Virtual Reality for Palmtop Computers",
journal = j-TOIS,
volume = "11",
number = "3",
pages = "197--218",
month = jul,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Virtual Worlds.",
URL = "http://www.acm.org:80",
abstract = "We are exploring how virtual reality theories can be
applied toward palmtop computers, In our prototype,
called the Cameleon, a small 4-inch hand-held monitor
acts as a palmtop computer with the capabilities of a
Silicon graphics workstation. A 6D input device and a
response button are attached to the small monitor to
detect user gestures and input selections for issuing
commands. An experiment was conducted to evaluate our
design and to see how well depth could be perceived in
the small screen compared to a large 21-inch screen,
and the extent to which movement of the small display (
in a palmtop virtual reality condition) could improve
depth perception.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Toronto",
affiliationaddress = "Can",
classification = "723",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer workstations; Computers; Depth perception
improvement; Palmtop virtual reality condition; Silicon
graphics workstation; Virtual reality theories; Virtual
storage",
}
@Article{Sturman:1993:DMW,
author = "David J. Sturman and David Zeltzer",
title = "A Design Method for ``Whole Hand'' Human-Computer
Interaction",
journal = j-TOIS,
volume = "11",
number = "3",
pages = "219--238",
month = jul,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Virtual Worlds.",
URL = "http://www.acm.org:80",
abstract = "A disciplined investigation of whole-hand interfaces
(often glove based, currently) and their appropriate
use for the control of complex task domains by the
design method for whole-hand input. This is a series of
procedures --- including a common basis for the
description, design, and evaluation of whole-hand
input, together with an accompanying taxonomy --- that
enumerates key issues and points for consideration in
the development of whole-hand input. The method helps
designers focus on task requirements, isolate problem
areas, and choose appropriate whole-hand input
strategies for their specified tasks.",
acknowledgement = ack-nhfb,
affiliation = "Massachusetts Inst of Technology",
affiliationaddress = "Cambridge, MA, USA",
classification = "723; 723.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer graphics; Computers; Input devices;
Interaction techniques; Man machine systems; Virtual
environments; Whole hand human computer interaction",
}
@Article{Arthur:1993:ETP,
author = "Kevin W. Arthur and Kellogg S. Booth and Colin Ware",
title = "Evaluating {3D} Task Performance for Fish Tank Virtual
Worlds",
journal = j-TOIS,
volume = "11",
number = "3",
pages = "239--265",
month = jul,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Virtual Worlds.",
URL = "http://www.acm.org:80",
abstract = "'Fish tank virtual reality' refers to the use of a
standard graphics workstation to achieve real-time
display of 3D scenes using stereopsis and dynamic
head-coupled perspective. Fish tank VR has a number of
advantages over head-mounted immersion VR which makes
it more practical for many applications. After
discussing the characteristics of fish tank VR, we
describe a set of three experiments conducted to study
the benefits of fish tank VR over a traditional
workstation graphics display. These experiments tested
user performance under two conditions: (a) whether or
not stereoscopic display was used and (b) whether or
not the perspective display was coupled dynamically to
the positions of a user's eyes. Subjects using a
comparison protocol consistently preferred head
coupling without stereo over stereo without head
coupling.",
acknowledgement = ack-nhfb,
affiliation = "Univ of British Columbia",
affiliationaddress = "Can",
classification = "723; 723.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer graphics; Computer workstations; Computers;
Fish tank virtual worlds; Head-coupled display;
Standard graphics workstation; Three-dimensional
graphics; Virtual storage; Virtual worlds",
wwwauthor = "K. Arthur and K. Booth and C. Ware",
}
@Article{Koike:1993:RAS,
author = "Hideki Koike",
title = "The Role of Another Spatial Dimension in Software
Visualization",
journal = j-TOIS,
volume = "11",
number = "3",
pages = "266--286",
month = jul,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Virtual Worlds.",
URL = "http://www.acm.org:80",
abstract = "The primary objective of this article is to
demonstrate the use of 3D-computer graphics in
visualizing shapeless software information by focusing
on performance monitoring of parallel-concurrent
computer systems. Issues are addressed from two
different perspectives: expressiveness of output media
and user cognition. The former describes the
limitations of 2D output media. The latter refers to a
user's cognitive load when using 2D representations in
a multiple-window environment.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Electro-Communications",
affiliationaddress = "Jpn",
classification = "723; 723.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer graphics; Computer software; Electric power
control system; Multiple-window environment; Parallel
manipulator; Parallel-concurrent computer system;
Prototype visualization system vogue; Shapeless
software visualization; User's cognitive load",
wwwtitle = "The Roles of Another Spatial Dimension in Software
Visualization",
}
@Article{Shaw:1993:DSV,
author = "Chris Shaw and Mark Green and Jiandong Liang and Yunqi
Sun",
title = "Decoupled Simulation in Virtual Reality with the {MR}
Toolkit",
journal = j-TOIS,
volume = "11",
number = "3",
pages = "287--317",
month = jul,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Virtual Worlds.",
URL = "http://www.acm.org:80",
abstract = "The Virtual Reality (VR) user interface style allows
natural hand and body motions to manipulate virtual
objects in 3D environments using one or more 3D input
devices. This style is best suited to application
areas",
acknowledgement = ack-nhfb,
affiliation = "Univ of Alberta",
affiliationaddress = "Can",
classification = "723; 723.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer software; Decoupled simulation model (dsm);
Interactive computer graphics; Interactive three
dimensional graphics; User interface software; Virtual
object manipulations; Virtual reality (VR) user
interface style; Virtual storage",
}
@Article{Malone:1993:GE,
author = "Thomas Malone and Norbert Streitz",
title = "Guest Editorial",
journal = j-TOIS,
volume = "11",
number = "4",
pages = "319--320",
month = oct,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Supported Cooperative Work
(CSCW).",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Olson:1993:GCC,
author = "Judith S. Olson and Gary M. Olson and Marianne
Storrosten and Mark Carter",
title = "Groupwork Close Up: a Comparison of the Group Design
Process With and Without a Simple Group Editor",
journal = j-TOIS,
volume = "11",
number = "4",
pages = "321--348",
month = oct,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Supported Cooperative Work
(CSCW).",
URL = "http://www.acm.org:80",
abstract = "A simple collaborative tool, a shared text editor
called ShrEdit, changed the way groups of designers
performed their work, and changed it for the better.
First, the designs produced by the 19 groups of three
designers were of higher quality than those of the 19
groups who worked with conventional whiteboard, paper
and pencil. The groups with the new tool reported
liming their work process a little less, probably
because they had to adapt their work style to a new
tool. We expected, from the brainstorming literature
and recent work on Group Support Systems, that the
reason the designs were of better quality was that the
supported groups generated more ideas. To our surprise,
the groups working with ShrEdit generated fewer design
ideas, but apparently better ones. It appears that the
tool helped the supported groups keep more focused on
the core issues in the emerging design, to waste less
time on less important topics, and to capture what was
said as they went. This suggests that small workgroups
can capitalize on the free access they have to a shared
workspace, without requiring a facilitator or a work
process embedded in the software.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Michigan",
affiliationaddress = "Ann Arbor, MI, USA",
classification = "723; 903",
conferenceyear = "1993",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer software; Concurrent editing; Decision
support systems; Design; Group behavior; Group support
system; Groupwork; Information science; Management
information systems",
}
@Article{Ishii:1993:IIS,
author = "Hiroshi Ishii and Minoru Kobayashi and Jonathan
Grudin",
title = "Integration of Interpersonal Space and Shared
Workspace; {ClearBoard} Design and {Experiments}",
journal = j-TOIS,
volume = "11",
number = "4",
pages = "349--375",
month = oct,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Supported Cooperative Work
(CSCW).",
URL = "http://www.acm.org:80",
abstract = "We describe the evolution of the novel shared drawing
medium clearBoard which was designed to seamlessly
integrate an intrapersonal space and a shared
workspace. ClearBoard permits coworkers in two
locations to draw with color markers or with electronic
pens and software tools while maintaining direct eye
contact and the ability to employ natural gestures. The
ClearBoard design is based on the key metaphor of
`talking through and drawing on a transparent glass
window'. We describe the evolution from ClearBoard-1
(which enables shared video drawing) to ClearBoard-2
(which incorporates TeamPaint, a multiuser paint
editor). Initial observations and findings gained
through the experimental use of the prototype,
including the feature of `gaze awareness', are
discussed. Further experiments are conducted with
ClearBoard-0 (a simple mockup), ClearBoard-1, and an
actual desktop as a control. IN the settings we
examined, the ClearBoard environment led to more eye
contact and potential awareness of collaborator's gaze
direction over the traditional desktop environment.",
acknowledgement = ack-nhfb,
affiliation = "NTT Human Interface Laboratories",
classification = "723; 903",
conferenceyear = "1993",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer software; Decision support systems; Gaze
awareness; Groupware; Information science; Interfaces
(computer); Interpersonal space; management information
systems; Shared workspace; Teleconferencing",
}
@Article{Hindus:1993:CSR,
author = "Debby Hindus and Chris Schmandt and Chris Horner",
title = "Capturing, Structuring, and Representing Ubiquitous
Audio",
journal = j-TOIS,
volume = "11",
number = "4",
pages = "376--400",
month = oct,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Supported Cooperative Work
(CSCW).",
URL = "http://www.acm.org:80",
abstract = "Although talking is an integral part of collaboration,
there has been little computer support for acquiring
and accessing the contents of conversations. Our
approach has focused on ubiquitous audio, or the
unobtrusive capture of speech interactions in everyday
work environments. Speech recognition technology cannot
yet transcribe fluent conversational speech, so the
words themselves are not available for organizing the
captured interactions. Instead, the structure of an
interaction is derived from acoustical information
inherent in the stored speech and augmented by user
interaction during or after capture. This article
describes applications for capturing and structuring
audio from office discussions and telephone calls, and
mechanisms for later retrieval of these stored
interactions. An important aspect of retrieval is
choosing an appropriate visual representation, and this
article describes the evolution of a family of
representations across a range of applications.
Finally, this work is placed within the broader context
of desktop audio, mobile audio applications, and social
implications.",
acknowledgement = ack-nhfb,
affiliation = "Interval Research Corporation",
affiliationaddress = "Palo Alto, CA, USA",
classification = "723; 752; 903",
conferenceyear = "1993",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Audio systems; Collaborative work; Computer software;
Decision support systems; Information retrieval
systems; Interfaces (computer); Multimedia workstation;
Software telephony; Teleconferencing; Ubiquitous
audio",
}
@Article{Resnick:1993:PBC,
author = "Paul Resnick",
title = "Phone-Based {CSCW}: Tools and Trials",
journal = j-TOIS,
volume = "11",
number = "4",
pages = "401--424",
month = oct,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Computer-Supported Cooperative Work
(CSCW).",
URL = "http://www.acm.org:80",
abstract = "Telephones are the most ubiquitous, best-networked,
and simplest computer terminals available today. They
have been used for voice mail but largely overlooked as
a platform for asynchronous cooperative-work
applications such as event calendars, issue
discussions, and question-and-answer gathering.
HyperVoice is a software toolkit for constructing such
applications. Its building blocks are high-level
presentation formats for collections of structured
voice messages. The presentation formats can themselves
be presented and manipulated, enabling significant
customization of applications by phone. Results of two
field trials suggest social-context factors that will
influence the success or failure of phone-based
cooperative work applications in particular settings.",
acknowledgement = ack-nhfb,
classification = "716; 723; 903",
conferenceyear = "1993",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Asynchronous cooperative work; Computer networks;
Computer programming; Computer software; Phone based
interface; Software toolkit; Telephone systems; User
interfaces; Voice/data communication systems",
}
@Article{Anonymous:1993:AI,
author = "Anonymous",
title = "1993 Author Index",
journal = j-TOIS,
volume = "11",
number = "4",
pages = "425--426",
month = oct,
year = "1993",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Allen:1994:E,
author = "Robert B. Allen",
title = "Editorial",
journal = j-TOIS,
volume = "12",
number = "1",
pages = "1--1",
month = jan,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Anonymous:1994:TC,
author = "Anonymous",
title = "{TOIS} Charter",
journal = j-TOIS,
volume = "12",
number = "1",
pages = "3--3",
month = jan,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 16:21:56 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Marchionini:1994:EHL,
author = "Gary Marchionini and Gregory Crane",
title = "Evaluating Hypermedia and Learning: Methods and
Results from the {Perseus Project}",
journal = j-TOIS,
volume = "12",
number = "1",
pages = "5--34",
month = jan,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The Perseus Project has developed a hypermedia corpus
of materials related to the ancient Greek world. The
materials include a variety of texts and images, and
tools for using these materials and navigating the
system. Results from a three-year evaluation of Perseus
use in a variety of college settings are described. The
evaluation assessed both this particular system and the
application of the technological genre to information
management and to learning.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Maryland",
affiliationaddress = "College Park, MD, USA",
classification = "403.2; 461.4; 723.5; 912.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer milieux; Human computer interaction; Human
engineering; Human information processing; Hypermedia;
Information science; Learning systems; Logic design;
Machine systems; Navigation systems",
}
@Article{Poulovassilis:1994:NGM,
author = "Alexandra Poulovassilis and Mark Levene",
title = "A Nested-Graph Model for the Representation and
Manipulation of Complex Objects",
journal = j-TOIS,
volume = "12",
number = "1",
pages = "35--68",
month = jan,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Three recent trends in database research are
object-oriented and deductive databases and graph-based
user interfaces. We draw these trends together in a
data model we call the Hypernode Model. The single data
structure of this model is the hypernode, a graph whose
nodes can themselves be graphs. Hypernodes are typed,
and types, too, are nested graphs. We give the
theoretical foundations of hypernodes and types, and we
show that type checking is tractable. We show also how
conventional type-forming operators can be simulated by
our graph types, including cyclic types. The Hypernode
Model comes equipped with a rule-based query language
called Hyperlog, which is complete with respect to
computation and update. We define the operational
semantics of Hyperlog and show that the evaluation of
Hyperlog programs is intractable in the general
case--we identify cases when evaluation can be
performed efficiently.",
acknowledgement = ack-nhfb,
affiliation = "King's College",
affiliationaddress = "London, Engl",
classification = "721.2; 723.2; 723.4; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer graphics; Computer networks; Computer
programming; Data processing; Database browsing;
Database management; Expert systems; Hyperlog programs;
Hypernode project; Logic design; Nested graph",
}
@Article{Schauble:1994:EPQ,
author = "Peter Schauble and Beat Wuthrich",
title = "On the Expressive Power of Query Languages",
journal = j-TOIS,
volume = "12",
number = "1",
pages = "69--91",
month = jan,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Two main topics are addressed. First, an algebraic
approach is presented to define a general notion of
expressive power. Heterogeneous algebras represent
information systems and morphisms represent the
correspondences between the instances of databases, the
correspondences between answers, and the
correspondences between queries. An important feature
of this new notion of expressive power is that query
languages of different types can be compared with
respect to their expressive power.",
acknowledgement = ack-nhfb,
affiliation = "Swiss Federal of Technology",
affiliationaddress = "Zurich, Switz",
classification = "721.1; 721.2; 723.4; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Abstract data; Artificial intelligence; Computation
theory; Computer programming; Datalog; Heterogeneous
algebra; Information science; Logic design; Query
correspondence; Query languages; Recursion",
}
@Article{Fuhr:1994:PIR,
author = "Norbert Fuhr and Ulrich Pfeifer",
title = "Probabilistic Information Retrieval as a Combination
of Abstraction, Inductive Learning, and Probabilistic
Assumptions",
journal = j-TOIS,
volume = "12",
number = "1",
pages = "92--115",
month = jan,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "We show that former approaches in probabilistic
information retrieval are based on one or two of the
three concepts abstraction, inductive learning, and
probabilistic assumptions, and we propose a new
approach which combines all three concepts. This
approach is illustrated for the case of indexing with a
controlled vocabulary. For this purpose, we describe a
new probabilistic model first, which is then combined
with logistic regression, thus yielding a
generalization of the original model.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Dortmund",
affiliationaddress = "Dortmund, Ger",
classification = "721.2; 723.2; 723.4; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Abstraction; Artificial intelligence; Data feedback;
Data storage equipment; Information science;
Interactive devices; Learning systems; Logic design;
Logistic regression; Probabilistic information;
Probabilistic retrieval",
wwwtitle = "Probabilistic Information Retrieval as Combination of
Abstraction, Inductive Learning and Probabilistic
Assumptions",
}
@Article{Kling:1994:ISI,
author = "R. Kling",
title = "Introduction to the Special Issue on Social Science
Perspectives on {IS}",
journal = j-TOIS,
volume = "12",
number = "2",
pages = "117--118",
month = apr,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 16:21:56 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Markus:1994:FHM,
author = "M. L. Markus",
title = "Finding a Happy Medium: Explaining the Negative
Effects of Electronic Communication on Social Life at
Work",
journal = j-TOIS,
volume = "12",
number = "2",
pages = "119--149",
month = apr,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The sometimes observed negative social effects of
electronic communication technology are often
attributed to the characteristics of the technology
itself. Electronic mail, for instance, filters out
personal and social cues and provides new capabilities
not found in traditional media,and it has been argued
that these factors have consequences such as `flaming'
and depersonalization. Alternative theoretical
perspectives on the impacts of information technology
suggest that our ability to explain these outcomes
might be enhanced by attending to user's intentional
choices about how to use technology and to the
unpredictable technology usage patterns that emerge
when users interact with the technology and each other.
These alternative perspectives are examined in the
context of an exploratory case study of a complex
organization in which electronic mail was heavily
used.",
acknowledgement = ack-nhfb,
affiliation = "The Calemont Graduate School",
affiliationaddress = "Claremont, CA, USA",
classification = "718.1; 903.2; 903.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Depersonalization; Electronic communication;
Electronic mail; Information services; Negative
effects; Social life at work; Telecommunication
systems",
wwwtitle = "Finding a Happy Medium: Explaining the Effects of
Electronic Mail on Social Life at Work",
}
@Article{Walsham:1994:ISS,
author = "G. Walsham and T. Waema",
title = "Information Systems Strategy and Implementation: a
Case Study of a Building Society",
journal = j-TOIS,
volume = "12",
number = "2",
pages = "150--173",
month = apr,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The formation and implementation of strategy with
respect to computer-based information systems (IS) are
important issues in many contemporary organizations,
including those in the financial services sector. This
paper describes and analyzes an in-depth case study of
the strategy formation and implementation process in
one such organization, a medium-sized UK building
society, and relates the process to its organizational
and broader contexts; the organization is examined over
a period of several years and under the contrasting
leadership of two different chief executives. The case
study is used to develop some general implications on
IS strategy and implementation, which can be taken as
themes for debate in any new situation. The paper
provides an example of a more detailed perspective on
processes in IS strategy and implementation than
typically available in the literature. In addition, a
new framework for further research in this area is
developed, which directs the researcher toward
exploring the dynamic interplay of strategic content,
multilevel contexts, and cultural and political
perspectives on the process of change.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Cambridge",
affiliationaddress = "Cambridge, Engl",
classification = "723.5; 903.2; 903.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer applications; Implementation; Information
dissemination; Information services; Information
systems strategy; Multilevel context",
}
@Article{Orlikowski:1994:TFM,
author = "Wanda J. Orlikowski and Debra C. Gash",
title = "Technological Frames: Making Sense of Information
Technology in Organizations",
journal = j-TOIS,
volume = "12",
number = "2",
pages = "174--207",
month = apr,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "In this article, we build on and extend research into
the cognitions and values of users and designers by
proposing a systematic approach for examining the
underlying assumptions. expectations, and knowledge
that people have about technology. Such interpretations
of technology (which we call technological (frames))
are central to understanding technological development,
use, and change in organizations. We suggest that where
the technological frames of key groups in
organizations---such as managers, technologists, and
change of technology may result. We use the findings of
an empirical study to illustrate how the nature, value,
and use of a groupware technology were interpreted by
various organizational stakeholders, resulting in
outcomes that deviated from those expected. We argue
that technological frames offer an interesting and
useful analytic perspective for explaining and
anticipating actions and meanings that are not easily
obtained with other theoretical lenses.",
acknowledgement = ack-nhfb,
affiliation = "Massachusetts Institute of Technology",
affiliationaddress = "Cambridge, MA, USA",
classification = "716.1; 723.5; 903.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Human factors; Information science; Information
services; Organizations; Technological frames;
Technology",
}
@Article{Ruhleder:1994:RLR,
author = "Karen Ruhleder",
title = "Rich and Lean Representations of Information for
Knowledge Work: The Role of Computing Packages in the
Work of Classical Scholars",
journal = j-TOIS,
volume = "12",
number = "2",
pages = "208--230",
month = apr,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Applying information systems to complex intellectual
tasks requires the representation and codification of
ambiguous and fragmentary forms of data. This
application effects changes not only in representation
of this data, but in the relationships between users
and tools, techniques, or systems for data
interpretation. It also affects the complex
infrastructures that support this process. This article
uses a package metaphor to examine the impact on one
domain of knowledge work, classical scholarship, of the
`computerization' of a key data source, the textual
edition. The construction of one on-line textual
databank, the Thesaurus Linguae Graecae (TLG), has
altered the traditional relationships between text
`owners' and `users', has changed the role of the text
as a conduit for social and historical information, and
has disrupted traditional patterns of transmitting
domain expertise. A rich information resource has
become lean in its electronic form.",
acknowledgement = ack-nhfb,
affiliation = "Worcester Polytechnic Institute",
affiliationaddress = "Worcester, MA, USA",
classification = "723.5; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Classical scholars; Computer applications; Computing
packages; Information retrieval systems; Information
science; Lean representation; Rich representation",
}
@Article{Lewis:1994:GE,
author = "D. D. Lewis and P. J. Hayes",
title = "Guest Editorial",
journal = j-TOIS,
volume = "12",
number = "3",
pages = "231--233",
month = jul,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 16:21:56 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Text Categorization.",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Apte:1994:ALD,
author = "Chidanand Apte and Fred Damerau and Sholom M. Weiss",
title = "Automated Learning of Decision Rules for Text
Categorization",
journal = j-TOIS,
volume = "12",
number = "3",
pages = "233--251",
month = jul,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Text Categorization.",
URL = "http://www.acm.org:80",
abstract = "We describe the results of extensive experiments using
optimized rule-based induction methods on large
document collections. The goal of these methods is to
discover automatically classification patterns that can
be used for general document categorization or
personalized filtering of free text. Previous reports
indicate that human-engineered rule-based systems,
requiring many man-years of developmental efforts, have
been successfully built to `read' documents and assign
topics to them. We show that machine-generated decision
rules appear comparable to human performance, while
using the identical rule-based representation. In
comparison with other machine-learning techniques,
results on a key benchmark from the Reuters collection
show a large gain in performance, from a previously
reported 67\% recall\slash precision breakeven point to
80.5\%. In the context of a very high-dimensional
feature space, several methodological alternatives are
examined, including universal versus local
dictionaries, and binary versus frequency-related
features.",
acknowledgement = ack-nhfb,
affiliation = "IBM T. J. Watson Research Cent",
affiliationaddress = "Yorktown Heights, NY, USA",
classification = "461.4; 722.1; 723.4; 901.1.1; 902.2; 903.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Classification (of information); Data acquisition;
Data storage equipment; Decision support systems; Human
engineering; Information retrieval systems; Knowledge
based systems; Learning systems; Man machine systems;
Performance; Reuters collection; Societies and
institutions; Standards; Terminology; Text
categorization",
}
@Article{Yang:1994:EBM,
author = "Yiming Yang and Christopher G. Chute",
title = "An Example-Based Mapping Method for Text
Categorization and Retrieval",
journal = j-TOIS,
volume = "12",
number = "3",
pages = "252--277",
month = jul,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Text Categorization.",
URL = "http://www.acm.org:80",
abstract = "A unified model for text categorization and text
retrieval is introduced. We use a training set of
manually categorized documents to learn word-category
associations, and use these associations to predict the
categories of arbitrary documents. Similarly, we use a
training set of queries and their related documents to
obtain empirical associations between query words and
indexing terms of documents, and use these associations
to predict the related documents of arbitrary queries.
A Linear Least Squares Fit (LLSF) technique is employed
to estimate the likelihood of these associations.
Document collections from the MEDLINE database and Mayo
patient records are used for studies on the
effectiveness of our approach, and on how much the
effectiveness depends on the choices of training data,
indexing language, word-weighting scheme, and
morphological canonicalization. Alternative methods are
also tested on these data collections for comparison.
It is evident that the LLSF approach uses the relevance
information effectively within human decisions of
categorization and retrieval, and achieves a semantic
mapping of free texts to their representations in an
indexing language. Such a semantic mapping leads to a
significant improvement in categorization and
retrieval, compared to alternative approaches.",
acknowledgement = ack-nhfb,
affiliation = "Mayo Clinic\slash Foundation",
affiliationaddress = "Rochester, MN, USA",
classification = "721.1; 723.2; 723.3; 903.1; 903.3; 921.6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Classification (of information); Computational
linguistics; Data acquisition; Database systems; Human
engineering; Indexing (of information); Information
analysis; Information retrieval; Learning systems;
Least squares approximations; Mapping; Mathematical
models; Morphological canonicalization; Query
languages; Text categorization; Text retrieval",
}
@Article{Liddy:1994:TCM,
author = "Elizabeth D. Liddy and Woojin Paik and Edmund S. Yu",
title = "Text Categorization for Multiple Users Based on
Semantic Features from a Machine-Readable Dictionary",
journal = j-TOIS,
volume = "12",
number = "3",
pages = "278--295",
month = jul,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Text Categorization.",
URL = "http://www.acm.org:80",
abstract = "The text categorization module described here provides
a front-end filtering function for the larger DR-LINK
text retrieval system [Liddy and Myaeng 1993]. The
module evaluates a large incoming stream of documents
to determine which documents are sufficiently similar
to a profile at the broad subject level to warrant more
refined representation and matching. To accomplish this
task, each substantive word in a text is first
categorized using a feature set based on the semantic
Subject Field Codes (SFCs) assigned to individual word
senses in a machine-readable dictionary. When tested on
50 user profiles and 550 megabytes of documents,
results indicate that the feature set that is the basis
of the text categorization module and the algorithm
that establishes the boundary of categories of
potentially relevant documents accomplish their tasks
with a high level of performance. This means that the
category of potentially relevant documents for most
profiles would contain at least 80\% of all documents
later determined to be relevant to the profile. The
number of documents in this set would be uniquely
determined by the system's category-boundary predictor,
and this set is likely to contain less than 5\% of the
incoming stream of documents.",
acknowledgement = ack-nhfb,
affiliation = "Syracuse Univ",
affiliationaddress = "Syracuse, NY, USA",
classification = "721.1; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Abstracting; Algorithms; Classification (of
information); Codes (symbols); Computational
linguistics; Encoding (symbols); Indexing (of
information); Information retrieval systems; Machine
readable dictionary; Performance; Semantic features;
Semantic vectors; Subject field coding; Terminology;
Text categorization; User interfaces",
}
@Article{Riloff:1994:IEB,
author = "Ellen Riloff and Wendy Lehnert",
title = "Information Extraction as a Basis for High-Precision
Text Classification",
journal = j-TOIS,
volume = "12",
number = "3",
pages = "296--333",
month = jul,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Text Categorization.",
URL = "http://www.acm.org:80",
abstract = "We describe an approach to text classification that
represents a compromise between traditional word-based
techniques and in-depth natural language processing.
Our approach uses a natural language processing task
called `information extraction' as a basis for
high-precision text classification. We present three
algorithms that use varying amounts of extracted
information to classify texts. The relevancy signatures
algorithm uses linguistic phrases; the augmented
relevancy signatures algorithm uses phrases and local
context; and the case-based text classification
algorithm uses larger pieces of context. Relevant
phrases and contexts are acquired automatically using a
training corpus. We evaluate the algorithms on the
basis of two test sets from the MUC-4 corpus. All three
algorithms achieved high precision on both test sets,
with the augmented relevancy signatures algorithm and
the case-based algorithm reaching 100\% precision with
over 60\% recall on one set. Additionally, we compare
the algorithms on a larger collection of 1700 texts and
describe an automated method for empirically deriving
appropriate threshold values. The results suggest that
information extraction techniques can support
high-precision text classification and, in general,
that using more extracted information improves
performance. As a practical matter, we also explain how
the text classification system can be easily ported
across domains.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Massachusetts",
affiliationaddress = "Amherst, MA, USA",
classification = "721.1; 723.2; 903.1; 903.3; 922.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Augmented relevancy signatures algorithms;
Case based text classification; Classification (of
information); Computational linguistics; Data
acquisition; Indexing (of information); Information
analysis; Information extraction; Information
retrieval; Natural language processing systems; Online
searching; Phrases; Statistical methods; Training
corpus",
wwwpages = "296--337",
wwwtitle = "Information Extraction as a Basis for High-Precision
Text",
}
@Article{Anonymous:1994:IA,
author = "Anonymous",
title = "Information for Authors",
journal = j-TOIS,
volume = "12",
number = "3",
pages = "333--337",
month = jul,
year = "1994",
bibdate = "Mon Jan 18 12:02:07 1999",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Merz:1994:DQF,
author = "Ulla Merz and Roger King",
title = "{DIRECT}: a Query Facility for Multiple Databases",
journal = j-TOIS,
volume = "12",
number = "4",
pages = "339--359",
month = oct,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The subject of this research project is the
architecture and design of a multidatabase query
facility. These databases contain structured data,
typical for business applications. Problems addressed
are: presenting a uniform interface for retrieving data
from multiple databases, providing autonomy for the
component databases, and defining an architecture for
semantic services. DIRECT is a query facility for
heterogeneous databases. The databases and their
definitions can differ in their data models, names,
types, and encoded values. Instead of creating a global
schema, descriptions of different databases are allowed
to coexist. A multidatabase query language provides a
uniform interface for retrieving data from different
databases. DIRECT has been exercised with operational
databases that are part of an automated business
system.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Colorado",
affiliationaddress = "Boulder, CO, USA",
classification = "721.1; 723.1; 723.2; 723.3; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computational linguistics; Computer architecture; Data
models; Data structures; direct query facility;
Heterogeneous databases; Information retrieval;
Interfaces (computer); Multiple databases; Query
languages",
}
@Article{Chang:1994:SAB,
author = "Man Kit Chang and Carson C. Woo",
title = "A Speech Act Based Negotiation Protocol: Design,
Implementation, and Test Use",
journal = j-TOIS,
volume = "12",
number = "4",
pages = "360--382",
month = oct,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Existing negotiation protocols used in Distributed
Artificial Intelligence (DAI) systems rarely take into
account the results from negotiation research. We
propose a negotiation protocol, SANP (Speech-Act-based
Negotiation Protocol), which is based on Ballmer and
Brennenstuhl's speech act classification and on
negotiation analysis literature. The protocol is
implemented as a domain-independent system using
Strudel, which is an electronic mail toolkit. A small
study tested the potential use of the protocol.
Although a number of limitations were found in the
study, the protocol appears to have potential in
domains without these limitations, and it can serve as
a building block to design more general negotiation
protocols.",
acknowledgement = ack-nhfb,
affiliation = "Hong Kong Baptist Coll",
affiliationaddress = "Hong Kong",
classification = "722.3; 722.4; 723.1; 723.4; 723.5; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Data communication systems;
Data structures; Distributed artificial intelligence;
Distributed computer systems; Electronic mail; Expert
systems; Information retrieval systems; Network
protocols; Office automation; Organizational computing
systems; Societies and institutions; Speech act based
negotiation protocol",
}
@Article{Chimera:1994:EET,
author = "Richard Chimera and Ben Shneiderman",
title = "An Exploratory Evaluation of Three Interfaces for
Browsing Large Hierarchical Tables of Contents",
journal = j-TOIS,
volume = "12",
number = "4",
pages = "383--406",
month = oct,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Three different interfaces were used to browse a large
(1296 items) table of contents. A fully expanded stable
interface, expand\slash contract interface, and
multipane interface were studied in a between-groups
experiment with 41 novice participants. Nine timed fact
retrieval tasks were performed; each task is analyzed
and discussed separately. We found that both the
expand\slash contract and multipane interfaces produced
significantly faster times than the stable interface
for many tasks using this large hierarchy; other
advantages of the expand\slash contract and multipane
interfaces over the stable interface are discussed. The
animation characteristics of the expand\slash contract
interface appear to play a major role. Refinements to
the multipane and expand\slash contract interfaces are
suggested. A predictive model for measuring navigation
effort of each interface is presented.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Maryland",
affiliationaddress = "College Park, MD, USA",
classification = "461.4; 722.2; 723.2; 903.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Expand/contract interfaces; Hierarchical systems;
Hierarchical tables of contents; Human engineering; Man
machine systems; Multipane interfaces; Online
searching; User interfaces",
wwwauthor = "B. Shneiderman and R. Chimera",
wwwtitle = "Evaluation of Three Interfaces for Browsing
Hierarchical Tables of Contents",
}
@Article{Wong:1994:PBD,
author = "Stephen T. C. Wong",
title = "Preference-Based Decision Making for Cooperative
Knowledge-Based Systems",
journal = j-TOIS,
volume = "12",
number = "4",
pages = "407--435",
month = oct,
year = "1994",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Recent advances in cooperative knowledge-based systems
(CKBS) offer significant promise for intelligent
interaction between multiple AI systems for solving
larger, more complex problems. In this paper, we
propose a logical, qualitative problem-solving scheme
for CKBS that uses social choice theory as a formal
basis for making joint decisions and promoting conflict
resolution. This scheme consists of three steps: (1)
the selection of decision criteria and competing
alternatives, (2) the formation of preference profiles
and collective choices, and (3) the negotiation among
agents as conflicts arise in group decision making. In
this paper, we focus on the computational mechanisms
developed to support steps (2) and (3) of the scheme.
In addition, the practicality of the scheme is
illustrated with examples taken from a working
prototype dealing with collaborative structural design
of buildings.",
acknowledgement = ack-nhfb,
affiliation = "Inst for New Generation Computer Technology",
affiliationaddress = "Tokyo, Jpn",
classification = "461.4; 723.2; 723.4; 723.4.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Cooperative knowledge based
systems; Decision support systems; Distributed
artificial intelligence; Heuristic methods; Human
engineering; Information retrieval systems; Knowledge
based systems; Preference based decision making; Social
choice theory",
wwwtitle = "Cooperative Decision Making Based on Preferences",
}
@Article{Isakowitz:1995:TLP,
author = "Tom{\'a}s Isakowitz and Shimon Schocken and Henry C.
{Lucas, Jr.}",
title = "Toward a Logical\slash Physical Theory of Spreadsheet
Modeling",
journal = j-TOIS,
volume = "13",
number = "1",
pages = "1--37",
month = jan,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "In spite of the increasing sophistication and power of
commercial spreadsheet packages, we still lack a formal
theory or a methodology to support the construction and
maintenance of spreadsheet models. Using a dual
logical\slash physical perspective, we identify four
principal components that characterize any spreadsheet
model: schema, data, editorial, and binding. We present
a factoring algorithm for identifying and extracting
these components from conventional spreadsheets with
minimal user intervention, and a synthesis algorithm
that assists users in the construction of executable
spreadsheets from reusable model components. This
approach opens new possibilities for applying
object-oriented and model management techniques to
support the construction, sharing, and reuse of
spreadsheet models in organizations. Importantly, our
approach to model management and the Windows-based
prototype that we have developed are designed to
coexist with, rather than replace, traditional
spreadsheet programs. In other words, the users are not
required to learn a new modeling language; instead,
their logical models and data sets are extracted from
their spreadsheets transparently, as a side-effect of
using standard spreadsheet programs.",
acknowledgement = ack-nhfb,
affiliation = "New York Univ",
classification = "723.1; 723.1.1; 723.2; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Computer programming languages; Computer
simulation; Computer software; Data reduction; Data
structures; Factoring algorithm; Model management;
Spreadsheet modeling theory; Spreadsheets",
}
@Article{Wong:1995:MIR,
author = "S. K. M. Wong and Y. Y. Yao",
title = "On Modeling Information Retrieval with Probabilistic
Inference",
journal = j-TOIS,
volume = "13",
number = "1",
pages = "38--68",
month = jan,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "This article examines and extends the logical models
of information retrieval in the context of probability
theory. The fundamental notions of term weights and
relevance are given probabilistic interpretations. A
unified framework is developed for modeling the
retrieval process with probabilistic inference. This
new approach provides a common conceptual and
mathematical basis for many retrieval models, such as
the Boolean, fuzzy set, vector space, and conventional
probabilistic models. Within this framework, the
underlying assumptions employed by each model are
identified, and the inherent relationships between
these models are analyzed. Although this article is
mainly a theoretical analysis of probabilistic
inference for information retrieval, practical methods
for estimating the required probabilities are provided
by simple examples.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Regina",
affiliationaddress = "Regina, Sask, Can",
classification = "721.1; 723.2; 903.1; 903.3; 921.1; 921.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Boolean algebra; Data structures; Document
representation; Fuzzy sets; Indexing (of information);
Information retrieval; Information theory; Mathematical
models; Maximum entropy principle; Minimum entropy
principle; Probabilistic logics; Probability;
Similarity measures; Theorem proving; Vector space
model",
}
@Article{Salminen:1995:THI,
author = "Airi Salminen and Jean Tague-Sutcliffe and Charles
McClellan",
title = "From Text to Hypertext by Indexing",
journal = j-TOIS,
volume = "13",
number = "1",
pages = "69--99",
month = jan,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "A model is presented for converting a collection of
documents to hypertext by means of indexing. The
documents are assumed to be semistructured, i.e., their
text is a hierarchy of parts, and some of the parts
consist of natural language. The model is intended as a
framework for specifying hypertextual reading
capabilities for specific application areas and for
developing new automated tools for the conversion of
semistructured text to hypertext. In the model, two
well-known paradigms --- formal grammars and document
indexing --- are combined. The structure of the source
text is defined by a schema that is a constrained
context-free grammar. The hierarchic structure of the
source may thus be modeled by a parse tree for the
grammar. The effect of indexing is described by grammar
transformations. The new grammar, called an indexing
schema, is associated with a new parse tree where some
text parts are index elements. The indexing schema may
hide some parts of the original documents or the
structure of some parts. For information retrieval,
parts of the indexed text are considered to be nodes of
a hypergraph. In the hypergraph-based information
access, the navigation capabilities of hypertext
systems are combined with the querying capabilities of
information retrieval systems.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Jyvaskyla",
affiliationaddress = "Jyvaskyla, Finl",
classification = "721.1; 723.2; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Automata theory; Constraint theory; Content analysis;
Context free grammars; Data structures; Formal logic;
Hypertext; Indexing (of information); Information
retrieval systems; Structured text; Text entities;
Transient hypergraphs",
wwwpages = "69--111",
}
@Article{Cooper:1995:SIM,
author = "William S. Cooper",
title = "Some Inconsistencies and Misidentified Modeling
Assumptions in Probabilistic Information Retrieval",
journal = j-TOIS,
volume = "13",
number = "1",
pages = "100--111",
month = jan,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Research in the probabilistic theory of information
retrieval involves the construction of mathematical
models based on statistical assumptions. One of the
hazards inherent in this kind of theory construction is
that the assumptions laid down may be inconsistent in
unanticipated ways with the data to which they are
applied. Another hazard is that the stated assumptions
may not be those on which the derived modeling
equations or resulting experiments are actually based.
Both kinds of mistakes have been made in past research
on probabilistic information retrieval. One consequence
of these errors is that the statistical character of
certain probabilistic IR models, including the
so-called Binary Independence model, has been seriously
misapprehended.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California",
affiliationaddress = "Berkeley, CA, USA",
classification = "721.1; 722.4; 723.2; 903.3; 922.1; 922.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Bibliographic retrieval systems; Bibliographic
searching; Binary independence model; Data structures;
Document retrieval; Hazards and race conditions;
Information retrieval; Online searching; Probabilistic
logics; Probability; Statistical methods",
wwwtitle = "Some Inconsistencies and Misidentified Modelling
Assumptions in Probabilistic Information Retrieval",
}
@Article{Anonymous:1995:AR,
author = "Anonymous",
title = "Acknowledgment to Referees",
journal = j-TOIS,
volume = "13",
number = "1",
pages = "112--113",
month = jan,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 16:21:56 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Gudivada:1995:DEA,
author = "Venkat N. Gudivada and Vijay V. Raghavan",
title = "Design and Evaluation of Algorithms for Image
Retrieval by Spatial Similarity",
journal = j-TOIS,
volume = "13",
number = "2",
pages = "115--144",
month = apr,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "An algorithm for computing the spatial similarity
between two symbolic images is proposed. This
algorithms is simple in the sense that it can deal with
translation, scale and rotational variances in images.
The idea of quantifying a system's retrieval quality by
having an expert specify the expected rank ordering
with respect to each query for a set of test queries is
also introduced. Finally, a comparison of the
characteristics of the proposed algorithm with those of
the previously available algorithms revealed that the
proposed algorithm is more efficient and it provides a
rank ordering of images that consistently matches with
the expert's expected rank ordering.",
acknowledgement = ack-nhfb,
affiliation = "Ohio Univ",
affiliationaddress = "Athens, OH, USA",
classification = "721.1; 722.2; 723.1; 723.3; 903.3; 921.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Computational complexity; Database
systems; Expert systems; Graph theory; Image databases;
Image retrieval; Image retrieval systems; Information
retrieval; Information retrieval systems; Query
languages; Rotational invariance; Spatial similarity;
User interfaces",
wwwtitle = "An Experimental Evaluation of Algorithms for Retrieval
by Spatial Similarity",
}
@Article{Rangan:1995:FTC,
author = "P. Venkat Rangan and Srinivas Ramanathan and Srihari
Sampathkumar",
title = "Feedback Techniques for Continuity and Synchronization
in Multimedia Information Retrieval",
journal = j-TOIS,
volume = "13",
number = "2",
pages = "145--176",
month = apr,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "The development of techniques for supporting
continuous and synchronous retrieval from multimedia
servers is discussed. Several feedback techniques that
remain robust even in the presence of playback rate
mismatches and network delay jitter are presented. In
general, the constant rate feedback techniques
developed in this study form the basis of a prototype
on-demand information server developed at the UCSD
Multimedia Laboratory.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California at San Diego",
affiliationaddress = "La Jolla, CA, USA",
classification = "722.3; 723.3; 723.5; 903.3; 903.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer networks; Computer simulation; Feedback;
Information retrieval; Information retrieval systems;
Information services; Intermedia synchronization;
Intramedia continuity; Multimedia; Multimedia
information retrieval; Synchronization",
wwwauthor = "P. V. Rangan and S. Ramanathan",
}
@Article{Malone:1995:EOR,
author = "Thomas W. Malone and Kum-Yew Lai and Christopher Fry",
title = "Experiments with Oval: a Radically Tailorable Tool for
Cooperative Work",
journal = j-TOIS,
volume = "13",
number = "2",
pages = "177--205",
month = apr,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "This article describes a series of tests of the
generality of a `radically tailorable' tool for
cooperative work. Users of this system can create
applications by combining and modifying four kinds of
building blocks: objects, views, agents, and links. We
found that user-level tailoring of these primitives can
provide most of the functionality found in well-known
cooperative work systems such as gIBIS, Coordinator,
Lotus Notes, and Information Lens. These primitives,
therefore, appear to provide an elementary `tailoring
language' out of which a wide variety of integrated
information management and collaboration applications
can be constructed by end users.",
acknowledgement = ack-nhfb,
affiliation = "MIT Cent for Coordination Science",
affiliationaddress = "Cambridge, MA, USA",
classification = "722.2; 723.1; 723.1.1; 723.3; 723.5; 903",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer aided software engineering; Computer
programming; Computer simulation; Computer supported
cooperative work; End user programming; High level
languages; Human engineering; Information management;
Information retrieval systems; Radical tailorability;
User interfaces",
}
@Article{Strong:1995:EEH,
author = "Diane M. Strong and Steven M. Miller",
title = "Exceptions and Exception Handling in Computerized
Information Processes",
journal = j-TOIS,
volume = "13",
number = "2",
pages = "206--233",
month = apr,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Exceptions, situations that cannot be correctly
processed by computer systems, occur frequently in
computer-based information processes. Five perspectives
on exceptions provide insights into why exceptions
occur and how they might be eliminated or more
efficiently handled. We investigate these perspectives
using an in-depth study of an operating information
process that has frequent exceptions. Our results
support the use of a total quality management (TQM)
approach of eliminating exceptions for some exceptions,
in particular, those caused by computer systems that
are poor matches to organizational processes. However,
some exceptions are explained better by a political
system perspective of conflicting goals between
subunits. For these exceptions and several other types,
designing an integrated human-computer process will
provide better performance than will eliminating
exceptions and moving toward an entirely automated
process.",
acknowledgement = ack-nhfb,
affiliation = "Boston Univ",
affiliationaddress = "Boston, MA, USA",
classification = "722.2; 722.4; 723.2; 723.5; 912.2; 913.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Administrative data processing; Computer applications;
Computer systems; Computerized information processes;
Data handling; Data processing; Exception handling;
Exceptions; Human computer interaction; Office
automation; Performance; Process design; Quality
assurance; Total quality management",
}
@Article{Celentano:1995:KBD,
author = "Augusto Celentano and Maria Grazia Fugini and Silvano
Pozzi",
title = "Knowledge-Based Document Retrieval in Office
Environments: The {Kabiria} System",
journal = j-TOIS,
volume = "13",
number = "3",
pages = "237--268",
month = jul,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "In the office environment, the retrieval of documents
is performed using the concepts contained in the
documents, information about the procedural context
where the documents are used, and information about the
regulations and laws that discipline the life of
documents within a given application domain. To fulfill
the requirements of such a sophisticated retrieval, we
propose a document retrieval model and system based on
the representation of knowledge describing the semantic
contents of documents, the way in which the documents
are managed by procedures and by people in the office,
and the application domain where the office operates.
The article describes the knowledge representation
issues needed for the document retrieval system and
presents a document retrieval model that captures these
issues. The effectiveness of the approach is
illustrated by describing a system, named Kabiria,
built on top of such model. The article describes the
querying and browsing environments, and the
architecture of the system.",
acknowledgement = ack-nhfb,
affiliation = "Politecnico di Milano",
affiliationaddress = "Milano, Italy",
classification = "722.1; 722.4; 723.1.1; 723.2; 723.4.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Administrative data processing; Browser; Computational
linguistics; Computer programming languages; Data
reduction; Data structures; Expert systems; Hypertext;
Information retrieval systems; Kabiria system;
Knowledge based document retrieval; Knowledge based
systems; Object orientation; Office automation; Systems
analysis; User interfaces",
}
@Article{Tuzhilin:1995:TKB,
author = "Alexander Tuzhilin",
title = "{Templar}: a Knowledge-Based Language for Software
Specifications Using Temporal Logic",
journal = j-TOIS,
volume = "13",
number = "3",
pages = "269--304",
month = jul,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "A software specification language Templar is defined
in this article. The development of the language was
guided by the following objectives: requirements
specifications written in Templar should have a clear
syntax and formal semantics, should be easy for a
systems analyst to develop and for an end-user to
understand, and it should be easy to map them into a
broad range of design specifications. Templar is based
on temporal logic and on the
Activity-Event-Condition-Activity model of a rule which
is an extension of the Event-Condition-Activity model
in active databases. The language supports a rich set
of modeling primitives, including rules, procedures,
temporal logic operators, events, activities,
hierarchical decomposition of activities, parallelism,
and decisions combined together into a cohesive
system.",
acknowledgement = ack-nhfb,
affiliation = "New York Univ",
affiliationaddress = "New York, NY, USA",
classification = "721.1; 723.1.1; 723.4.1; 921.6; 922.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computational linguistics; Computer hardware
description languages; Computer programming languages;
Database systems; Decision making; Formal logic;
Hierarchical systems; Knowledge based language Templar;
Knowledge based systems; Mathematical operators;
Natural languages; Software engineering; Temporal
logic",
}
@Article{Koike:1995:FVF,
author = "Hideki Koike",
title = "Fractal Views: a Fractal-Based Method for Controlling
Information Display",
journal = j-TOIS,
volume = "13",
number = "3",
pages = "305--323",
month = jul,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "Computer users often must view large amounts of
information through video displays which are physically
limited in size. Although some methods, which
automatically display\slash erase information units
based on their degrees of importance, have been
proposed, they lack an ability to keep the total amount
of displayed information nearly constant. We propose a
new method for information display based on fractal
theory. By regarding the information structures used in
computers as complex objects, we can abstract these
objects as well as control their amount. Using our
method, (1) the total amount of information is kept
nearly constant even when users change their focuses of
attention and (2) this amount can be set flexibly.
Through mathematical analysis, we show our method's
ability to control the amount. An application to
program display is also shown. When this method is
applied to the display of structured programs, it
provides fisheye-like views which integrate local
details around the focal point and major landmarks
further away.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Electro-Communications",
affiliationaddress = "Tokyo, Jpn",
classification = "722.2; 723.1; 723.2; 723.5; 903.1; 921.6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer systems programming; Data structures;
Fractals; Information analysis; Information
visualization; Program display; Software engineering;
Systems analysis; UI theory; User interfaces",
wwwpages = "305--324",
}
@Article{Kwok:1995:NAP,
author = "K. L. Kwok",
title = "A Network Approach to Probabilistic Information
Retrieval",
journal = j-TOIS,
volume = "13",
number = "3",
pages = "324--353",
month = jul,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "In this article we show how probabilistic information
retrieval based on document components may be
implemented as a feedforward (feedbackward) artificial
neural network. The network supports adaptation of
connection weights as well as the growing of new edges
between queries and terms based on user relevance
feedback data for training, and it reflects query
modification and expansion in information retrieval. A
learning rule is applied that can also be viewed as
supporting sequential learning using a harmonic
sequence learning rate. Experimental results with four
standard small collections and a large Wall Street
Journal collection (173,219 documents) show that
performance of feedback improves substantially over no
feedback, and further gains are obtained when queries
are expanded with terms from the feedback documents.
The effect is much more pronounced in small collections
than in the large collection. Query expansion may be
considered as a tool for both precision and recall
enhancement. In particular, small query expansion
levels of about 30 terms can achieve most of the gains
at the low-recall high-precision region, while larger
expansion levels continue to provide gains at the
high-recall low-precision region of a precision recall
curve.",
acknowledgement = ack-nhfb,
affiliation = "City Univ of New York",
affiliationaddress = "Flushing, NY, USA",
classification = "721.1; 723.2; 723.4; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data reduction; Data structures; Document focused
relevance feedback; Feedback; Feedforward neural
networks; Indexing (of information); Information
retrieval; Learning systems; Probabilistic information
retrieval; Probabilistic logics; Query expansion; Query
focused relevance feedback",
wwwpages = "325-354",
}
@Article{Kong:1995:DDI,
author = "Q. Kong and G. Chen",
title = "On Deductive Databases with Incomplete Information",
journal = j-TOIS,
volume = "13",
number = "3",
pages = "354--369",
month = jul,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
abstract = "In order to extend the ability to handle incomplete
information in a definite deductive database, a Horn
clause-based system representing incomplete information
as incomplete constants is proposed. By using the
notion of incomplete constants the deductive database
system handles incomplete information in the form of
sets of possible values, thereby giving more
information than null values. The resulting system
extends Horn logic to express a restricted form of
indefiniteness. Although a deductive database with this
kind of incomplete information is, in fact, a subset of
an indefinite deductive database system, it represents
indefiniteness in terms of value incompleteness, and
therefore it can make use of the existing Horn logic
computation rules. The inference rules for such a
system are presented, its model theory discussed, and a
model theory of indefiniteness proposed. The theory is
consistent with minimal model theory and extends its
expressive power.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Queensland",
affiliationaddress = "Queensland, Aust",
classification = "721.1; 723.1.1; 723.2; 723.3; 723.4.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data structures; Database systems; Formal logic; Horn
clause; Incomplete information; Inference engines;
Prolog (programming language); Query evaluation; Query
languages; Systems analysis",
wwwpages = "355--369",
wwwtitle = "On Deductive Database with Incomplete Information",
}
@Article{Stevens:1995:ISI,
author = "Scott Stevens and Thomas Little",
title = "Introduction to the Special Issue on Video Information
Retrieval",
journal = j-TOIS,
volume = "13",
number = "4",
pages = "371--372",
month = oct,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
wwwauthor = "Tom Little and Scott Stevens",
wwwtitle = "Guest Editors' Introduction",
}
@Article{Chua:1995:VRS,
author = "Tat-Seng Chua and Li-Qun Ruan",
title = "A Video Retrieval and Sequencing System",
journal = j-TOIS,
volume = "13",
number = "4",
pages = "373--407",
month = oct,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Video Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "Video is an effective medium for capturing the events
in the real world around us, and a vast amount of video
materials exists, covering a wide range of
applications. However, widespread use of video in
computer applications is often impeded by the lack of
effective tools to manage video information
systematically. This article discusses the design and
implementation of a frame-based video retrieval and
sequencing system (VRSS). The system is designed to
support the entire process of video information
management: segmenting, indexing, retrieving, and
sequencing of video data. A semiautomatic tool is
developed to divide video sequences into meaningful
shots. Each video shot is logged using text
descriptions, audio dialogue, and cinematic attributes.
A two-layered, concept-based model is used as the basis
for accurately retrieving relevant video shots based on
users' free-text queries. A cinematic, rule-based,
virtual editing tool is also developed to sequence the
video shots retrieved for presentation within a
specified time constraint. The system has been tested
on a video documentary on the NUS (National University
of Singapore) engineering faculty. The results of video
retrieval experiments are encouraging.",
acknowledgement = ack-nhfb,
affiliation = "Natl Univ of Singapore",
affiliationaddress = "Singapore, Singapore",
classification = "722.2; 723.2; 723.3; 723.4.1; 723.5; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Cinematic rules; Computer simulation; Data structures;
Frame based modeling; Image segmentation; Indexing (of
information); Information management; Information
retrieval; Information retrieval systems; Knowledge
based systems; Knowledge representation; Multimedia;
Query languages; Systems analysis; User interfaces;
Video; Video retrieval; Video retrieval and sequencing
system; Video signal processing; Virtual editing",
}
@Article{Dimitrova:1995:MRV,
author = "Nevenka Dimitrova and Forouzan Golshani",
title = "Motion Recovery for Video Content Classification",
journal = j-TOIS,
volume = "13",
number = "4",
pages = "408--439",
month = oct,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Video Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "Like other types of digital information, video
sequences must be classified based on the semantics of
their contents. A more-precise and completer extraction
of semantic information will result in a more-effective
classification. The most-discernible difference between
still images and moving pictures stems from movements
and variations. Thus, to go from the realm of
still-image repositories to video databases, we must be
able to deal with motion. Particularly, we need the
ability to classify objects appearing in a video
sequence based on their characteristics and features
such as shape or color, as well as their movements. By
describing the movements that we derive from the
process of motion analysis, we introduce a dual
hierarchy consisting of spatial and temporal parts for
video sequence representation. This gives us the
flexibility to examine arbitrary sequences of frames at
various levels of abstraction and to retrieve the
associated temporal information (say, object
trajectories) in addition to the spatial
representation. Our algorithm for motion detection uses
the motion compensation component of the MPEG
video-encoding scheme and then computes trajectories
for objects of interest. The specification of a
language for retrieval of video based on the spatial as
well as motion characteristics is presented.",
acknowledgement = ack-nhfb,
affiliation = "Arizona State Univ",
affiliationaddress = "Tempe, AZ, USA",
classification = "723.1; 723.1.1; 723.2; 723.3; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Classification (of information); Computer
hardware description languages; Database systems;
Feature extraction; Image analysis; Image coding;
Information retrieval; Motion pictures; Motion
recovery; mpeg; Object recognition; Video analysis;
Video content classification; Video databases; Video
retrieval; Video sequence; Video signal processing",
}
@Article{Bulterman:1995:EVH,
author = "Dick C. A. Bulterman",
title = "Embedded Video in Hypermedia Documents: Supporting
Integration and Adaptive Control",
journal = j-TOIS,
volume = "13",
number = "4",
pages = "440--470",
month = oct,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Video Information Retrieval.",
URL = "http://www.acm.org:80",
abstract = "As the availability of digital video becomes
commonplace, a shift in application focus will occur
from merely accessing video as an independent data
stream to embedding video with other multimedia data
types into coordinated hypermedia presentations. The
migration to embedded video will present new demands on
application and support environments: processing of any
one piece of video data will depend on how that data
relates to other data streams active within the same
presentation. This article describes presentation,
synchronization, and interaction control issues for
manipulating embedded video. First we describe the
requirements for embedded video, contrasted against
other forms of video use. Next we consider mechanisms
for describing and implementing the behavior of
embedded-video segments relative to other data items in
a document; these relationships form the basis of
implementing cooperative control among the events in a
presentation. Finally we consider extending the
possibilities for tailoring embedded video to the
characteristics of the local runtime environment; this
forms the basis for adaptive, application-level
quality-of-service control of a presentation. In all
cases, we describe a mechanism to externalize the
behavior of hypermedia presentations containing
resource-intensive data requirements so that effective
control can be implemented by low-level system
facilities based on application-specific requirements.
We present our results in terms of the CMIFed
authoring\slash presentation system.",
acknowledgement = ack-nhfb,
affiliation = "Centrum voor Wiskunde en Informatica",
affiliationaddress = "Amsterdam, Neth",
classification = "723.1; 723.2; 731.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Adaptive control systems; Algorithms; Data processing;
Embedded video; Hypermedia documents; Information
retrieval systems; Multimedia; Synchronization; Systems
analysis; Video presentation; Video signal processing",
}
@Article{Keller:1995:XAI,
author = "Ralf Keller and Wolfgang Effelsberg and Bernd
Lamparter",
title = "{XMovie}: Architecture and Implementation of a
Distributed Movie System",
journal = j-TOIS,
volume = "13",
number = "4",
pages = "471--499",
month = oct,
year = "1995",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
note = "Special Issue on Video Information Retrieval.",
URL = "http://www.acm.org:80",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
}
@Article{Anonymous:1996:MGS,
author = "Anonymous",
title = "In Memoriam: {Gerard Salton}",
journal = j-TOIS,
volume = "14",
number = "1",
pages = "1--1",
month = jan,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 17:28:08 1999",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lucarella:1996:VRE,
author = "Dario Lucarella and Antonella Zanzi",
title = "A Visual Retrieval Environment for Hypermedia
Information Systems",
journal = j-TOIS,
volume = "14",
number = "1",
pages = "3--29",
month = jan,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/lucarella.html",
abstract = "A graph-based object model that may be used as a
uniform framework for direct manipulation of multimedia
information is presented. After motivating the need for
abstraction and structuring mechanisms in hypermedia
systems, the notion of perspective is introduced, which
is a form of data abstraction that acts as a user
interface to the system, providing control over the
visibility of the objects and their properties.
Presented is a visual retrieval environment that
effectively combines filtering, browsing, and
navigation to provide an integrated view of the
retrieval problem. Design and implementation issues are
outlined for MORF (Multimedia Object Retrieval
Environment), a prototype system relying on the
proposed model. The focus is on the main user interface
functionalities. Actual interaction sessions are
presented including schema creation, information
loading, and information retrieval.",
acknowledgement = ack-nhfb,
affiliation = "Centro Ricerca di Automatica",
affiliationaddress = "Milano, Italy",
classification = "722.2; 723.2; 723.3; 723.5; 903.3; 903.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Abstracting; Browsing; Computer simulation; Data
structures; Database systems; Graphical user
interfaces; Hypermedia information systems; Hypertext;
Information filtering; Information retrieval systems;
Information services; Information technology;
Interactive computer graphics; Multimedia; Multimedia
object retrieval environment; Pattern matching; Schema
graph; Subgraph; Systems analysis; Visual retrieval
environment; Visualization",
}
@Article{Robey:1996:SPI,
author = "Daniel Robey and Michael Newman",
title = "Sequential Patterns in Information Systems
Development: An Application of a Social Process Model",
journal = j-TOIS,
volume = "14",
number = "1",
pages = "30--63",
month = jan,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/robey.html",
abstract = "We trace the process of developing and implementing a
materials management system in one company over a
15-year period. Using a process research model
developed by Newman and Robey, we identify 44 events in
the process and define them as either encounters or
episodes. Encounters are concentrated events, such as
meetings and announcements, that separate episodes,
which are events of longer duration. By examining the
sequence of events over the 15 years of the case, we
identify a pattern of repeated failure, followed by
success. Our discussion centers on the value of
detecting and displaying such patterns and the need for
theoretical interpretation of recurring sequences of
events. Five alternative theoretical perspectives,
originally proposed by Kling, are used to interpret the
sequential patterns identified by the model. We
conclude that the form of the process model allows
researchers who operate from different perspectives to
enrich their understanding of the process of system
development.",
acknowledgement = ack-nhfb,
affiliation = "Georgia State Univ",
affiliationaddress = "Atlanta, GA, USA",
classification = "722.4; 723.2; 723.3; 723.5; 903.3; 912.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Administrative data processing; Computer systems; Data
structures; Database systems; Information retrieval
systems; Management information systems; Materials
management system; Process research model; Sequential
patterns; Social process model; System implementation;
Systems analysis",
wwwtitle = "Sequential Patterns in Information Systems
Development: An Application of a Process Model",
}
@Article{Taghva:1996:EMB,
author = "Kazem Taghva and Julie Borsack and Allen Condit",
title = "Evaluation of Model-Based Retrieval Effectiveness with
{OCR} Text",
journal = j-TOIS,
volume = "14",
number = "1",
pages = "64--93",
month = jan,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/taghva.html",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
}
@Article{Berghel:1996:EUE,
author = "Hal Berghel and David Roach",
title = "An Extension of {Ukkonen}'s Enhanced Dynamic
Programming {ASM} Algorithm",
journal = j-TOIS,
volume = "14",
number = "1",
pages = "94--106",
month = jan,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/berghel.html",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
}
@Article{Lee:1996:DRW,
author = "Dik Lun Lee and Liming Ren",
title = "Document Ranking on Weight-Partitioned Signature
Files",
journal = j-TOIS,
volume = "14",
number = "2",
pages = "109--137",
month = apr,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/lee.html",
abstract = "A signature file organization, called the
weight-partitioned signature file, for supporting
document ranking is proposed. It employs multiple
signature files, each of which corresponds to one term
frequency, to represent terms with different term
frequencies. Words with the same term frequency in a
document are grouped together and hashed into the
signature file corresponding to that term frequency.
This eliminates the need to record the term frequency
explicitly for each word. We investigate the effect of
false drops on retrieval effectiveness if they are not
eliminated in the search process. We have shown that
false drops introduce insignificant degradation on
precision and recall when the false-drop probability is
below a certain threshold. This is an important result
since false-drop elimination could become the
bottleneck in systems using fast signature file search
techniques. We perform an analytical study on the
performance of the weight-partitioned signature file
under different search strategies and configurations.
An optimal formula is obtained to determine for a fixed
total storage overhead the storage to be allocated to
each partition in order to minimize the effect of false
drops on document ranks. Experiments were performed
using a document collection to support the analytical
results.",
acknowledgement = ack-nhfb,
affiliation = "Ohio State Univ",
affiliationaddress = "Columbus, OH, USA",
classification = "722.1; 723.2; 723.5; 903.3; 922.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Access method; Computer simulation; Document ranking;
Document retrieval; Encoding (symbols); File
organization; Information retrieval; Information
retrieval systems; Performance; Probability; Storage
allocation (computer); Superimposed coding; Text
retrieval; Weight partitioned signature files",
}
@Article{Rowe:1996:ULO,
author = "Neil C. Rowe",
title = "Using Local Optimality Criteria for Efficient
Information Retrieval with Redundant Information
Filters",
journal = j-TOIS,
volume = "14",
number = "2",
pages = "138--174",
month = apr,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/rowe.html",
abstract = "We consider information retrieval when the data ---
for instance, multimedia --- is computationally
expensive to fetch. Our approach uses `information
filters' to considerably narrow the universe of
possibilities before retrieval. We are especially
interested in redundant information filters that save
time over more general but more costly filters.
Efficient retrieval requires that decisions must be
made about the necessity, order, and concurrent
processing of proposed filters (an `execution plan').
We develop simple polynomial-time local criteria for
optimal execution plans and show that most forms of
concurrency are suboptimal with information filters.
Although the general problem of finding an optimal
execution plan is likely to be exponential in the
number of filters, we show experimentally that our
local optimality criteria, used in a polynomial-time
algorithm, nearly always find the global optimum with
15 filters or less, a sufficient number of filters for
most applications. Our methods require no special
hardware and avoid the high processor idleness that is
characteristic of massive-parallelism solutions to this
problem. We apply our ideas to an important
application, information retrieval of captioned data
using natural-language understanding, a problem for
which the natural-language processing can be the
bottleneck if not implemented well.",
acknowledgement = ack-nhfb,
affiliation = "Naval Postgraduate Sch",
affiliationaddress = "Monterey, CA, USA",
classification = "721.1; 723.1; 723.2; 723.3; 903.3; 921.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Boolean algebra; Concurrency control;
Conjunction; Information retrieval; Information
retrieval systems; Natural language processing systems;
Optimization; Performance; Query languages; Redundant
information filters",
}
@Article{Jungclaus:1996:TLO,
author = "Ralf Jungclaus and Gunter Saake and Thorsten Hartmann
and Cristina Sernadas",
title = "{TROLL} --- {A} Language for Object-Oriented
Specification of Information Systems",
journal = j-TOIS,
volume = "14",
number = "2",
pages = "175--211",
month = apr,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/hartmann.html",
abstract = "TROLL is a language particularly suited for the early
stages of information system development, when the
universe of discourse must be described. In TROLL the
descriptions of the static and dynamic aspects of
entities are integrated into object descriptions.
Sublanguages for data terms, for first-order and
temporal assertions, and for processes, are used to
describe respectively the static properties, the
behavior, and the evolution over time of objects. TROLL
organizes system design through object-orientation and
the support of abstractions such as classification,
specialization, roles, and aggregation. Language
features for state interactions and dependencies among
components support the composition of the system from
smaller modules, as does the facility of defining
interfaces on top of object descriptions.",
acknowledgement = ack-nhfb,
affiliation = "Deutsche Telekom",
affiliationaddress = "Bonn, Ger",
classification = "723.1; 723.1.1; 723.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer hardware description languages; Computer
programming languages; Data processing; Language
classifications; Language constructs and features;
Management information systems; Object oriented
specification; Software engineering; Systems analysis",
}
@Article{Grant:1996:CPM,
author = "Rebecca A. Grant and Chris A. Higgins",
title = "Computerized Performance Monitors as Multidimensional
Systems: Derivation and Application",
journal = j-TOIS,
volume = "14",
number = "2",
pages = "212--235",
month = apr,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/grant.html",
abstract = "An increasing number of companies are introducing
computer technology into more aspects of work.
Effective use of information systems to support office
and service work can improve staff productivity,
broaden a company's market, or dramatically change its
business. It can also increase the extent to which work
is computer mediated and thus within the reach of
software known as Computerized Performance Monitoring
and Control Systems (CPMCSs). Virtually all research
has studied CPMCSs as unidimensional systems. Employees
are described as `monitored' or `unmonitored' or as
subject to `high,' `moderate,' or `low' levels of
monitoring. Research that does not clearly distinguish
among possible monitor design cannot explain how
designs may differ in effect. Nor can it suggest how to
design better monitors. A multidimensional view of
CPMCSs describes monitor designs in terms of object of
measurements, tasks measured, recipient of data,
reporting period, and message content. This view is
derived from literature in control systems,
organizational behavior, and management information
systems. The multidimensional view can then be
incorporated into causal models to explain
contradictory results of earlier CPMCS research.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Victoria",
affiliationaddress = "Victoria, BC, Can",
classification = "723.1; 723.2; 723.5; 731.1; 912.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer applications; Computer software; Computerized
performance evaluation; Computerized performance
monitoring and control systems; Computerized work
monitoring; Control systems; Management information
systems; Monitoring; Personnel rating; Productivity;
Systems analysis; Work monitoring system design",
}
@Article{Guglielmo:1996:NLR,
author = "Eugene J. Guglielmo and Neil C. Rowe",
title = "Natural-Language Retrieval of Images Based on
Descriptive Captions",
journal = j-TOIS,
volume = "14",
number = "3",
pages = "237--267",
month = jul,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/guglielmo.html",
abstract = "We describe a prototype intelligent information
retrieval system that uses natural-language
understanding to efficiently locate captioned data.
Multimedia data generally require captions to explain
their features and significance. Such descriptive
captions often rely on long nominal compounds (strings
of consecutive nouns) which create problems of
disambiguating word sense. In our system, captions and
user queries are parsed and interpreted to produce a
logical form, using a detailed theory of the meaning of
nominal compounds. A fine-grain match can then compare
the logical form of the query to the logical forms for
each caption. To improve system efficiency, we first
perform a coarse-grain match with index files, using
nouns and verbs extracted from the query. Our
experiments with randomly selected queries and captions
from an existing image library show an increase of 30\%
in precision and 50\% in recall over the keyphrase
approach currently used. Our processing times have a
media of seven seconds as compared to eight minutes for
the existing system, and our system is much easier to
use.",
acknowledgement = ack-nhfb,
affiliation = "Monterey Bay Aquarium Research Inst (MBARI)",
affiliationaddress = "Moss Landing, CA, USA",
classification = "723.1.1; 723.2; 723.3; 723.4.1; 741; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Coarse grain match; Computational
linguistics; Database systems; Descriptive captions;
Fine grain match; Formal logic; Image processing;
Information retrieval systems; Intelligent information
retrieval system; Knowledge based systems; Knowledge
representation; Multimedia; Natural language processing
systems; Query languages",
}
@Article{Gottlob:1996:EOO,
author = "Georg Gottlob and Michael Schrefl and Brigitte Rock",
title = "Extending Object-Oriented Systems with Roles",
journal = j-TOIS,
volume = "14",
number = "3",
pages = "268--296",
month = jul,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/gottlob.html",
abstract = "This article shows how class-based object-oriented
systems can be extended to handle evolving objects
well. Class hierarchies are complemented by role
hierarchies, whose nodes represent role types an object
classified in the root may take on. At any point in
time, an entity is represented by an instance of the
root and an instance of every role type whose role it
currently plays. In a natural way, the approach extends
traditional object-oriented concepts, such as
classification, object identity, specialization,
inheritance, and polymorphism in a natural way. The
practicability of the approach is demonstrated by an
implementation in Smalltalk. Smalltalk was chosen
because it is widely known, which is not true for any
particular class-based object-oriented database
programming language. Roles can be provided in
Smalltalk by adding a few classes. There is no need to
modify the semantics of Smalltalk itself. Role
hierarchies are mapped transparently onto ordinary
classes. The presented implementation can easily be
ported to object-oriented database programming
languages based on Smalltalk, such as Gemstone's
OPAL.",
acknowledgement = ack-nhfb,
affiliation = "Vienna Univ of Technology",
affiliationaddress = "Wien, Austria",
classification = "721.1; 723.1; 723.1.1; 723.2; 723.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Class hierarchies; Computational linguistics; Computer
programming languages; Data structures; Database
systems; Object oriented databases; Object oriented
programming; Role hierarchies; Semantics; Smalltalk
programming language; Software engineering",
}
@Article{Gulla:1996:GEC,
author = "Jon Atle Gulla",
title = "A General Explanation Component for Conceptual
Modeling in {CASE} Environments",
journal = j-TOIS,
volume = "14",
number = "3",
pages = "297--329",
month = jul,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/gulla.html",
abstract = "In information systems engineering, conceptual models
are constructed to assess existing information systems
and work out requirements for new ones. As these models
serve as a means for communication between customers
and developers, it is paramount that both parties
understand the models, as well as that the models form
a proper basis for the subsequent design and
implementation of the systems. New CASE environments
are now experimenting with formal modeling languages
and various techniques for validating conceptual
models, though it seems difficult to come up with a
technique that handles the linguistic barriers between
the parties involved in a satisfactory manner. In this
article, we discuss the theoretical basis of an
explanation component implemented for the PPP CASE
environment. This component integrates other validation
techniques and provides a very flexible
natural-language interface to complex model
information. It describes properties of the modeling
language and the conceptual models in terms familiar to
users, and the explanations can be combined with
graphical model views. When models are executed, it can
justify requested inputs and explain computed outputs
by relating trace information to properties of the
models.",
acknowledgement = ack-nhfb,
classification = "721.1; 723.1; 723.1.1; 723.2; 723.3; 723.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Computational linguistics;
Computer aided software engineering; Computer graphics;
Computer simulation; Computer simulation languages;
Conceptual modeling; Database systems; Formal
languages; Information systems engineering; Natural
language processing systems; Program documentation;
Validation techniques",
wwwtitle = "A General Explanation Component for Conceptual
Modeling in {CASE} Environment",
}
@Article{Friedman:1996:BCS,
author = "Batya Friedman and Helen Nissenbaum",
title = "Bias in Computer Systems",
journal = j-TOIS,
volume = "14",
number = "3",
pages = "330--347",
month = jul,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/friedman.html",
abstract = "From an analysis of actual cases, three categories of
bias in computer systems have been developed:
preexisting, technical, and emergent. Preexisting bias
has its roots in social institutions, practices, and
attitudes. Technical bias arises from technical
constraints or considerations. Emergent bias arises in
a context of use. Although others have pointed to bias
in particular computer systems and have noted the
general problem, we know of no comparable work that
examines this phenomenon comprehensively and which
offers a framework for understanding and remedying it.
We conclude by suggesting that freedom from bias should
be counted among the select set of criteria ---
including reliability, accuracy, and efficiency ---
according to which the quality of systems in use in
society should be judged.",
acknowledgement = ack-nhfb,
affiliation = "Colby Coll",
affiliationaddress = "Waterville, ME, USA",
classification = "461.4; 722.4; 723.2; 901.1; 901.1.1; 901.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer ethics; Computer systems; Human values; Man
machine systems; Philosophical aspects; Reliability;
Social aspects; Social computing; Social impact; Social
sciences computing; Societies and institutions;
Software engineering; Standards; Systems analysis",
wwwpages = "330--346",
wwwtitle = "Bias in Computer Science",
}
@Article{Moffat:1996:SII,
author = "Alistair Moffat and Justin Zobel",
title = "Self-Indexing Inverted Files for Fast Text Retrieval",
journal = j-TOIS,
volume = "14",
number = "4",
pages = "349--379",
month = oct,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/moffat.html",
abstract = "Query-processing costs on large text databases are
dominated by the need to retrieve and scan the inverted
list of each query term. Retrieval time for inverted
lists can be greatly reduced by the use of compression,
but this adds to the CPU time required. Here we show
that the CPU component of query response time for
conjunctive Boolean queries and for informal ranked
queries can be similarly reduced, at little cost in
terms of storage, by the inclusion of an internal index
in each compressed inverted list. This method has been
applied in a retrieval system for a collection of
nearly two million short documents. Our experimental
results show that the self-indexing strategy adds less
than 20\% to the size of the compressed inverted file,
which itself occupies less than 10\% of the indexed
text, yet can reduce processing time for Boolean
queries of 5-10 terms to under one fifth of the
previous cost. Similarly, ranked queries of 40-50 terms
can be evaluated in as little as 25\% of the previous
time, with little or no loss of retrieval
effectiveness.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Melbourne",
affiliationaddress = "Parkville, Aust",
classification = "716.1; 722.1; 723.2; 723.3; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Boolean queries; Data compression; Data storage
equipment; File organization; Full text retrieval;
Index compression; Indexing (of information);
Information retrieval; Information retrieval systems;
Inverted file; Query languages; Query processing; Self
indexing",
}
@Article{Oberweis:1996:ISB,
author = "Andreas Oberweis and Peter Sander",
title = "Information System Behavior Specification by
High-Level {Petri} Nets",
journal = j-TOIS,
volume = "14",
number = "4",
pages = "380--420",
month = oct,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/oberweis.html",
abstract = "The specification of an information system should
include a description of structural system aspects as
well as a description of the system behavior. In this
article, we show how this can be achieved by high-level
Petri nets --- namely, the so-called NR/T-nets
(Nested-Relation\slash Transition Nets). In NR/T-nets,
the structural part is modeled by nested relations, and
the behavioral part is modeled by a novel Petri net
formalism. Each place of a net represents a nested
relation scheme, and the marking of each place is given
as a nested relation of the respective type. Insert and
delete operations in a nested relational database
(NF2-database) are expressed by transitions in a net.
These operations may operate not only on whole tuples
of a given relation, but also on `subtuples' of
existing tuples. The arcs of a net are inscribed with
so-called Filter Tables, which allow (together with an
optional logical expression as transition inscription)
conditions to be formulated on the specified (sub-)
tuples. The occurrence rule for NR/T-net transitions is
defined by the operations union, intersection, and
`negative' in lattices of nested relations. The
structure of an NR/T-net, together with the occurrence
rule, defines classes of possible information system
procedures, i.e., sequences of (possibly concurrent)
operations in an information system.",
acknowledgement = ack-nhfb,
affiliation = "Universitaet Karlsruhe",
affiliationaddress = "Karlsruhe, Ger",
classification = "721.2; 723.1.1; 723.3; 723.5; 903.3; 921.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Behavior specification; Complex objects; Computer
aided logic design; Computer hardware description
languages; Conceptual design; Data manipulation
languages; Data structures; Information retrieval
systems; Nested relations; Petri nets; Query languages;
Transition nets",
}
@Article{Cheung:1996:MAG,
author = "Waiman Cheung and Cheng Hsu",
title = "The Model-Assisted Global Query System for Multiple
Databases in Distributed Enterprises",
journal = j-TOIS,
volume = "14",
number = "4",
pages = "421--470",
month = oct,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/cheung.html",
abstract = "Today's enterprises typically employ multiple
information systems, which are independently developed,
locally administered, and different in logical or
physical designs. Therefore, a fundamental challenge in
enterprise information management is the sharing of
information for enterprise users across organizational
boundaries; this requires a global query system capable
of providing on-line intelligent assistance to users.
Conventional technologies, such as schema-based query
languages and hard-coded schema integration, are not
sufficient to solve this problem. This article develops
a new approach, a `model-assisted global query system,'
that utilizes an on-line repository of enterprise
metadata --- the Metadatabase --- to facilitate global
query formulation and processing with certain desirable
properties such as adaptiveness and open-systems
architecture. A definitional model characterizing the
various classes and roles of the required metadata as
knowledge for the system is presented. The significance
of possessing this knowledge (via a Metadatabase)
toward improving the global query capabilities
available previously is analyzed. On this basis, a
direct method using model traversal and a query
language using global model constructs are developed
along with other new methods required for this
approach. It is then tested through a prototype system
in a computer-integrated manufacturing (CIM)
settings.",
acknowledgement = ack-nhfb,
affiliation = "Chinese Univ of Hong Kong",
affiliationaddress = "Shatin, Hong Kong",
classification = "721.2; 722.2; 722.4; 723.1.1; 723.3; 921",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data storage equipment; Distributed database systems;
Enterprise information management; Global query system;
Hard coded schema integration; Information retrieval;
Logic design; Mathematical models; Metadatabases; Model
traversal; Multiple information systems; Online
intelligent assistance; Online systems; Query
languages; User interfaces",
wwwtitle = "The Model-Assisted Global Query System for Multiple
Databases in Distributed Enterprise",
}
@Article{Anonymous:1996:AI,
author = "Anonymous",
title = "1996 Author Index",
journal = j-TOIS,
volume = "14",
number = "4",
pages = "471--472",
month = oct,
year = "1996",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 16:21:56 MST 1999",
bibsource = "http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/cheung.html",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wiil:1997:HHS,
author = "Uffe K. Wiil and John J. Leggett",
title = "{Hyperform}: a Hypermedia System Development
Environment",
journal = j-TOIS,
volume = "15",
number = "1",
pages = "1--31",
month = jan,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/wiil.html",
abstract = "Development of hypermedia systems is a complex matter.
The current trend toward open, extensible, and
distributed multiuser hypermedia systems adds
additional complexity to the development process. As a
means of reducing this complexity, there has been an
increasing interest in hyperbase management systems
that allow hypermedia system developers to abstract
from the intricacies and complexity of the hyperbase
layer and fully attend to application and user
interface issues. Design, development, and deployment
experiences of a dynamic, open, and distributed
multiuser hypermedia system development environment
called Hyperform is presented. Hyperform is based on
the concepts of extensibility, tailorability, and rapid
prototyping of hypermedia system services. Open,
extensible hyperbase management systems permit
hypermedia system developers to tailor hypermedia
functionality for specific applications and to serve as
a platform for research. The Hyperform development
environment is comprised of multiple instances of four
component types: (1) a hyperbase management system
server, (2) a tool integrator, (3) editors, and (4)
participating tools. Hyperform has been deployed in
Unix environments, and experiments have shown that
Hyperform greatly reduces the effort required to
provide customized hyperbase management system support
for distributed multiuser hypermedia systems.",
acknowledgement = ack-nhfb,
affiliation = "Aalborg Univ",
affiliationaddress = "Den",
classification = "722.4; 723.1; 723.2; 723.3; 723.5; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Advanced hypermedia system architecture; Computational
complexity; Computer architecture; Data structures;
Database systems; Extensible hyperbase management
system; Hyperform; Information retrieval systems;
Object oriented extension language; Object oriented
programming; Rapid prototyping; System theory",
}
@Article{Fuhr:1997:PRA,
author = "Norbert Fuhr and Thomas R{\"o}lleke",
title = "A Probabilistic Relational Algebra for the Integration
of Information Retrieval and Database Systems",
journal = j-TOIS,
volume = "15",
number = "1",
pages = "32--66",
month = jan,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/fuhr.html",
abstract = "We present a probabilistic relational algebra (PRA)
which is a generalization of standard relational
algebra. In PRA, tuples are assigned probabilistic
weights giving the probability that a tuple belongs to
a relation. Based on intensional semantics, the tuple
weights of the result of a PRA expression always
conform to the underlying probabilistic model. We also
show for which expressions extensional semantics yields
the same results. Furthermore, we discuss complexity
issues and indicate possibilities for optimization.
With regard to databases, the approach allows for
representing imprecise attribute values, whereas for
information retrieval, probabilistic document indexing
and probabilistic search term weighting can be modeled.
We introduce the concept of vague predicates which
yield probabilistic weights instead of Boolean values,
thus allowing for queries with vague selection
conditions. With these features, PRA implements
uncertainty and vagueness in combination with the
relational model.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Dortmund",
affiliationaddress = "Ger",
classification = "721.1; 723.2; 723.3; 903.3; 921.5; 922.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computational complexity; Computational linguistics;
Computer simulation; Data structures; Hypertext
retrieval; Imprecise data; Indexing (of information);
Information retrieval; Logical retrieval model;
Optimization; Probabilistic relational algebra;
Probabilistic retrieval; Probability; Query languages;
Relational data model; Relational database systems;
Uncertain data; Vague predicates",
wwwauthor = "N. Fuhr and T. Rolleke",
}
@Article{Rus:1997:CIC,
author = "Daniela Rus and Devika Subramanian",
title = "Customizing Information Capture and Access",
journal = j-TOIS,
volume = "15",
number = "1",
pages = "67--101",
month = jan,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/rus.html",
abstract = "This article presents a customizable architecture for
software agents that capture and access information in
large, heterogeneous, distributed electronic
repositories. The key idea is to exploit underlying
structure at various levels of granularity to build
high-level indices with task-specific interpretations.
Information agents construct such indices and are
configured as a network of reusable modules called
structure detectors and segmenters. We illustrate our
architecture with the design and implementation of
smart information filters in two contexts: retrieving
stock market data from Internet newsgroups and
retrieving technical reports from Internet FTP sites.",
acknowledgement = ack-nhfb,
affiliation = "Dartmouth Coll",
affiliationaddress = "NH, USA",
classification = "716.1; 722.3; 722.4; 723.1; 723.2; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer architecture; Computer networks; Computer
software; Data acquisition; Information gathering;
Information retrieval systems; Information theory;
Software agents; Table recognition",
}
@Article{Entlich:1997:MDL,
author = "Richard Entlich and Lorrin Garson and Michael Lesk and
Lorraine Normore and Jan Olsen and Stuart Weibel",
title = "Making a Digital Library: The Contents of the {CORE}
Project",
journal = j-TOIS,
volume = "15",
number = "2",
pages = "103--123",
month = apr,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/entlich.html",
abstract = "The CORE (Chemical Online Retrieval Experiment)
project is a library of primary journal articles in
chemistry. Any library has an inside and an outside; in
this article we describe the inside of the library and
the methods for building the system and accumulating
the database. A later article will describe the outside
(user experiences). Among electronic-library projects,
the CORE project is unusual in that it has both ASCII
derived from typesetting and image data for all its
pages, and among experimental electronic-library
projects, it is unusually large. We describe here (a)
the processes of scanning and analyzing about 400,000
pages of primary journal material, (b) the conversion
of a similar amount of textual database material, (c)
the linking of these two data sources, and (d) the
indexing of the text material.",
acknowledgement = ack-nhfb,
affiliation = "Cornell Univ",
affiliationaddress = "NY, USA",
classification = "722.2; 723.3; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Chemical online retrieval experiment (core) project;
Database systems; Indexing (of information);
Information retrieval systems; User interfaces",
}
@Article{Manber:1997:TCS,
author = "Udi Manber",
title = "A Text Compression Scheme That Allows Fast Searching
Directly in the Compressed File",
journal = j-TOIS,
volume = "15",
number = "2",
pages = "124--136",
month = apr,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/manber.html",
abstract = "A new text compression scheme is presented in this
article. The main purpose of this scheme is to speed up
string matching by searching the compressed file
directly. The scheme requires no modification of the
string-matching algorithm, which is used as a black
box; any string-matching procedure can be used.
Instead, the pattern is modified; only the outcome of
the matching of the modified pattern against the
compressed file is decompressed. Since the compressed
file is smaller than the original file, the search is
faster both in terms of I/O time and processing time
than a search in the original file. For typical text
files, we achieve about 30\% reduction of space and
slightly less of search time. A 30\% space saving is
not competitive with good text compression schemes, and
thus should not be used where space is the predominant
concern. The intended applications of this scheme are
files that are searched often, such as catalogs,
bibliographic files, and address books. Such files are
typically not compressed, but with this scheme they can
remain compressed indefinitely, saving space while
allowing faster search at the same time. A particular
application to an information retrieval system that we
developed is also discussed.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Arizona",
affiliationaddress = "Tucson, AZ, USA",
classification = "723; 723.2; 723.5; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Data compression; Information retrieval
systems; Pattern recognition; String matching
algorithms",
}
@Article{Dunlop:1997:EAN,
author = "Mark D. Dunlop",
title = "The Effect of Accessing Nonmatching Documents on
Relevance Feedback",
journal = j-TOIS,
volume = "15",
number = "2",
pages = "137--153",
month = apr,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/dunlop.html",
abstract = "Traditional information retrieval (IR) systems only
allow users access to documents that match their
current query, and therefore, users can only give
relevance feedback on matching documents (or those with
a matching strength greater than a set threshold). This
article shows that, in systems that allow access to
nonmatching documents (e.g., hybrid hypertext and
information retrieval systems), the strength of the
effect of giving relevance feedback varies between
matching and nonmatching documents. For positive
feedback the results shown here are encouraging, as
they can be justified by an intuitive view of the
process. However, for negative feedback the results
show behavior that cannot easily be justified and that
varies greatly depending on the model of feedback
used.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Glasgow",
affiliationaddress = "Glasgow, UK",
classification = "731.1; 903.3; 921; 921.1; 922.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Feedback; Free text information retrieval; Information
retrieval systems; Mathematical models; Probability;
Vectors",
}
@Article{Gladney:1997:ACL,
author = "H. M. Gladney",
title = "Access Control for Large Collections",
journal = j-TOIS,
volume = "15",
number = "2",
pages = "154--194",
month = apr,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/gladney.html",
abstract = "Efforts to place vast information resources at the
fingertips of each individual in large user populations
must be balanced by commensurate attention to
information protection. For centralized operational
systems in controlled environments, external
administrative controls may suffice. For distributed
systems with less-structured tasks, more-diversified
information, and a heterogeneous user set, the
computing system must administer enterprise-chosen
access control policies. One kind of resource is a
digital library that emulates massive collections of
paper and other physical media for clerical,
engineering, and cultural applications. This article
considers the security requirements for such libraries
and proposes an access control method that mimics
organizational practice by combining a subject tree
with ad hoc role granting that controls privileges for
many operations independently, that treats (all but
one) privileged roles (e.g., auditor, security officer)
like every other individual authorization, and that
binds access control information to objects indirectly
for scaling, flexibility, and reflexive protection. We
sketch a realization and show that it will perform
well, generalizes many deployed proposed access control
policies, and permits individual data centers to
implement other models economically and without
disruption.",
acknowledgement = ack-nhfb,
affiliation = "IBM Almaden Research Cent",
affiliationaddress = "San Jose, CA, USA",
classification = "722.4; 723.2; 723.3; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Access control; Digital library; Distributed computer
systems; Distributed database systems; Information
retrieval systems; Security of data",
}
@Article{Dreilinger:1997:ESS,
author = "Daniel Dreilinger and Adele E. Howe",
title = "Experiences with Selecting Search Engines Using
Metasearch",
journal = j-TOIS,
volume = "15",
number = "3",
pages = "195--222",
month = jul,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/dreilinger.html",
abstract = "Search engines are among the most useful and
high-profile resources on the Internet. The problem of
finding information on the Internet has been replaced
with the problem of knowing where search engines are,
what they are designed to retrieve, and how to use
them. This article describes and evaluates SavvySearch,
a metasearch engine designed to intelligently select
and interface with multiple remote search engines. The
primary metasearch issue examined is the importance of
carefully selecting and ranking remote search engines
for user queries. We studied the efficacy of
SavvySearch's incrementally acquired metaindex approach
to selecting search engines by analyzing the effect of
time and experience on performance. We also compared
the metaindex approach to the simpler categorical
approach and showed how much experience is required to
surpass the simple scheme.",
acknowledgement = ack-nhfb,
affiliation = "MIT Media Lab",
affiliationaddress = "Cambridge, MA, USA",
classification = "722.2; 722.3; 723.3; 723.4; 723.4.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Inference engines; Information retrieval systems;
Interfaces (computer); Internet; Learning algorithms;
Learning systems; Query languages; Search engines;
Software package SavvySearch; Wide area networks",
}
@Article{Tomasic:1997:DSE,
author = "Anthony Tomasic and Luis Gravano and Calvin Lue and
Peter Schwarz and Laura Haas",
title = "Data Structures for Efficient Broker Implementation",
journal = j-TOIS,
volume = "15",
number = "3",
pages = "223--253",
month = jul,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/tomasic.html",
abstract = "With the profusion of text databases on the Internet,
it is becoming increasingly hard to find the most
useful databases for a given query. To attack this
problem, several existing and proposed systems employ
brokers to direct user queries, using a local database
of summary information about the available databases.
This summary information must effectively distinguish
relevant databases and must be compact while allowing
efficient access. We offer evidence that one broker,
GlOSS, can be effective at locating databases of
interest even in a system of hundreds of databases and
can examine the performance of accessing the GlOSS
summaries for two promising storage methods: the grid
file and partitioned hashing. We show that both methods
can be tuned to provide good performance for a
particular workload (within a broad range of
workloads), and we discuss the tradeoffs between the
two data structures. As a side effect of our work, we
show that grid files are more broadly applicable than
previously thought; in particular, we show that by
varying the policies used to construct the grid file we
can provide good performance for a wide range of
workloads even when storing highly skewed data.",
acknowledgement = ack-nhfb,
affiliation = "INRIA Rocquencourt",
affiliationaddress = "Le Chesnay, Fr",
classification = "722.1; 722.2; 723.2; 723.3; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Data storage equipment; Data structures; Distributed
database systems; Grid files; Information retrieval;
Internet; Partitioned hashing; Query languages; Text
databases; User interfaces",
}
@Article{Bookstein:1997:MWO,
author = "A. Bookstein and S. T. Klein and T. Raita",
title = "Modeling Word Occurrences for the Compression of
Concordances",
journal = j-TOIS,
volume = "15",
number = "3",
pages = "254--290",
month = jul,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/bookstein.html",
abstract = "An earlier paper developed a procedure for compressing
concordances, assuming that all elements occurred
independently. The models introduced in that paper are
extended here to take the possibility of clustering
into account. The concordance is conceptualized as a
set of bitmaps, in which the bit locations represent
documents, and the one-bits represent the occurrence of
given terms. Hidden Markov Models (HMMs) are used to
describe the clustering of the one-bits. However, for
computational reasons, the HMM is approximated by
traditional Markov models. A set of criteria is
developed to constrain the allowable set of n-state
models, and a full inventory is given for n less than
or equal 4. Graph-theoretic reduction and
complementation operations are defined among the
various models and are used to provide a structure
relating the models studied. Finally, the new methods
were tested on the concordances of the English Bible
and of two of the world's largest full-text retrieval
system: the Tr{\'e}sor de la Langue Fran{\c{c}}aise and
the Responsa Project.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Chicago",
affiliationaddress = "Chicago, IL, USA",
classification = "723.2; 903.3; 921; 921.4; 921.6; 922.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Approximation theory; Classification (of information);
Computational methods; Data compression; Data storage
equipment; Data structures; Full text retrieval
systems; Graph theory; Hidden Markov models (HMM);
Information retrieval systems; Markov processes;
Mathematical models",
wwwpages = "254--291",
}
@Article{Cohen:1997:RHF,
author = "Jonathan D. Cohen",
title = "Recursive Hashing Functions for $n$-Grams",
journal = j-TOIS,
volume = "15",
number = "3",
pages = "291--320",
month = jul,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
http://www.acm.org/pubs/tois/toc.html;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/tois/abstracts/cohen.html",
abstract = "Many indexing, retrieval, and comparison methods are
based on counting or cataloguing n-grams in streams of
symbols. The fastest method of implementing such
operations is through the use of hash tables. Rapid
hashing of consecutive n-grams is best done using a
recursive hash function, in which the hash value of the
current n-gram is derived from the hash value of its
predecessor. This article generalizes recursive hash
functions found in the literature and proposes new
methods offering superior performance. Experimental
results demonstrate substantial speed improvement over
conventional approaches, while retaining near-ideal
hash value distribution.",
acknowledgement = ack-nhfb,
affiliation = "Natl Security Agency",
affiliationaddress = "Fort Meade, MD, USA",
classification = "721.1; 723.2; 903.1; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computational complexity; Data structures; Indexing
(of information); Information retrieval; Recursive
functions; Recursive hashing functions",
}
@Article{Kimbrough:1997:AMP,
author = "Steven O. Kimbrough and Scott A. Moore",
title = "On Automated Message Processing in Electronic Commerce
and Work Support Systems: Speech Act Theory and
Expressive Felicity",
journal = j-TOIS,
volume = "15",
number = "4",
pages = "321--367",
month = oct,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Electronic messaging, whether in an office environment
or for electronic commerce, is normally carried out in
natural language, even when supported by information
systems. For a variety of reasons, it would be useful
if electronic messaging systems could have semantic
access to, that is, access to the meanings and contents
of, the messages they process. Given that natural
language understanding is not a practicable
alternative, there remain three approaches to
delivering systems with semantic access: electronic
data interchange (EDI), tagged messages, and the
development of a formal language for business
communication (FLBC). We favor the latter approach. In
this article we compare and contrast these three
approaches, present a theoretical basis for an FLBC
(using speech act theory), and describe a prototype
implementation.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Pennsylvania",
affiliationaddress = "Philadelphia, PA, USA",
classification = "721.1; 722.3; 723.1; 723.4; 751.5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Data communication systems;
Electronic commerce; Formal language for business
communication; Formal languages; Knowledge
representation; Software prototyping; Speech act
theory; Speech processing",
}
@Article{Mostafa:1997:MAI,
author = "J. Mostafa and S. Mukhopadhyay and W. Lam and M.
Palakal",
title = "A Multilevel Approach to Intelligent Information
Filtering: Model, System, and Evaluation",
journal = j-TOIS,
volume = "15",
number = "4",
pages = "368--399",
month = oct,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In information-filtering environments, uncertainties
associated with changing interests of the user and the
dynamic document stream must be handled efficiently. In
this article, a filtering model is proposed that
decomposes the overall task into subsystem
functionalities and highlights the need for multiple
adaptation techniques to cope with uncertainties. A
filtering system, SIFTER, has been implemented based on
the model, using established techniques in information
retrieval and artificial intelligence. These techniques
include document representation by a vector-space
model, document classification by unsupervised
learning, and user modeling by reinforcement learning.
The system can filter information based on content and
a user's specific interests. The user's interests are
automatically learned with only limited user
intervention in the form of optional relevance feedback
for documents. We also describe experimental studies
conducted with SIFTER to filter computer and
information science documents collected from the
Internet and commercial database services. The
experimental results demonstrate that the system
performs very well in filtering documents in a
realistic problem setting.",
acknowledgement = ack-nhfb,
affiliation = "Indiana Univ",
affiliationaddress = "Bloomington, IN, USA",
classification = "723.2; 723.3; 723.4; 723.5; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial intelligence; Computer simulation; Data
processing; Database systems; Information retrieval
systems; Intelligent information filtering; Learning
systems; Reinforcement learning; Unsupervised
learning",
}
@Article{Navarro:1997:PNM,
author = "Gonzalo Navarro and Ricardo {Baeza- Yates}",
title = "Proximal Nodes: a Model to Query Document Databases by
Content and Structure",
journal = j-TOIS,
volume = "15",
number = "4",
pages = "400--435",
month = oct,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "A model to query document databases by both their
content and structure is presented. The goal is to
obtain a query language that is expressive in practice
while being efficiently implementable, features not
present at the same time in previous work. The key
ideas of the model are a set-oriented query language
based on operations on nearby structure elements of one
or more hierarchies, together with content and
structural indexing and bottom-up evaluation. The model
is evaluated in regard to expressiveness and
efficiency, showing that it provides a good trade-off
between both goals. Finally, it is shown how to include
in the model other media different from text.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Chile",
affiliationaddress = "Santiago, Chile",
classification = "461.4; 723.1; 723.1.1; 723.2; 723.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Computer programming languages; Data
processing; Data structures; Hierarchical documents;
Human engineering; Man machine systems; Performance;
Query languages; Structured text; Text algebras",
}
@Article{Anonymous:1997:AI,
author = "Anonymous",
title = "1997 Author Index",
journal = j-TOIS,
volume = "15",
number = "4",
pages = "436--437",
month = oct,
year = "1997",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:02:45 MST 1999",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Stotts:1998:HAV,
author = "P. David Stotts and Richard Furuta and Cyrano {Ruiz
Cabarrus}",
title = "Hyperdocuments as Automata: Verification of
Trace-Based Browsing Properties by Model Checking",
journal = j-TOIS,
volume = "16",
number = "1",
pages = "1--30",
month = jan,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We present a view of hyperdocuments in which each
document encodes its own browsing semantics in its
links. This requires a mental shift in how a
hyperdocument is thought of abstractly. Instead of
treating the links of a document as defining a static
directed graph, they are thought of as defining an
abstract program, termed the links automaton of the
document. A branching temporal logic notation, termed
HTL<sup>*</sup>, is introduced for specifying
properties a document should exhibit during browsing.
An automated program verification technique called
model checking is used to verify that browsing
specifications in a subset of HTL<sup>*</sup> are met
by the behavior defined in the links automaton. We
illustrate the generality of these techniques by
applying them first to several Trellis documents and
then to a Hyperties document.",
acknowledgement = ack-nhfb,
affiliation = "Univ of North Carolina",
affiliationaddress = "Chapel Hill, NC, USA",
classification = "721.1; 723.2; 921.4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Automata theory; Browsing semantics; Computation
theory; Encoding (symbols); Graph theory;
Hyperdocuments; Hypermedia; Model checking",
}
@Article{Vujovic:1998:EAF,
author = "N. Vujovic and D. Brzakovic",
title = "Evaluation of an Algorithm for Finding a Match of a
Distorted Texture Pattern in a Large Image Database",
journal = j-TOIS,
volume = "16",
number = "1",
pages = "31--60",
month = jan,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Evaluation of an algorithm for finding a match for a
random texture pattern in a large image database is
presented. The algorithm was designed assuming that the
random pattern may be subject to misregistration
relative to its representation in the database and
assuming that it may have missing parts. The potential
applications involve authentication of legal documents,
bank notes, or credit cards, where thin fibers are
embedded randomly into the document medium during
medium fabrication. The algorithm achieves image
matching by a three-step hierarchical procedure, which
starts by matching parts of fiber patterns while
solving the misregistration problem and ends up by
matching complete fiber patterns. Performance of the
algorithm is studied both theoretically and
experimentally. Theoretical analysis includes the
study. of the probability that two documents have the
same pattern, and the probability of the algorithm
establishing a wrong match, as well as the algorithm's
performance in terms of processing time. Experiments
involving over 250,000 trials using databases of
synthetic documents, containing up to 100,000
documents, were used to confirm theoretical
predictions. In addition, experiments involving a
database containing real images were conducted in order
to confirm that the algorithm has potential in real
applications.",
acknowledgement = ack-nhfb,
affiliation = "Lehigh Univ",
affiliationaddress = "Bethlehem, PA, USA",
classification = "723.3; 731.1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Database systems; Identification (control
systems); Image database; Image matching; Image
processing",
}
@Article{Xu:1998:CBS,
author = "Jinxi Xu and W. Bruce Croft",
title = "Corpus-Based Stemming Using Cooccurrence of Word
Variants",
journal = j-TOIS,
volume = "16",
number = "1",
pages = "61--81",
month = jan,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Stemming is used in many information retrieval (IR)
systems to reduce variant word forms to common roots.
It is one of the simplest applications of natural
language processing to IR and is one of the most
effective in terms of user acceptance and consistency,
though small retrieval improvements. Current stemming
techniques do not, however, reflect the language use in
specific corpora, and this can lead to occasional
serious retrieval failures. We propose a technique for
using corpus-based word variant cooccurrence statistics
to modify or create a stemmer. The experimental results
generated using English newspaper and legal text and
Spanish text demonstrate the viability of this
technique and its advantages relative to conventional
approaches that only employ morphological rules.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Massachusetts",
affiliationaddress = "Amherst, MA, USA",
classification = "723.3; 903.3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Cooccurrence; Corpus analysis; Database
systems; Failure analysis; Information retrieval;
Stemming",
}
@Article{Romm:1998:EMC,
author = "Celia T. Romm and Nava Pliskin",
title = "Electronic Mail as a Coalition-Building Information
Technology",
journal = j-TOIS,
volume = "16",
number = "1",
pages = "82--100",
month = jan,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "One of the most intriguing lines of research within
the literature on diffusion of information technologies
(IT) is the study of the power and politics of this
process. The major objective of this article is to
build on the work of Kling and Markus on power and IT,
by extending their perspective to email. To demonstrate
how email can be used for political purposes within an
organizational context, a case study is presented. The
case study describes a series of events which took
place in a university. In the case, email was used by a
group of employees to stage a rebellion against the
university president. The discussion demonstrates that
email features make it amenable to a range of political
uses. The article is concluded with a discussion of the
implications from this case to email research and
practice.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Wollongong",
affiliationaddress = "Wollongong, Aust",
classification = "903; 903.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Coalition building information technology; Electronic
mail; Information dissemination; Information science;
Information technology",
}
@Article{Wilbur:1998:KMH,
author = "W. John Wilbur",
title = "The Knowledge in Multiple Human Relevance Judgments",
journal = j-TOIS,
volume = "16",
number = "2",
pages = "101--126",
month = apr,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We show first that the pooling of multiple human
judgments of relevance provides a predictor of
relevance that is superior to that obtained from a
single human's relevance judgments. A learning
algorithm applied to a set of relevance judgments
obtained from a single human would be expected to
perform on new material at a level somewhat below that
human. However, we examine two learning methods which
when trained on the superior source of pooled human
relevance judgments are able to perform at the level of
a single human on new material. All performance
comparisons are based on an independent human judge.
Both algorithms function by producing term weights ---
one by a log odds calculation and the other by
producing a least-squares fit to human relevance
ratings. Some characteristics of the algorithms are
examined.",
acknowledgement = ack-nhfb,
affiliation = "Natl Cent for Biotechnology Information (NCBI)",
affiliationaddress = "Bethesda, MD, USA",
classification = "903; 903.3; 921.6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Information retrieval; Information
technology; Inverse document frequency weights; Least
squares approximations",
}
@Article{Hicks:1998:HVC,
author = "David L. Hicks and John J. Leggett and Peter J.
Nurnberg and John L. Schnase",
title = "A Hypermedia Version Control Framework",
journal = j-TOIS,
volume = "16",
number = "2",
pages = "127--160",
month = apr,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The areas of application of hypermedia technology,
combined with the capabilities that hypermedia provides
for manipulating structure, create an environment in
which version control is very important. A hypermedia
version control framework has been designed to
specifically address the version control problem in
open hypermedia environments. One of the primary
distinctions of the framework is the partitioning of
hypermedia version control functionality into intrinsic
and application-specific categories. The version
control framework has been used as a model for the
design of version control services for a hyperbase
management system that provides complete version
support for both data and structural entities. In
addition to serving as a version control model for open
hypermedia environments, the framework offers a
clarifying and unifying context in which to examine the
issues of version control in hypermedia.",
acknowledgement = ack-nhfb,
affiliation = "Knowledge Systems",
affiliationaddress = "Export, PA, USA",
classification = "723.2; 723.3; 912.2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Computer operating systems; Database systems;
Hipermedia; Hyperbase management systems; Management;
Management information systems",
}
@Article{Belussi:1998:SSJ,
author = "Alberto Belussi and Christos Faloutsos",
title = "Self-Spatial Join Selectivity Estimation Using Fractal
Concepts",
journal = j-TOIS,
volume = "16",
number = "2",
pages = "161--201",
month = apr,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The problem of selectivity estimation for queries of
nontraditional databases is still an open issue. In
this article, we examine the problem of selectivity
estimation for some types of spatial queries in
databases containing real data. We have shown earlier
[Faloutsos and Kamel 1994] that real point sets
typically have a non-uniform distribution, violating
consistently the uniformity and independence
assumptions. Moreover, we demonstrated that the theory
of fractals can help to describe real point sets. In
this article we show how the concept of fractal
dimension, i.e., (non-integer) dimension, can lead to
the solution for the selectivity estimation problem in
spatial databases. Among the infinite family of fractal
dimensions, we consider here the Hausdorff fractal
dimension D<sub>0</sub> and the `Correlation' fractal
dimension D<sub>2</sub>. Specifically, we show that (a)
the average number of neighbors for a given point set
follows a power law, with D<sub>2</sub> as exponent,
and (b) the average number of nonempty range queries
follows a power law with E --- D<sub>0</sub> as
exponent (E is the dimension of the embedding space).
We present the formulas to estimate the selectivity for
`biased' range queries, for self-spatial joins, and for
the average number of nonempty range queries. The
result of some experiments on real and synthetic point
sets are shown. Our formulas achieve very low relative
errors, typically about 10\%, versus 40\%-100\% of the
formulas that are based on the uniformity and
independence assumptions.",
acknowledgement = ack-nhfb,
affiliation = "Politecnico di Milano",
affiliationaddress = "Milan, Italy",
classification = "722; 723.3; 921",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
journalabr = "ACM Trans Inf Syst",
keywords = "Algorithms; Computer selection and evaluation;
Database systems; Fractal dimension; Fractals;
Selectivity estimation",
}
@Article{Ackerman:1998:AOM,
author = "Mark S. Ackerman",
title = "Augmenting Organizational Memory: a Field Study of
{Answer Garden}",
journal = j-TOIS,
volume = "16",
number = "3",
pages = "203--224",
month = jul,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-3/p203-ackerman/",
abstract = "A growing concern for organizations and groups has
been to augment their knowledge and expertise. One such
augmentation is to provide an organizational memory,
some record of the organization's knowledge. However,
relatively little is known about how computer systems
might enhance organizational, group, or community
memory. This article presents Answer Garden, a system
for growing organizational memory. The article
describes the system and its underlying implementation.
It then presents findings from a field study of Answer
Garden. The article discusses the usage data and
qualitative evaluations from the field study, and then
draws a set of lessons for next-generation
organizational memory systems.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "performance; reliability",
subject = "{\bf H.5.3} Information Systems, INFORMATION
INTERFACES AND PRESENTATION, Group and Organization
Interfaces. {\bf C.2.4} Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed applications. {\bf H.1.2} Information
Systems, MODELS AND PRINCIPLES, User/Machine Systems.
{\bf H.3.3} Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval. {\bf
H.4.3} Information Systems, INFORMATION SYSTEMS
APPLICATIONS, Communications Applications. {\bf H.5.2}
Information Systems, INFORMATION INTERFACES AND
PRESENTATION, User Interfaces. {\bf I.7.2} Computing
Methodologies, DOCUMENT AND TEXT PROCESSING, Document
Preparation, Hypertext/hypermedia. {\bf K.4.3}
Computing Milieux, COMPUTERS AND SOCIETY,
Organizational Impacts.",
}
@Article{Crestani:1998:SPK,
author = "F. Crestani and C. J. {Van Rijsbergen}",
title = "A Study of Probability Kinematics in Information
Retrieval",
journal = j-TOIS,
volume = "16",
number = "3",
pages = "225--255",
month = jul,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-3/p225-crestani/",
abstract = "We analyze the kinematics of probabilistic term
weights at retrieval time for different Information
Retrieval models. We present four models based on
different notions of probabilistic retrieval. Two of
these models are based on classical probability theory
and can be considered as prototypes of models long in
use in Information Retrieval, like the Vector Space
Model and the Probabilistic Model. The two other models
are based on a logical technique of evaluating the
probability of a conditional called imaging; one is a
generalization of the other. We analyze the transfer of
probabilities occurring in the term space at retrieval
time for these four models, compare their retrieval
performance using classical test collections, and
discuss the results. We believe that our results
provide useful suggestions on how to improve existing
probabilistic models of Information Retrieval by taking
into consideration term-term similarity.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "experimentation; performance; theory",
subject = "{\bf H.3.3} Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Retrieval models. {\bf F.1.2} Theory of Computation,
COMPUTATION BY ABSTRACT DEVICES, Modes of Computation,
Probabilistic computation.",
}
@Article{Moffat:1998:ACR,
author = "Alistair Moffat and Radford M. Neal and Ian H.
Witten",
title = "Arithmetic Coding Revisited",
journal = j-TOIS,
volume = "16",
number = "3",
pages = "256--294",
month = jul,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-3/p256-moffat/",
abstract = "Over the last decade, arithmetic coding has emerged as
an important compression tool. It is now the method of
choice for adaptive coding on multisymbol alphabets
because of its speed, low storage requirements, and
effectiveness of compression. This article describes a
new implementation of arithmetic coding that
incorporates several improvements over a widely used
earlier version by Witten, Neal, and Cleary, which has
become a {\em de facto\/} standard. These improvements
include fewer multiplicative operations, greatly
extended range of alphabet sizes and symbol
probabilities, and the use of low-precision arithmetic,
permitting implementation by fast shift/add operations.
We also describe a modular structure that separates the
coding, modeling, and probability estimation components
of a compression system. To motivate the improved
coder, we consider the needs of a word-based text
compression program. We report a range of experimental
results using this and other models. Complete source
code is available.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "algorithms; performance",
subject = "{\bf E.4} Data, CODING AND INFORMATION THEORY, Data
compaction and compression. {\bf E.1} Data, DATA
STRUCTURES.",
}
@Article{Egenhofer:1998:MDN,
author = "Max J. Egenhofer and A. Rashid B. M. Shariff",
title = "Metric details for natural-language spatial
relations",
journal = j-TOIS,
volume = "16",
number = "4",
pages = "295--321",
month = oct,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-4/p295-egenhofer/",
abstract = "Spatial relations often are desired answers that a
geographic information system (GIS) should generate in
response to a user's query. Current GIS's provide only
rudimentary support for processing and interpreting
natural-language-like spatial relations, because their
models and representations are primarily quantitative,
while natural-language spatial relations are usually
dominated by qualitative properties. Studies of the use
of spatial relations in natural language showed that
topology accounts for a significant portion of the
geometric properties. This article develops a formal
model that captures {\em metric details\/} for the
description of natural-language spatial relations. The
metric details are expressed as refinements of the
categories identified by the 9-intersection, a model
for topological spatial relations, and provide a more
precise measure than does topology alone as to whether
a geometric configuration matches with a spatial term
or not. Similarly, these measures help in identifying
the spatial term that describes a particular
configuration. Two groups of metric details are
derived: {\em splitting ratios\/} as the normalized
values of lengths and areas of intersections; and {\em
closeness measures\/} as the normalized distances
between disjoint object parts. The resulting model of
topological and metric properties was calibrated for 64
spatial terms in English, providing values for the best
fit as well as value ranges for the significant
parameters of each term. Three examples demonstrate how
the framework and its calibrated values are used to
determine the best spatial term for a relationship
between two geometric objects.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "design; human factors",
subject = "{\bf H.2.8} Information Systems, DATABASE MANAGEMENT,
Database Applications, Spatial databases and GIS. {\bf
H.2.3} Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.3.3} Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Search and Retrieval, Query formulation. {\bf H.3.3}
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval, Search process. {\bf
H.3.3} Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Selection
process. {\bf I.2.1} Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Applications and Expert
Systems, Cartography. {\bf I.2.7} Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Natural
Language Processing, Language parsing and
understanding. {\bf I.5.1} Computing Methodologies,
PATTERN RECOGNITION, Models, Geometric.",
}
@Article{Kolda:1998:SMD,
author = "Tamara G. Kolda and Dianne P. O'Leary",
title = "A semidiscrete matrix decomposition for latent
semantic indexing information retrieval",
journal = j-TOIS,
volume = "16",
number = "4",
pages = "322--346",
month = oct,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-4/p322-kolda/",
abstract = "The vast amount of textual information available today
is useless unless it can be effectively and efficiently
searched. The goal in information retrieval is to find
documents that are relevant to a given user query. We
can represent and document collection by a matrix whose
$(i, j)$ entry is nonzero only if the $i$th term
appears in the {\em j\/}th document; thus each document
corresponds to a column vector. The query is also
represented as a column vector whose $i$th term is
nonzero only if the $i$th term appears in the query. We
score each document for relevancy by taking its inner
product with the query. The highest-scoring documents
are considered the most relevant. Unfortunately, this
method does not necessarily retrieve all relevant
documents because it is based on literal term matching.
Latent semantic indexing (LSI) replaces the document
matrix with an approximation generated by the truncated
singular-value decomposition (SVD). This method has
been shown to overcome many difficulties associated
with literal term matching. In this article we propose
replacing the SVD with the semidiscrete decomposition
(SDD). We will describe the SDD approximation, show how
to compute it, and compare the SDD-based LSI method to
the SVD-based LSI methods. We will show that SDD-based
LSI does as well as SVD-based LSI in terms of document
retrieval while requiring only one-twentieth the
storage and one-half the time to compute each query. We
will also show how to update the SDD approximation when
documents are added or deleted from the document
collection.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "algorithms; design; performance; theory",
subject = "{\bf H.3.3} Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval. {\bf
G.1.2} Mathematics of Computing, NUMERICAL ANALYSIS,
Approximation. {\bf H.2.2} Information Systems,
DATABASE MANAGEMENT, Physical Design.",
}
@Article{Ram:1998:CCS,
author = "Sudha Ram and V. Ramesh",
title = "Collaborative conceptual schema design: a process
model and prototype system",
journal = j-TOIS,
volume = "16",
number = "4",
pages = "347--371",
month = oct,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-4/p347-ram/",
abstract = "Recent years have seen an increased interest in
providing support for collaborative activities among
groups of users participating in various information
systems design tasks such as, requirements
determination and process modeling. However, little
attention has been paid to the collaborative conceptual
database design process. In this article, we develop a
model of the collaborative conceptual schema
development process and describe the design and
implementation of a graphical multiuser conceptual
schema design tool that is based on the model. The
system we describe allows a group of users to work
collaboratively on the creation of database schemas in
synchronous (same-time) mode (either in a face-to-face
or distributed setting). Extensive modeling support is
provided to assist users in creating semantically
correct conceptual schemas. The system also provides
users with several graphical facilities such as, a
large drawing workspace with the ability to scroll or
``jump'' to any portion of this workspace, zooming
capabilities, and the ability to move object(s) to any
portion of the workspace. The unique component of the
system, however, is its built-in support for
collaborative schema design. The system supports a
relaxed WYSIWIS environment, i.e., each user can
control the graphical layout of the same set of schema
objects. The system ensures that changes/additions made
by any user are consistent. Any conflicts that may
compromise to the integrity of the shared schema are
flagged and resolved by the system. The results from a
preliminary experiment suggest that the use of our
system in a collaborative mode improved information
sharing among users, minimized conflicts, and led to a
more comprehensive schema definition.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "design; management",
subject = "{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf K.6.3}
Computing Milieux, MANAGEMENT OF COMPUTING AND
INFORMATION SYSTEMS, Software Management. {\bf H.5.3}
Information Systems, INFORMATION INTERFACES AND
PRESENTATION, Group and Organization Interfaces,
Collaborative computing.",
}
@Article{Wang:1998:SHD,
author = "Weigang Wang and Roy Rada",
title = "Structured hypertext with domain semantics",
journal = j-TOIS,
volume = "16",
number = "4",
pages = "372--412",
month = oct,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-4/p372-wang/",
abstract = "One important facet of current hypertext research
involves using knowledge-based techniques to develop
and maintain document structures. A semantic net is one
such technique. However, most semantic-net-based
hypertext systems leave the linking consistency of the
net to individual users. Users without guidance may
accidentally introduce structural and relational
inconsistencies in the semantic nets. The relational
inconsistency hinders the creation of domain
information models. The structural inconsistency leads
to unstable documents, especially when a document is
composed by computation with traversal algorithms. This
work tackles to above problems by integrating logical
structure and domain semantics into a semantic net. A
semantic-net-based structured-hypertext model has been
formalized. The model preserves structural and
relational consistency after changes to the semantic
net. The hypertext system (RICH) based on this model
has been implemented and tested. The RICH system can
define and enforce a set of rules to maintain to
integrity of the semantic net and provide particular
support for creating multihierarchies with the reuse of
existing contents and structures. Users have found such
flexible but enforceable semantics to be helpful.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "design; documentation; management",
subject = "{\bf I.7.2} Computing Methodologies, DOCUMENT AND TEXT
PROCESSING, Document Preparation, Hypertext/hypermedia.
{\bf E.1} Data, DATA STRUCTURES, Graphs and networks.
{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.3.4} Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Systems and
Software. {\bf H.5.0} Information Systems, INFORMATION
INTERFACES AND PRESENTATION, General.",
}
@Article{Croft:1998:AI,
author = "W. Bruce Croft",
title = "Author Index",
journal = j-TOIS,
volume = "16",
number = "4",
pages = "413--414",
month = oct,
year = "1998",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Jul 26 16:33:55 MDT 1999",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org:80/pubs/citations/journals/tois/1998-16-4/p413-croft/",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
subject = "{\bf A.0} General Literature, GENERAL.",
}
@Article{Chang:1999:PRT,
author = "Chen-Chuan K. Chang and H{\'e}ctor Garcia-Molina and
Andreas Paepcke",
title = "Predicate rewriting for translating {Boolean} queries
in a heterogeneous information system",
journal = j-TOIS,
volume = "17",
number = "1",
pages = "1--39",
month = jan,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-1/p1-chang/",
abstract = "Searching over heterogeneous information sources is
difficult in part because of the nonuniform query
languages. Our approach is to allow users to compose
Boolean queries in one rich front-end language. For
each user query and target source, we transform the
user query into a subsuming query that can be supported
by the source but that may return extra documents. The
results are then processed by a filter query to yield
the correct final results. In this article we introduce
the architecture and associated mechanism for query
translation. In particular, we discuss techniques for
rewriting predicates in Boolean queries into native
subsuming forms, which is a basis of translating
complex queries. In addition, we present experimental
results for evaluating the cost of postfiltering. We
also discuss the drawbacks of this approach and cases
when it may not be effective. We have implemented
prototype versions of these mechanisms and demonstrated
them on heterogeneous Boolean systems.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Experimentation; Languages; Measurement",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Boolean queries; content-based retrieval; filtering;
predicate rewriting; query subsumption; query
translation",
subject = "Information Systems --- Database Management ---
Languages (H.2.3): {\bf Query languages}; Information
Systems --- Database Management --- Heterogeneous
Databases (H.2.5); Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Query formulation}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}; Information Systems --- Information Storage
and Retrieval --- Digital Libraries (H.3.7): {\bf
Systems issues}",
}
@Article{Hawking:1999:MIS,
author = "David Hawking and Paul Thistlewaite",
title = "Methods for information server selection",
journal = j-TOIS,
volume = "17",
number = "1",
pages = "40--76",
month = jan,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-1/p40-hawking/",
abstract = "The problem of using a broker to select a subset of
available information servers in order to achieve a
good trade-off between document retrieval effectiveness
and cost is addressed. Server selection methods which
are capable of operating in the absence of global
information, and where servers have no knowledge of
brokers, are investigated. A novel method using
Lightweight Probe queries (LWP method) is compared with
several methods based on data from past query
processing, while Random and Optimal server rankings
serve as controls. Methods are evaluated, using TREC
data and relevance judgments, by computing ratios, both
empirical and ideal, of recall and early precision for
the subset versus the complete set of available
servers. Estimates are also made of the best-possible
performance of each of the methods. LWP and Topic
Similarity methods achieved best results, each being
capable of retrieving about 60\% of the relevant
documents for only one-third of the cost of querying
all servers. Subject to the applicable cost model, the
LWP method is likely to be preferred because it is
suited to dynamic environments. The good results
obtained with a simple automatic LWP implementation
were replicated using different data and a larger set
of query topics.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design; Experimentation; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "information servers; Lightweight Probe queries;
network servers; server ranking; server selection; text
retrieval",
subject = "Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4): {\bf Distributed databases}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}; Information Systems --- Information Storage
and Retrieval --- Information Search and Retrieval
(H.3.3): {\bf Selection process}; Information Systems
--- Information Storage and Retrieval --- Systems and
Software (H.3.4): {\bf Information networks};
Information Systems --- Information Storage and
Retrieval --- Library Automation (H.3.6): {\bf Large
text archives}",
}
@Article{Tan:1999:EIG,
author = "Bernard C. Y. Tan and Kwok-kee Wei and Richard T.
Watson",
title = "The equalizing impact of a group support system on
status differentials",
journal = j-TOIS,
volume = "17",
number = "1",
pages = "77--100",
month = jan,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-1/p77-tan/",
abstract = "This study investigates the impact of the electronic
communication capability of a group support system
(GSS) on status differentials in small groups. A
laboratory experiment was used to answer the research
questions. Three support levels were studied: manual,
face-to-face GSS, and dispersed GSS. Two task types
were examined: intellective and preference. Five
dependent variables reflecting different aspects of
status differentials were measured: status influence,
sustained influence, residual disagreement, perceived
influence, and decision confidence. The results show
that manual groups had higher status influence,
sustained influence, and decision confidence, but lower
residual disagreement than face-to-face GSS and
dispersed GSS groups. Preference task groups also
produced higher status influence and sustained
influence, but lower residual disagreement compared to
intellective task groups. In addition, manual groups
working on the preference task reported higher
perceived influence than face-to-face GSS and dispersed
GSS groups working on the same task. These findings
suggest that when groups are engaged in activities for
which status differentials are undesirable, a GSS can
be used in both face-to-face and dispersed settings to
dampen status differentials. Moreover, when a task
amplifies status differentials, the use of a GSS tends
to produce corresponding stronger dampening effects.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Management; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "electronic communication; group support systems;
status differentials; task type",
subject = "Information Systems --- Information Systems
Applications --- Communications Applications (H.4.3);
Information Systems --- Information Interfaces and
Presentation --- Group and Organization Interfaces
(H.5.3); Computer Applications --- Social and
Behavioral Sciences (J.4)",
}
@Article{Bertino:1999:FAM,
author = "Elisa Bertino and Sushil Jajodia and Pierangela
Samarati",
title = "A flexible authorization mechanism for relational data
management systems",
journal = j-TOIS,
volume = "17",
number = "2",
pages = "101--140",
month = apr,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-2/p101-bertino/",
abstract = "In this article, we present an authorization model
that can be used to express a number of discretionary
access control policies for relational data management
systems. The model permits both positive and negative
authorizations and supports exceptions at the same
time. The model is flexible in that the users can
specify, for each authorization they grant, whether the
authorization can allow for exceptions or whether it
must be strongly obeyed. It provides authorization
management for groups with exceptions at any level of
the group hierarchy, and temporary suspension of
authorizations. The model supports ownership together
with decentralized administration of authorizations.
Administrative privileges can also be restricted so
that owners retain control over their tables.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Security; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "access control mechanism; access control policy;
authorization; data management system; group management
support; relational database",
subject = "Software --- Operating Systems --- Security and
Protection (D.4.6): {\bf Access controls}; Information
Systems --- Database Management --- Database
Administration (H.2.7): {\bf Security, integrity, and
protection}; Information Systems --- Database
Management --- General (H.2.0): {\bf Security,
integrity, and protection**}",
}
@Article{Cohen:1999:CSL,
author = "William W. Cohen and Yoram Singer",
title = "Context-sensitive learning methods for text
categorization",
journal = j-TOIS,
volume = "17",
number = "2",
pages = "141--173",
month = apr,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-2/p141-cohen/",
abstract = "Two recently implemented machine-learning algorithms,
{\em RIPPER\/} and {\em sleeping-experts for phrases},
are evaluated on a number of large text categorization
problems. These algorithms both construct classifiers
that allow the ``context'' of a word {\em w\/} to
affect how (or even whether) the presence or absence of
{\em w\/} will contribute to a classification. However,
RIPPER and sleeping-experts differ radically in many
other respects: differences include different notions
as to what constitutes a context, different ways of
combining contexts to construct a classifier, different
methods to search for a combination of contexts, and
different criteria as to what contexts should be
included in such a combination. In spite of these
differences, both RIPPER and sleeping-experts perform
extremely well across a wide variety of categorization
problems, generally outperforming previously applied
learning methods. We view this result as a confirmation
of the usefulness of classifiers that represent
contextual information.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Experimentation",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "context-sensitive models; mistake-driven algorithms;
on-line learning; rule learning; text categorization",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3);
Computing Methodologies --- Artificial Intelligence ---
Learning (I.2.6): {\bf Concept learning}; Computing
Methodologies --- Artificial Intelligence --- Learning
(I.2.6): {\bf Parameter learning}; Computing
Methodologies --- Pattern Recognition --- Applications
(I.5.4): {\bf Text processing}; Computing Methodologies
--- Artificial Intelligence --- Natural Language
Processing (I.2.7): {\bf Text analysis}",
}
@Article{El-Kwae:1999:RFC,
author = "Essam A. El-Kwae and Mansur R. Kabuka",
title = "A robust framework for content-based retrieval by
spatial similarity in image databases",
journal = j-TOIS,
volume = "17",
number = "2",
pages = "174--198",
month = apr,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-2/p174-el-kwae/",
abstract = "A framework for retrieving images by spatial
similarity (FRISS) in image databases is presented. In
this framework, a robust retrieval by spatial
similarity (RSS) algorithm is defined as one that
incorporates both directional and topological spatial
constraints, retrieves similar images, and recognized
images even after they undergo translation, scaling,
rotation (both perfect and multiple), or any arbitrary
combination of transformations. The FRISS framework is
discussed and used as a base for comparing various
existing RSS algorithms. Analysis shows that none of
them satisfies all the FRISS specifications. An
algorithm, {\em SIM dtc}, is then presented. {\em SIM
dtc\/} introduces the concept of a {\em rotation
correction angle\/} (RCA) to align objects in one image
spatially closer to matching objects in another image
for more accurate similarity assessment. Similarity
between two images is a function of the number of
common objects between them and the closeness of
directional and topological spatial relationships
between object pairs in both images. The {\em SIM
dtc\/} retrieval is invariant under translation,
scaling, and perfect rotation, and the algorithm is
able to rank multiple rotation variants. The algorithm
was tested using synthetic images and the TESSA image
database. Analysis shows the robustness of the {\em SIM
dtc\/} algorithm over current algorithms.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Design; Experimentation; Measurement",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "content-based retrieval; image databases; multimedia
databases; query formulation; retrieval models;
similarity retrieval; spatial similarity",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Retrieval models}; Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Query formulation}",
}
@Article{Shipman:1999:IFH,
author = "Frank M. Shipman and Raymond J. McCall",
title = "Incremental formalization with the hyper-object
substrate",
journal = j-TOIS,
volume = "17",
number = "2",
pages = "199--227",
month = apr,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-2/p199-shipman/",
abstract = "Computers require formally represented information to
perform computations that support users; yet users who
have needed such support have often proved to be unable
or unwilling to formalize it. To address this problem,
this article introduces an approach called incremental
formalization, in which, first, users express
information informally and then the system aids them in
formalizing it. Incremental formalization requires a
system architecture the (1) integrates formal and
informal representations and (2) supports progressive
formalization of information. The system should have
both tools to capture naturally available informal
information and techniques to suggest possible
formalizations of this information. The hyper-object
substrate (HOS) was developed to satisfy these
requirements. HOS has been applied to a number of
problem domains, including network design,
archaeological site analysis, and neuroscience
education. Users have been successful in adding
informal information and then later formalizing it
incrementally with the aid of the system. Our
experience with HOS has reaffirmed the need for
information spaces to evolve during use and has
identified additional considerations in the design and
instantiation of systems enabling and supporting
incremental formalization",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design; Human Factors",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
subject = "Information Systems --- Information Interfaces and
Presentation --- User Interfaces (H.5.2); Information
Systems --- Information Interfaces and Presentation ---
Hypertext/Hypermedia (H.5.4); Computing Methodologies
--- Artificial Intelligence --- Knowledge
Representation Formalisms and Methods (I.2.4)",
}
@Article{Fuhr:1999:DTA,
author = "Norbert Fuhr",
title = "A decision-theoretic approach to database selection in
networked {IR}",
journal = j-TOIS,
volume = "17",
number = "3",
pages = "229--229",
month = jul,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-3/p229-fuhr/",
abstract = "In networked IR, a client submits a query to a broker,
which is in contact with a large number of databases.
In order to yield a maximum number of documents at
minimum cost, the broker has to make estimates about
the retrieval cost of each database, and then decide
for each database whether or not to use it for the
current query, and if, how many documents to retrieve
from it. For this purpose, we develop a general
decision-theoretic model and discuss different cost
structures. Besides cost for retrieving relevant versus
nonrelevant documents, we consider the following
parameters for each database: expected retrieval
quality, expected number of relevant documents in the
database and cost factors for query processing and
document delivery. For computing the overall optimum, a
divide-and-conquer algorithm is given. If there are
several brokers knowing different databases, a
preselection of brokers can only be performed
heuristically, but the computation of the optimum can
be done similarly to the single-broker case. In
addition, we derive a formula which estimates the
number of relevant documents in a database based on
dictionary information.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "networked retrieval; probabilistic retrieval;
probability ranking principle; resource discovery",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Retrieval models}; Information Systems ---
Information Storage and Retrieval --- Systems and
Software (H.3.4): {\bf Information networks}",
}
@Article{Gauch:1999:CAA,
author = "Susan Gauch and Jianying Wang and Satya Mahesh
Rachakonda",
title = "A corpus analysis approach for automatic query
expansion and its extension to multiple databases",
journal = j-TOIS,
volume = "17",
number = "3",
pages = "250--250",
month = jul,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-3/p250-gauch/",
abstract = "Searching online text collections can be both
rewarding and frustrating. While valuable information
can be found, typically many irrelevant documents are
also retrieved, while many relevant ones are missed.
Terminology mismatches between the user's query and
document contents are a main cause of retrieval
failures. Expanding a user's query with related words
can improve search performances, but finding and using
related words is an open problem. This research uses
corpus analysis techniques to automatically discover
similar words directly from the contents of the
databases which are not tagged with part-of-speech
labels. Using these similarities, user queries are
automatically expanded, resulting in conceptual
retrieval rather than requiring exact word matches
between queries and documents. We are able to achieve a
7.6\% improvement for TREC 5 queries and up to a 28.5\%
improvement on the narrow-domain Cystic Fibrosis
collection. This work has been extended to
multidatabase collections where each subdatabase has a
collection-specific similarity matrix associated with
it. If the best matrix is selected, substantial search
improvements are possible. Various techniques to select
the appropriate matrix for a particular query are
analyzed, and a 4.8\% improvement in the results is
validated.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Experimentation",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "query expansion",
subject = "Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1):
{\bf Linguistic processing}; Information Systems ---
Information Storage and Retrieval --- Content Analysis
and Indexing (H.3.1): {\bf Thesauruses}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Query
formulation}",
}
@Article{Goh:1999:CIN,
author = "Cheng Hian Goh and St{\'e}phane Bressan and Stuart
Madnick and Michael Siegel",
title = "Context interchange: new features and formalisms for
the intelligent integration of information",
journal = j-TOIS,
volume = "17",
number = "3",
pages = "270--270",
month = jul,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-3/p270-goh/",
abstract = "The {\em Context Interchange strategy\/} presents a
novel perspective for mediated data access in which
semantic conflicts among heterogeneous systems are not
identified a priori, but are detected and reconciled by
a {\em context mediator\/} through comparison of {\em
contexts axioms\/} corresponding to the systems engaged
in data exchange. In this article, we show that queries
formulated on shared views, export schema, and shared
``ontologies'' can be mediated in the same way using
the {\em Context Interchange framework}. The proposed
framework provides a logic-based object-oriented
formalism for representing and reasoning about data
semantics in disparate systems, and has been validated
in a prototype implementation providing mediated data
access to both traditional and web-based information
sources.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "abductive reasoning; information integration;
mediators; semantic heterogeneity; semantic
interoperability",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Database Management --- Heterogeneous
Databases (H.2.5): {\bf Data translation**};
Information Systems --- Database Management ---
Heterogeneous Databases (H.2.5)",
}
@Article{Lim:1999:HDQ,
author = "Ee-Peng Lim and Ying Lu",
title = "{Harp}: a distributed query system for legacy public
libraries and structured databases",
journal = j-TOIS,
volume = "17",
number = "3",
pages = "294--294",
month = jul,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-3/p294-lim/",
abstract = "The main purpose of a digital library is to facilitate
users easy access to enormous amount of globally
networked information. Typically, this information
includes preexisting public library catalog data,
digitized document collections, and other databases. In
this article, we describe the distributed query system
of a digital library prototype system known as HARP. In
the HARP project, we have designed and implemented a
distributed query processor and its query front-end to
support integrated queries to preexisting public
library catalogs and structured databases. This article
describes our experiences in the design of an extended
Sequel (SQL) query language known as HarpSQL. It also
presents the design and implementation of the
distributed query system. Our experience in distributed
query processor and user interface design and
development will be highlighted. We believe that our
prototyping effort will provide useful lessons to the
development of a complete digital library
infrastructure.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "digital libraries; Internet databases; interoperable
databases",
subject = "Information Systems --- Information Storage and
Retrieval (H.3); Information Systems --- Information
Interfaces and Presentation --- User Interfaces
(H.5.2): {\bf User interface management systems
(UIMS)}",
}
@Article{Plaisant:1999:IDA,
author = "Catherine Plaisant and Ben Shneiderman and Khoa Doan
and Tom Bruns",
title = "Interface and data architecture for query preview in
networked information systems",
journal = j-TOIS,
volume = "17",
number = "3",
pages = "320--320",
month = jul,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-3/p320-plaisant/",
abstract = "There are numerous problems associated with
formulating queries on networked information systems.
These include increased data volume and complexity,
accompanied by slow network access. This article
proposes a new approach to a network query user
interfaces that consists of two phases: query preview
and query refinement. This new approach is based on the
concepts of dynamic queries and query previews, which
guides users in rapidly and dynamically eliminating
undesired records, reducing the data volume to a
manageable size, and refining queries locally before
submission over a network. Examples of two applications
are given: a Restaurant Finder and a prototype for
NASA's Earth Observing Systems Data Information Systems
(EOSDIS). Data architecture is discussed, and user
feedback is presented.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design; Human Factors",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "direct manipulation; dynamic query; EOSDIS; graphical
user interface; query preview; query refinement;
science data",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Query formulation}; Information Systems ---
Information Interfaces and Presentation --- User
Interfaces (H.5.2)",
}
@Article{Chen:1999:IGL,
author = "Hao Chen and Jianying Hu and Richard W. Sproat",
title = "Integrating geometrical and linguistic analysis for
email signature block parsing",
journal = j-TOIS,
volume = "17",
number = "4",
pages = "343--366",
month = oct,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/articles/journals/tois/1999-17-4/p343-chen/p343-chen.pdf;
http://www.acm.org/pubs/citations/journals/tois/1999-17-4/p343-chen/",
abstract = "The signature block is a common structured component
found in email messages. Accurate identification and
analysis of signature blocks is important in many
multimedia messaging and information retrieval
applications such as email text-to-speech rendering,
automatic construction of personal address databases,
and interactive message retrieval. It is also a very
challenging task, because signature blocks often appear
in complex two-dimensional layouts which are guided
only by loose conventions. Traditional text analysis
methods designed to deal with sequential text cannot
handle two-dimensional structures, while the highly
unconstrained nature of signature blocks makes the
application of two-dimensional grammars very difficult.
In this article, we describe an algorithm for signature
block analysis which combines two-dimensional
structural segmentation with one-dimensional
grammatical constraints. The information obtained from
both layout and linguistic analysis is integrated in
the form of weighted finite-state transducers. The
algorithm is currently implemented as a component in a
preprocessing system for email text-to-speech
rendering.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "email signature block; finite-state transducer;
geometrical analysis; linguistic analysis;
text-to-speech rendering",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Selection process}; Information Systems ---
Information Systems Applications --- Communications
Applications (H.4.3): {\bf Electronic mail}",
}
@Article{Greiff:1999:PMC,
author = "Warren R. Greiff and W. Bruce Croft and Howard
Turtle",
title = "{PIC} matrices: a computationally tractable class of
probabilistic query operators",
journal = j-TOIS,
volume = "17",
number = "4",
pages = "367--405",
month = oct,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-4/p367-greiff/",
abstract = "The inference network model of information retrieval
allows a probabilistic interpretation of query
operators. In particular, Boolean query operators are
conveniently modeled as link matrices of the Bayesian
Network. Prior work has shown, however, that these
operators do not perform as well as the {\em pnorm\/}
operators used for modeling query operators in the
context of the vector space model. This motivates the
search for alternative probabilistic formulations for
these operators. The design of such alternatives must
contend with the issue of computational tractability,
since the evaluation of an arbitrary operator requires
exponential time. We define a flexible class of link
matrices that are natural candidates for the
implementation of query operators and an $O(n^2)$
algorithm ($n$ = the number of parent nodes) for the
computation of probabilities involving link matrices of
this class. We present experimental results indicating
that Boolean operators implemented in terms of link
matrices from this class perform as well as {\em
pnorm\/} operators in the context of the INQUERY
inference network.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Bayesian networks; Boolean queries; computational
complexity; inference networks; link matrices;
piecewise linear functions; pnorm; probabilistic
information retrieval; query operators",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Query formulation}",
}
@Article{Kaszkiel:1999:EPR,
author = "Marcin Kaszkiel and Justin Zobel and Ron Sacks-Davis",
title = "Efficient passage ranking for document databases",
journal = j-TOIS,
volume = "17",
number = "4",
pages = "406--439",
month = oct,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-4/p406-kaszkiel/",
abstract = "Queries to text collections are resolved by ranking
the documents in the collection and returning the
highest-scoring documents to the user. An alternative
retrieval method is to rank passages, that is, short
fragments of documents, a strategy that can improve
effectiveness and identify relevant material in
documents that are too large for users to consider as a
whole. However, ranking of passages can considerably
increase retrieval costs. In this article we explore
alternative query evaluation techniques, and develop
new techniques for evaluating queries on passages. We
show experimentally that, appropriately implemented,
effective passage retrieval is practical in limited
memory on a desktop machine. Compared to passage
ranking with adaptations of current document ranking
algorithms, our new ``DO-TOS'' passage-ranking
algorithm requires only a fraction of the resources, at
the cost of a small loss of effectiveness.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "inverted files; passage retrieval; query evaluation;
text databases; text retrieval",
subject = "Data --- Files (E.5); Information Systems --- Database
Management --- Physical Design (H.2.2); Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3)",
}
@Article{Sanderson:1999:IRE,
author = "Mark Sanderson and C. J. {Van Rijsbergen}",
title = "The impact on retrieval effectiveness of skewed
frequency distributions",
journal = j-TOIS,
volume = "17",
number = "4",
pages = "440--465",
month = oct,
year = "1999",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/1999-17-4/p440-sanderson/",
abstract = "We present an analysis of word senses that provides a
fresh insight into the impact of word ambiguity on
retrieval effectiveness with potential broader
implications for other processes of information
retrieval. Using a methodology of forming artificially
ambiguous words, known as pseudowords, and through
reference to other researchers' work, the analysis
illustrates that the distribution of the frequency of
occurrence of the senses of a word plays a strong role
in ambiguity's impact of effectiveness. Further
investigation shows that this analysis may also be
applicable to other processes of retrieval, such as
Cross Language Information Retrieval, query expansion,
retrieval of OCR'ed texts, and stemming. The analysis
appears to provide a means of explaining, at least in
part, reasons for the processes' impact (or lack of it)
on effectiveness.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Experimentation; Measurement",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "pseudowords; word sense ambiguity; word sense
disambiguation",
subject = "Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1):
{\bf Linguistic processing}; Computing Methodologies
--- Artificial Intelligence --- Natural Language
Processing (I.2.7): {\bf Text analysis}; Computing
Methodologies --- Simulation and Modeling --- Model
Validation and Analysis (I.6.4); Information Systems
--- Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Search process}",
}
@Article{Cahoon:2000:EPD,
author = "Brendon Cahoon and Kathryn S. McKinley and Zhihong
Lu",
title = "Evaluating the performance of distributed
architectures for information retrieval using a variety
of workloads",
journal = j-TOIS,
volume = "18",
number = "1",
pages = "1--43",
month = jan,
year = "2000",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-1/p1-cahoon/",
abstract = "The information explosion across the Internet and
elsewhere offers access to an increasing number of
document collections. In order for users to effectively
access these collections, information retrieval (IR)
systems must provide coordinated, concurrent, and
distributed access. In this article, we explore how to
achieve scalable performance in a distributed system
for collection sizes ranging from 1GB to 128GB. We
implement a fully functional distributed IR system
based on a multithreaded version of the Inquery
simulation model. We measure performance as a function
of system parameters such as client command rate,
number of document collections, ter ms per query, query
term frequency, number of answers returned, and command
mixture. Our results show that it is important to model
both query and document commands because the
heterogeneity of commands significantly impacts
performance. Based on our results, we recommend simple
changes to the prototype and evaluate the changes using
the simulator. Because of the significant resource
demands of information retrieval, it is not difficult
to generate workloads that overwhelm system resources
regardless of the architecture. However under some
realistic workloads, we demonstrate system
organizations for which response time gracefully
degrades as the workload increases and performance
scales with the number of processors. This scalable
architecture includes a surprisingly small number of
brokers through which a large number of clients and
servers communicate.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "distributed information retrieval architectures",
subject = "Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4); Computer Systems Organization --- Performance
of Systems (C.4); Computer Systems Organization ---
Performance of Systems (C.4): {\bf Performance
attributes}; Information Systems --- Information
Storage and Retrieval --- Systems and Software
(H.3.4)",
}
@Article{Clarke:2000:SSR,
author = "Charles L. A. Clarke and Gordon V. Cormack",
title = "Shortest-substring retrieval and ranking",
journal = j-TOIS,
volume = "18",
number = "1",
pages = "44--78",
month = jan,
year = "2000",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-1/p44-clarke/",
abstract = "We present a model for arbitrary passage retrieval
using Boolean queries. The model is applied to the task
of ranking documents, or other structural elements, in
the order of their expected relevance. Features such as
phrase matching, truncation, and stemming integrate
naturally into the model. Properties of Boolean algebra
are obeyed, and the exact-match semantics of Boolean
retrieval are preserved. Simple inverted-list file
structures provide an efficient implementation.
Retrieval effectiveness is comparable to that of
standard ranking techniques. Since global statistics
are not used, the method is of particular value in
distributed environments. Since ranking is based on
arbitrary passages, the structural elements to be
ranked may be specified at query time and do not need
to be restricted to predefined elements.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Boolean retrieval model; passage retrieval; relevance
ranking",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3);
Information Systems --- Information Storage and
Retrieval --- Systems and Software (H.3.4); Information
Systems --- Information Storage and Retrieval ---
Systems and Software (H.3.4): {\bf Performance
evaluation (efficiency and effectiveness)}",
}
@Article{Xu:2000:IEI,
author = "Jinxi Xu and W. Bruce Croft",
title = "Improving the effectiveness of information retrieval
with local context analysis",
journal = j-TOIS,
volume = "18",
number = "1",
pages = "79--112",
month = jan,
year = "2000",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-1/p79-xu/",
abstract = "Techniques for automatic query expansion have been
extensively studied in information research as a means
of addressing the word mismatch between queries and
documents. These techniques can be categorized as
either global or local. While global techniques rely on
analysis of a whole collection to discover word
relationships, local techniques emphasize analysis of
the top-ranked documents retrieved for a query. While
local techniques have shown to be more effective that
global techniques in general, existing local techniques
are not robust and can seriously hurt retrieved when
few of the retrieval documents are relevant. We propose
a new technique, called {\em local context analysis,\/}
which selects expansion terms based on cooccurrence
with the query terms within the top-ranked documents.
Experiments on a number of collections, both English
and non-English, show that local context analysis
offers more effective and consistent retrieval
results.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "cooccurrence; document analysis; feedback; global
techniques; information retrieval; local context
analysis; local techniques",
subject = "Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1);
Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1):
{\bf Indexing methods}; Information Systems ---
Information Storage and Retrieval --- Content Analysis
and Indexing (H.3.1): {\bf Thesauruses}; Information
Systems --- Information Storage and Retrieval ---
Content Analysis and Indexing (H.3.1): {\bf Linguistic
processing}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3); Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Query formulation}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}; Information Systems --- Information Storage
and Retrieval --- Information Search and Retrieval
(H.3.3): {\bf Relevance feedback}",
}
@Article{SilvadeMoura:2000:FFW,
author = "Edleno {Silva de Moura} and Gonzalo Navarro and Nivio
Ziviani and Ricardo Baeza-Yates",
title = "Fast and flexible word searching on compressed text",
journal = j-TOIS,
volume = "18",
number = "2",
pages = "113--139",
month = apr,
year = "2000",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-2/p113-silva_de_moura/",
abstract = "We present a fast compression technique for natural
language texts. The novelties are that (1)
decompression of arbitrary portions of the text can be
done very efficiently, (2) exact search for words and
phrases can be done on the compressed text directly,
using any known sequential pattern-matching algorithm,
and (3) word-based approximate and extended search can
also be done efficiently without any decoding. The
compression scheme uses a semistatic word-based model
and a Huffman code where the coding alphabet is
byte-oriented rather than bit-oriented. We compress
typical English texts to about 30\% of their original
size, against 40\% and 35\% for {\em Compress\/} and
{\em Gzip}, respectively. Compression time is close to
that of {\em Compress\/} and approximately half of the
time of {\em Gzip}, and decompression time is lower
than that of {\em Gzip\/} and one third of that of {\em
Compress}. We present three algorithms to search the
compressed text. They allow a large number of
variations over the basic word and phrase search
capability, such as sets of characters, arbitrary
regular expressions, and approximate matching.
Separators and stopwords can be discarded at search
time without significantly increasing the cost. When
searching for simple words, the experiments show that
running our algorithms on a compressed text is twice as
fast as running the best existing software on the
uncompressed version of the same text. When searching
complex or approximate patterns, our algorithms are up
to 8 times faster than the search on uncompressed text.
We also discuss the impact of our technique in inverted
files pointing to logical blocks and argue for the
possibility of keeping the text compressed all the
time, decompressing only for displaying purposes.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "compressed pattern matching; natural language text
compression; word searching; word-based Huffman
coding",
subject = "Data --- Coding and Information Theory (E.4): {\bf
Data compaction and compression}; Information Systems
--- Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Search process}",
}
@Article{Dourish:2000:EDM,
author = "Paul Dourish and W. Keith Edwards and Anthony LaMarca
and John Lamping and Karin Petersen and Michael
Salisbury and Douglas B. Terry and James Thornton",
title = "Extending document management systems with
user-specific active properties",
journal = j-TOIS,
volume = "18",
number = "2",
pages = "140--170",
month = apr,
year = "2000",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-2/p140-dourish/",
abstract = "Document properties are a compelling infrastructure on
which to develop document management applications. A
property-based approach avoids many of the problems of
traditional hierarchical storage mechanisms, reflects
document organizations meaningful to user tasks,
provides a means to integrate the perspectives of
multiple individuals and groups, and does this all
within a uniform interaction framework. Document
properties can reflect not only categorizations of
documents and document use, but also expressions of
desired system activity, such as sharing criteria,
replication management, and versioning. Augmenting
property-based document management systems with active
properties that carry executable code enables the
provision of document-based services on a property
infrastructure. The combination of document properties
as a uniform mechanism for document management, and
active properties as a way of delivering document
services, represents a new paradigm for document
management infrastructures. The Placeless Documents
system is an experimental prototype developed to
explore this new paradigm. It is based on the seamless
integration of user-specific, active properties. We
present the fundamental design approach, explore the
challenges and opportunities it presents, and show our
architectures deals with them.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "active properties; component software; document
management systems; document services; user
experience",
subject = "Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4): {\bf Distributed databases}; Software ---
Operating Systems --- File Systems Management (D.4.3):
{\bf Distributed file systems}; Data --- Files (E.5):
{\bf Organization/structure}; Information Systems ---
Information Storage and Retrieval --- Information
Storage (H.3.2): {\bf File organization}; Information
Systems --- Information Storage and Retrieval ---
Systems and Software (H.3.4): {\bf Distributed
systems}; Information Systems --- Information Storage
and Retrieval --- Information Search and Retrieval
(H.3.3): {\bf Search process}",
}
@Article{El-Kwae:2000:ECB,
author = "Essam A. El-Kwae and Mansur R. Kabuka",
title = "Efficient content-based indexing of large image
databases",
journal = j-TOIS,
volume = "18",
number = "2",
pages = "171--210",
month = apr,
year = "2000",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Sep 26 09:34:01 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-2/p171-el-kwae/",
abstract = "Large image databases have emerged in various
applications in recent years. A prime requisite of
these databases is the means by which their contents
can be indexed and retrieved. A multilevel signature
file called the Two Signature Multi-level Signature
File ( {\em 2SMLSF\/} ) is introduced as an efficient
access structure for large image databases. The {\em
2SMLSF\/} encodes image information into binary
signatures and creates a tree structures can be
efficiently searched to satisfy a user's query. Two
types of signatures are generated. Type {\em I\/}
signatures are used at all tree levels except the leaf
level and are based only on the domain objects included
in the image. Type {\em II\/} signatures, on the other
hand, are stored at the leaf level and are based on the
included domain objects and their spatial
relationships. The {\em 2SMLSF\/} was compared
analytically to existing signature file techniques. The
{\em 2SMLSF\/} significantly reduces the storage
requirements; the index structure can answer more
queries; and the {\em 2SMLSF\/} performance
significantly improves over current techniques. Both
storage reduction and performance improvement increase
with the number of objects per image and the number of
images in the database. For an example large image
database, a storage reduction of 78\% may be achieved
while the performance improvement may reach 98\%.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "content analysis and indexing; document managing;
image databases; index generation; multimedia
databases",
}
@Article{Anderson:2000:CHH,
author = "Kenneth M. Anderson and Richard N. Taylor and E. James
Whitehead",
title = "{Chimera}: hypermedia for heterogeneous software
development enviroments",
journal = j-TOIS,
volume = "18",
number = "3",
pages = "211--245",
year = "2000",
bibdate = "Tue Apr 17 08:10:03 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-3/p211-anderson/",
abstract = "Emerging software development environments are
characterized by heterogeneity: they are composed of
diverse object stores, user interfaces, and tools. This
paper presents an approach for providing hypermedia
services in this heterogeneous setting. Central notions
of the approach include the following: anchors are
established with respect to interactive {\em views\/}
of objects, rather than the objects themselves;
composable, $n$-ary links can be established between
anchors on different views of objects which may be
stored in distinct object bases; viewers may be
implemented in different programming languages; and,
hypermedia services are provided to multiple,
concurrently active, viewers. The paper describes the
approach, supporting architecture, and lessons learned.
Related work in the areas of supporting heterogeneity
and hypermedia data modeling is discussed. The system
has been employed in a variety of contexts including
research, development, and education.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "heterogeneous hypermedia; hypermedia system
architectures; link servers; open hypermedia systems;
software development environments",
subject = "Information Systems --- Information Interfaces and
Presentation --- Multimedia Information Systems
(H.5.1); Software --- Software Engineering --- Design
Tools and Techniques (D.2.2); Computing Methodologies
--- Document and Text Processing --- Document
Preparation (I.7.2): {\bf Hypertext/hypermedia};
Information Systems --- Information Interfaces and
Presentation --- Hypertext/Hypermedia (H.5.4)",
}
@Article{Greiff:2000:MEA,
author = "Warren R. Greiff and Jay M. Ponte",
title = "The maximum entropy approach and probabilistic {IR}
models",
journal = j-TOIS,
volume = "18",
number = "3",
pages = "246--287",
year = "2000",
bibdate = "Tue Apr 17 08:10:03 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-3/p246-greiff/",
abstract = "This paper takes a fresh look at modeling approaches
to information retrieval that have been the basis of
much of the probabilistically motivated IR research
over the last 20 years. We shall adopt a subjectivist
Bayesian view of probabilities and argue that classical
work on probabilistic retrieval is best understood from
this perspective. The main focus of the paper will be
the ranking formulas corresponding to the Binary
Independence Model (BIM), presented originally by
Roberston and Sparck John [1977] and the Combination
Match Model (CMM), developed shortly thereafter by
Croft and Harper [1979]. We will show how these same
ranking formulas can result from a probabilistic
methodology commonly known as Maximum Entropy
(MAXENT).",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Retrieval models}",
}
@Article{Cohen:2000:DIU,
author = "William W. Cohen",
title = "Data integration using similarity joins and a
word-based information representation language",
journal = j-TOIS,
volume = "18",
number = "3",
pages = "288--321",
year = "2000",
bibdate = "Tue Apr 17 08:10:03 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-3/p288-cohen/",
abstract = "The integration of distributed, heterogeneous
databases, such as those available on the World Wide
Web, poses many problems. Herer we consider the problem
of integrating data from sources that lack common
object identifiers. A solution to this problem is
proposed for databases that contain informal,
natural-language ``names'' for objects; most Web-based
databases satisfy this requirement, since they usually
present their information to the end-user through a
veneer of text. We describe WHIRL, a ``soft'' database
management system which supports ``similarity joins,''
based on certain robust, general-purpose similarity
metrics for text. This enables fragments of text (e.g.,
informal names of objects) to be used as keys. WHIRL
includes textual objects as a built-in type, similarity
reasoning as a built-in predicate, and answers every
query with a list of answer substitutions that are
ranked according to an overall score. Experiments show
that WHIRL is much faster than naive inference methods,
even for short queries, and efficient on typical
queries to real-world databases with tens of thousands
of tuples. Inferences made by WHIRL are also
surprisingly accurate, equaling the accuracy of
hand-coded normalization routines on one benchmark
problem, and outperforming exact matching with a
plausible global domain on a second.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
subject = "Information Systems --- Database Management ---
Heterogeneous Databases (H.2.5); Information Systems
--- Database Management --- Languages (H.2.3): {\bf
Data manipulation languages (DML)}; Information Systems
--- Database Management --- Languages (H.2.3): {\bf
Query languages}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Retrieval models}",
}
@Article{Fraternali:2000:MDD,
author = "Piero Fraternali and Paolo Paolini",
title = "Model-driven development of {Web} applications: the
{AutoWeb} system",
journal = j-TOIS,
volume = "18",
number = "4",
pages = "323--382",
year = "2000",
bibdate = "Tue Apr 17 08:10:03 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-4/p323-fraternali/",
abstract = "This paper describes a methodology for the development
of WWW applications and a tool environment specifically
tailored for the methodology. The methodology and the
development environment are based upon models and
techniques already used in the hypermedia, information
systems, and software engineering fields, adapted and
blended in an original mix. The foundation of the
proposal is the conceptual design of WWW applications,
using HDM-lite, a notation for the specification of
structure, navigation, and presentation semantics. The
conceptual schema is then translated into a
``traditional'' database schema, which describes both
the organization of the content and the desired
navigation and presentation features. The WWW pages can
therefore be dynamically generated from the database
content, following the navigation requests of the user.
A CASE environment, called AutoWeb System, offers a set
of software tools, which assist the design and the
execution of a WWW application, in all its different
aspects, Real-life experiences of the use of the
methodology and of the AutoWeb System in both the
industrial and academic context are reported.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design; Experimentation; Human Factors",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "application; development; HTML; intranet; modeling;
WWW",
subject = "Information Systems --- Information Interfaces and
Presentation --- Hypertext/Hypermedia (H.5.4); Software
--- Software Engineering --- Design Tools and
Techniques (D.2.2)",
}
@Article{Katzenstein:2000:BSO,
author = "Gary Katzenstein and F. Javier Lerch",
title = "Beneath the surface of organizational processes: a
social representation framework for business process
redesign",
journal = j-TOIS,
volume = "18",
number = "4",
pages = "383--422",
year = "2000",
bibdate = "Tue Apr 17 08:10:03 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/citations/journals/tois/2000-18-4/p383-katzenstein/",
abstract = "This paper raises the question, ``What is an effective
representation framework for organizational process
design?'' By combining our knowledge of existing
process models with data from a field study, the paper
develops criteria for an effective process
representation. Using these criteria and the case
study, the paper integrates the process redesign and
information system literatures to develop a
representation framework that captures a process'
social context. The paper argues that this social
context framework, which represents people's
motivations, social relationships, and social
constraints, gives redesigners a richer sense of the
process and allows process redesigners to
simultaneously change social and logistic systems. The
paper demonstrates the framework and some of its
benefits and limitations.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "business process redesign; organizational change;
process representation",
subject = "Computing Milieux --- Computers and Society ---
Organizational Impacts (K.4.3)",
}
@Article{Carpineto:2001:ITA,
author = "Claudio Carpineto and Renato de Mori and Giovanni
Romano and Brigitte Bigi",
title = "An information-theoretic approach to automatic query
expansion",
journal = j-TOIS,
volume = "19",
number = "1",
pages = "1--27",
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 17 08:17:10 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/articles/journals/tois/2001-19-1/p1-carpineto/p1-carpineto.pdf;
http://www.acm.org/pubs/citations/journals/tois/2001-19-1/p1-carpineto/",
abstract = "Techniques for automatic query expansion from top
retrieved documents have shown promise for improving
retrieval effectiveness on large collections; however,
they often rely on an empirical ground, and there is a
shortage of cross-system comparisons. Using ideas from
Information Theory, we present a computationally simple
and theoretically justified method for assigning scores
to candidate expansion terms. Such scores are used to
select and weight expansion terms within Rocchio's
framework for query reweighting. We compare ranking
with information-theoretic query expansion versus
ranking with other query expansion techniques, showing
that the former achieves better retrieval effectiveness
on several performance measures. We also discuss the
effect on retrieval effectiveness of the main
parameters involved in automatic query expansion, such
as data sparseness, query difficulty, number of
selected documents, and number of selected terms,
pointing out interesting relationships.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Design; Experimentation; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "automatic query expansion; information retrieval;
information theory; pseudorelevance feedback",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Retrieval models}; Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Relevance feedback};
Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Query formulation}; Information Systems ---
Information Storage and Retrieval --- Content Analysis
and Indexing (H.3.1): {\bf Indexing methods}",
}
@Article{deOliveira:2001:SBM,
author = "Maria Cristina Ferreira de Oliveira and Marcelo
Augusto Santos Turine and Paulo Cesar Masiero",
title = "A statechart-based model for hypermedia applications",
journal = j-TOIS,
volume = "19",
number = "1",
pages = "28--52",
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 17 08:17:10 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/articles/journals/tois/2001-19-1/p28-de_oliveira/p28-de_oliveira.pdf;
http://www.acm.org/pubs/citations/journals/tois/2001-19-1/p28-de_oliveira/",
abstract = "This paper presents a formal definition for HMBS
(Hypermedia Model Based on Statecharts). HMBS uses the
structure and execution semantics of statecharts to
specify both the structural organization and the
browsing semantics of hypermedia applications.
Statecharts are an extension of finite-state machines
and the model is thus a generalization of
hypergraph-based hypertext models. Some of the most
important features of HMBS are its ability to model
hierarchy and synchronization of information; provision
of mechanisms for specifying access structures,
navigational contexts, access control, multiple
tailored versions,and hierarchical views. Analysis of
the underlying statechart machine allows verification
of page reachability, valid paths, and other
properties, thus providing mechanisms to support
authors in the development of structured
applications.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
generalterms = "Algorithms; Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "browsing semantics; HMBS; hypermedia specification;
navigational model; statecharts",
subject = "Theory of Computation --- Computation by Abstract
Devices --- Models of Computation (F.1.1): {\bf
Relations between models}; Computing Methodologies ---
Document and Text Processing --- Document Preparation
(I.7.2): {\bf Hypertext/hypermedia}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}; Information Systems --- Information Storage
and Retrieval --- Systems and Software (H.3.4): {\bf
Information networks}; Information Systems ---
Information Interfaces and Presentation --- Multimedia
Information Systems (H.5.1): {\bf Hypertext navigation
and maps**}; Information Systems --- Information
Interfaces and Presentation --- Hypertext/Hypermedia
(H.5.4)",
}
@Article{Papadias:2001:AST,
author = "Dimitris Papadias and Nikos Mamoulis and Vasilis
Delis",
title = "Approximate spatio-temporal retrieval",
journal = j-TOIS,
volume = "19",
number = "1",
pages = "53--96",
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 17 08:17:10 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "http://www.acm.org/pubs/articles/journals/tois/2001-19-1/p53-papadias/p53-papadias.pdf;
http://www.acm.org/pubs/citations/journals/tois/2001-19-1/p53-papadias/",
abstract = "This paper proposes a framework for the handling of
spatio-temporal queries with inexact matches, using the
concept of relation similarity. We initially describe a
binary string encoding for 1D relations that permits
the automatic derivation of similarity measures. We
then extend this model to various granularity levels
and many dimensions, and show that reasoning on
spatio-temporal structure is significantly facilitated
in the new framework. Finally, we provide algorithms
and optimization methods for four types of queries: (i)
object retrieval based on some spatio-temporal
relations with respect to a reference object, (ii)
spatial joins, i.e., retrieval of object pairs that
satisfy some input relation, (iii) structural queries,
which retrieve configurations matching a particular
spatio-temporal structure, and (iv) special cases of
motion queries. Considering the current large
availability of multidimensional data and the
increasing need for flexible query-answering
mechanisms, our techniques can be used as the core of
spatio-temporal query processors.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Access methods};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Multimedia databases}; Information
Systems --- Database Management --- Database
Applications (H.2.8): {\bf Spatial databases and GIS}",
}
@Article{Callan:2001:QBS,
author = "Jamie Callan and Margaret Connell",
title = "Query-based sampling of text databases",
journal = j-TOIS,
volume = "19",
number = "2",
pages = "97--130",
month = apr,
year = "2001",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/382979.383040",
ISSN = "1046-8188",
bibdate = "Thu Oct 1 16:56:41 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The proliferation of searchable text databases on
corporate networks and the Internet causes a database
selection problem for many people. Algorithms such as
gGLOSS and CORI can automatically select which text
databases to search for a given information need, but
only if given a set of resource descriptions that
accurately represent the contents of each database. The
existing techniques for a acquiring resource
descriptions have significant limitations when used in
wide-area networks controlled by many parties. This
paper presents query-based sampling, a new technique
for acquiring accurate resource descriptions.
Query-based sampling does not require the cooperation
of resource providers, nor does it require that
resource providers use a particular search engine or
representation technique. An extensive set of
experimental results demonstrates that accurate
resource descriptions are created, that computation and
communication costs are reasonable, and that the
resource descriptions do in fact enable accurate
automatic database selection.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lempel:2001:SSA,
author = "R. Lempel and S. Moran",
title = "{SALSA}: the stochastic approach for link-structure
analysis",
journal = j-TOIS,
volume = "19",
number = "2",
pages = "131--160",
month = apr,
year = "2001",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/382979.383041",
ISSN = "1046-8188",
bibdate = "Thu Oct 1 16:56:41 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Today, when searching for information on the WWW, one
usually performs a query through a term-based search
engine. These engines return, as the query's result, a
list of Web pages whose contents matches the query. For
broad-topic queries, such searches often result in a
huge set of retrieved documents, many of which are
irrelevant to the user. However, much information is
contained in the link-structure of the WWW. Information
such as which pages are linked to others can be used to
augment search algorithms. In this context, Jon
Kleinberg introduced the notion of two distinct types
of Web pages: hubs and authorities. Kleinberg argued
that hubs and authorities exhibit a mutually
reinforcing relationship: a good hub will point to many
authorities, and a good authority will be pointed at by
many hubs. In light of this, he devised an algorithm
aimed at finding authoritative pages. We present SALSA,
a new stochastic approach for link-structure analysis,
which examines random walks on graphs derived from the
link-structure. We show that both SALSA and Kleinberg's
Mutual Reinforcement approach employ the same
metaalgorithm. We then prove that SALSA is equivalent to
a weighted in degree analysis of the link-structure of
WWW subgraphs, making it computationally more efficient
than the Mutual reinforcement approach. We compare that
results of applying SALSA to the results derived
through Kleinberg's approach. These comparisons reveal
a topological Phenomenon called the TKC effect which, in
certain cases, prevents the Mutual reinforcement
approach from identifying meaningful authorities.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Meuss:2001:CAA,
author = "Holger Meuss and Klaus U. Schulz",
title = "Complete answer aggregates for treelike databases: a
novel approach to combine querying and navigation",
journal = j-TOIS,
volume = "19",
number = "2",
pages = "161--215",
month = apr,
year = "2001",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/382979.383042",
ISSN = "1046-8188",
bibdate = "Thu Oct 1 16:56:41 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The use of markup languages like SGML, HTML or XML for
encoding the structure of documents or linguistic data
has lead to many databases where entries are adequately
described as trees. In this context querying formalisms
are interesting that offer the possibility to refer both
to textual content and logical structure. We consider
models where the structure specified in a query is not
only used as a filter, but also for selecting and
presenting different parts of the data. If answers are
formalized as mapping from query nodes to the database,
a simple enumeration of all mappings in the answer set
will often suffer from the effect that many answers
have common subparts. From a theoretical point of view
this may lead to an exponential time complexity of the
computation and presentation of all answers.
Concentration on the language of so called tree
queries-a variant and extension of Kilpel{\"a}inen's
Tree Matching formalism-we introduce the notion of a
``complete answer aggregate'' for a given query. This
new data structure offers a compact view of the set of
all answer and supports active exploration of the
answer space. Since complete answer aggregates use a
powerful structure-sharing mechanism their maximal size
is of order $ O(d \cdot h \cdot q) $ where $d$ and $q$
respectively denote the size of the database and the
query, and $h$ is the maximal depth of a path of the
database. An algorithm is given that computes a
complete answer aggregate for a given tree query in
time $ O(d \cdot \log (d) \cdot h \cdot q)$. For the
sublanguage of so-called rigid tree queries, as well as
for so-called ``nonrecursive'' databases, an improved
bound of $ O (d \cdot \log (d) \cdot q)$ is obtained.
The algorithm is based on a specific index structure
that supports practical efficiency.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Melnik:2001:BDF,
author = "Sergey Melnik and Sriram Raghavan and Beverly Yang and
Hector Garcia-Molina",
title = "Building a distributed full-text index for the {Web}",
journal = j-TOIS,
volume = "19",
number = "3",
pages = "217--241",
month = jul,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Kwok:2001:SQA,
author = "Cody Kwok and Oren Etzioni and Daniel S. Weld",
title = "Scaling question answering to the {Web}",
journal = j-TOIS,
volume = "19",
number = "3",
pages = "242--262",
month = jul,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hong:2001:WPB,
author = "Jason I. Hong and Jeffrey Heer and Sarah Waterson and
James A. Landay",
title = "{WebQuilt}: a proxy-based approach to remote web
usability testing",
journal = j-TOIS,
volume = "19",
number = "3",
pages = "263--285",
month = jul,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Aggarwal:2001:DLC,
author = "Charu C. Aggarwal and Fatima Al-Garawi and Philip S.
Yu",
title = "On the design of a learning crawler for topical
resource discovery",
journal = j-TOIS,
volume = "19",
number = "3",
pages = "286--309",
month = jul,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Meng:2001:HSE,
author = "Weiyi Meng and Zonghuan Wu and Clement Yu and Zhuogang
Li",
title = "A highly scalable and effective method for
metasearch",
journal = j-TOIS,
volume = "19",
number = "3",
pages = "310--335",
month = jul,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wong:2001:AAF,
author = "Kam-Fai Wong and Dawei Song and Peter Bruza and
Chun-Hung Cheng",
title = "Application of aboutness to functional benchmarking in
information retrieval",
journal = j-TOIS,
volume = "19",
number = "4",
pages = "337--370",
month = oct,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Comai:2001:CGQ,
author = "Sara Comai and Ernesto Damiani and Piero Fraternali",
title = "Computing graphical queries over {XML} data",
journal = j-TOIS,
volume = "19",
number = "4",
pages = "371--430",
month = oct,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yoshioka:2001:GTK,
author = "Takeshi Yoshioka and George Herman and JoAnne Yates
and Wanda Orlikowski",
title = "Genre taxonomy: a knowledge repository of
communicative actions",
journal = j-TOIS,
volume = "19",
number = "4",
pages = "431--456",
month = oct,
year = "2001",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Feb 19 14:45:47 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lempel:2002:PPA,
author = "Ronny Lempel and Aya Soffer",
title = "{PicASHOW}: {Pictorial} authority search by hyperlinks
on the {Web}",
journal = j-TOIS,
volume = "20",
number = "1",
pages = "1--24",
month = jan,
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Aridor:2002:KEF,
author = "Yariv Aridor and David Carmel and Yoelle S. Maarek and
Aya Soffer and Ronny Lempel",
title = "Knowledge encapsulation for focused search from
pervasive devices",
journal = j-TOIS,
volume = "20",
number = "1",
pages = "25--46",
month = jan,
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bharat:2002:WEA,
author = "Krishna Bharat and George A. Mihaila",
title = "When experts agree: using non-affiliated experts to
rank popular topics",
journal = j-TOIS,
volume = "20",
number = "1",
pages = "47--58",
month = jan,
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wen:2002:QCU,
author = "Ji-Rong Wen and Jian-Yun Nie and Hong-Jiang Zhang",
title = "Query clustering using user logs",
journal = j-TOIS,
volume = "20",
number = "1",
pages = "59--81",
month = jan,
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Buyukkokten:2002:EWB,
author = "Orkut Buyukkokten and Oliver Kaljuvee and Hector
Garcia-Molina and Andreas Paepcke and Terry Winograd",
title = "Efficient {Web} browsing on handheld devices using
page and form summarization",
journal = j-TOIS,
volume = "20",
number = "1",
pages = "82--115",
month = jan,
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Finkelstein:2002:PSC,
author = "Lev Finkelstein and Evgeniy Gabrilovich and Yossi
Matias and Ehud Rivlin and Zach Solan and Gadi Wolfman
and Eytan Ruppin",
title = "Placing search in context: The concept revisited",
journal = j-TOIS,
volume = "20",
number = "1",
pages = "116--131",
month = jan,
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cooper:2002:PPD,
author = "Brian F. Cooper and Hector Garcia-Molina",
title = "Peer-to-peer data trading to preserve information",
journal = j-TOIS,
volume = "20",
number = "2",
pages = "133--170",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chowdhury:2002:CSF,
author = "Abdur Chowdhury and Ophir Frieder and David Grossman
and Mary Catherine McCabe",
title = "Collection statistics for fast duplicate document
detection",
journal = j-TOIS,
volume = "20",
number = "2",
pages = "171--191",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Heinz:2002:BTF,
author = "Steffen Heinz and Justin Zobel and Hugh E. Williams",
title = "Burst tries: a fast, efficient data structure for
string keys",
journal = j-TOIS,
volume = "20",
number = "2",
pages = "192--223",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhu:2002:TKB,
author = "Lei Zhu and Aibing Rao and Aidong Zhang",
title = "Theory of keyblock-based image retrieval",
journal = j-TOIS,
volume = "20",
number = "2",
pages = "224--257",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:11 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Carpineto:2002:IRF,
author = "Claudio Carpineto and Giovanni Romano and Vittorio
Giannini",
title = "Improving retrieval feedback with multiple
term-ranking function combination",
journal = j-TOIS,
volume = "20",
number = "3",
pages = "259--290",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:12 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Owei:2002:IAH,
author = "Vesper Owei",
title = "An intelligent approach to handling imperfect
information in concept-based natural language queries",
journal = j-TOIS,
volume = "20",
number = "3",
pages = "291--328",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:12 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cannane:2002:GPC,
author = "Adam Cannane and Hugh E. Williams",
title = "A general-purpose compression scheme for large
collections",
journal = j-TOIS,
volume = "20",
number = "3",
pages = "329--355",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:12 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Amati:2002:PMI,
author = "Gianni Amati and Cornelis Joost {Van Rijsbergen}",
title = "Probabilistic models of information retrieval based on
measuring the divergence from randomness",
journal = j-TOIS,
volume = "20",
number = "4",
pages = "357--389",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:12 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Feng:2002:SNB,
author = "Ling Feng and Elizabeth Chang and Tharam Dillon",
title = "A semantic network-based design methodology for {XML}
documents",
journal = j-TOIS,
volume = "20",
number = "4",
pages = "390--421",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:12 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Jarvelin:2002:CGB,
author = "Kalervo J{\"a}rvelin and Jaana Kek{\"a}l{\"a}inen",
title = "Cumulated gain-based evaluation of {IR} techniques",
journal = j-TOIS,
volume = "20",
number = "4",
pages = "422--446",
year = "2002",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:12 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Gravano:2003:QSA,
author = "Luis Gravano and Panagiotis G. Ipeirotis and Mehran
Sahami",
title = "{QProber}: a system for automatic classification of
hidden-{Web} databases",
journal = j-TOIS,
volume = "21",
number = "1",
pages = "1--41",
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:13 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Calado:2003:LVG,
author = "P{\'a}vel Calado and Berthier Ribeiro-Neto and Nivio
Ziviani and Edleno Moura and Ilm{\'e}rio Silva",
title = "Local versus global link information in the {Web}",
journal = j-TOIS,
volume = "21",
number = "1",
pages = "42--63",
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:13 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ganesan:2003:EHD,
author = "Prasanna Ganesan and Hector Garcia-Molina and Jennifer
Widom",
title = "Exploiting hierarchical domain structure to compute
similarity",
journal = j-TOIS,
volume = "21",
number = "1",
pages = "64--93",
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:13 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Conrad:2003:EUS,
author = "Jack G. Conrad and Joanne R. S. Claussen",
title = "Early user--system interaction for database selection
in massive domain-specific online environments",
journal = j-TOIS,
volume = "21",
number = "1",
pages = "94--131",
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:13 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Moldovan:2003:PIE,
author = "Dan Moldovan and Marius Pa{\c{s}}ca and Sanda
Harabagiu and Mihai Surdeanu",
title = "Performance issues and error analysis in an
open-domain question answering system",
journal = j-TOIS,
volume = "21",
number = "2",
pages = "133--154",
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:13 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bertino:2003:HAC,
author = "Elisa Bertino and Jianping Fan and Elena Ferrari and
Mohand-Said Hacid and Ahmed K. Elmagarmid and Xingquan
Zhu",
title = "A hierarchical access control model for video database
systems",
journal = j-TOIS,
volume = "21",
number = "2",
pages = "155--191",
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:13 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Amato:2003:RPM,
author = "Giuseppe Amato and Fausto Rabitti and Pasquale Savino
and Pavel Zezula",
title = "Region proximity in metric spaces and its use for
approximate similarity search",
journal = j-TOIS,
volume = "21",
number = "2",
pages = "192--227",
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Aug 7 10:37:13 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Leroy:2003:UDC,
author = "Gondy Leroy and Ann M. Lally and Hsinchun Chen",
title = "The use of dynamic contexts to improve casual
{Internet} searching",
journal = j-TOIS,
volume = "21",
number = "3",
pages = "229--253",
month = jul,
year = "2003",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/858476.858477",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:24:06 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Research has shown that most users' online information
searches are suboptimal. Query optimization based on a
relevance feedback or genetic algorithm using dynamic
query contexts can help casual users search the
Internet. These algorithms can draw on implicit user
feedback based on the surrounding links and text in a
search engine result set to expand user queries with a
variable number of keywords in two manners. Positive
expansion adds terms to a user's keywords with a
Boolean ``and,'' negative expansion adds terms to the
user's keywords with a Boolean ``not.'' Each algorithm
was examined for three user groups, high, middle, and
low achievers, who were classified according to their
overall performance. The interactions of users with
different levels of expertise with different expansion
types or algorithms were evaluated. The genetic
algorithm with negative expansion tripled recall and
doubled precision for low achievers, but high achievers
displayed an opposed trend and seemed to be hindered in
this condition. The effect of other conditions was less
substantial.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bolchini:2003:LPD,
author = "Cristiana Bolchini and Fabio Salice and Fabio A.
Schreiber and Letizia Tanca",
title = "Logical and physical design issues for smart card
databases",
journal = j-TOIS,
volume = "21",
number = "3",
pages = "254--285",
month = jul,
year = "2003",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/858476.858478",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:24:06 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The design of very small databases for smart cards and
for portable embedded systems is deeply constrained by
the peculiar features of the physical medium. We
propose a joint approach to the logical and physical
database design phases and evaluate several data
structures with respect to the performance, power
consumption, and endurance parameters of read/program
operations on the Flash-EEPROM storage medium.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Upstill:2003:QIE,
author = "Trystan Upstill and Nick Craswell and David Hawking",
title = "Query-independent evidence in home page finding",
journal = j-TOIS,
volume = "21",
number = "3",
pages = "286--313",
month = jul,
year = "2003",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/858476.858479",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:24:06 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Hyperlink recommendation evidence, that is, evidence
based on the structure of a web's link graph, is widely
exploited by commercial Web search systems. However
there is little published work to support its
popularity. Another form of query-independent evidence,
URL-type, has been shown to be beneficial on a home
page finding task. We compared the usefulness of these
types of evidence on the home page finding task,
combined with both content and anchor text baselines.
Our experiments made use of five query sets spanning
three corpora---one enterprise crawl, and the WT10g and
VLC2 Web test collections.We found that, in optimal
conditions, all of the query-independent methods
studied (in-degree, URL-type, and two variants of
PageRank) offered a better than random improvement on a
content-only baseline. However, only URL-type offered a
better than random improvement on an anchor text
baseline. In realistic settings, for either baseline,
only URL-type offered consistent gains. In combination
with URL-type the anchor text baseline was more useful
for finding popular home pages, but URL-type with
content was more useful for finding randomly selected
home pages. We conclude that a general home page
finding system should combine evidence from document
content, anchor text, and URL-type classification.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Turney:2003:MPC,
author = "Peter D. Turney and Michael L. Littman",
title = "Measuring praise and criticism: {Inference} of
semantic orientation from association",
journal = j-TOIS,
volume = "21",
number = "4",
pages = "315--346",
month = oct,
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri Oct 31 06:13:42 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chang:2003:MME,
author = "Edward Chang and Beitao Li",
title = "{MEGA}---the maximizing expected generalization
algorithm for learning complex query concepts",
journal = j-TOIS,
volume = "21",
number = "4",
pages = "347--382",
month = oct,
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri Oct 31 06:13:42 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Eastman:2003:CRR,
author = "Caroline M. Eastman and Bernard J. Jansen",
title = "Coverage, relevance, and ranking: {The} impact of
query operators on {Web} search engine results",
journal = j-TOIS,
volume = "21",
number = "4",
pages = "383--411",
month = oct,
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri Oct 31 06:13:42 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Powell:2003:CPC,
author = "Allison L. Powell and James C. French",
title = "Comparing the performance of collection selection
algorithms",
journal = j-TOIS,
volume = "21",
number = "4",
pages = "412--456",
month = oct,
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri Oct 31 06:13:42 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Si:2003:SLM,
author = "Luo Si and Jamie Callan",
title = "A semisupervised learning method to merge search
engine results",
journal = j-TOIS,
volume = "21",
number = "4",
pages = "457--491",
month = oct,
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri Oct 31 06:13:42 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Staff:2003:TR,
author = "{ACM Transactions on Information Systems Staff}",
title = "{TOIS} reviewers",
journal = j-TOIS,
volume = "21",
number = "4",
pages = "492--493",
month = oct,
year = "2003",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri Oct 31 06:13:42 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Konstan:2004:IRS,
author = "Joseph A. Konstan",
title = "Introduction to recommender systems: Algorithms and
Evaluation",
journal = j-TOIS,
volume = "22",
number = "1",
pages = "1--4",
month = jan,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sun Jan 11 10:24:10 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Herlocker:2004:ECF,
author = "Jonathan L. Herlocker and Joseph A. Konstan and Loren
G. Terveen and John T. Riedl",
title = "Evaluating collaborative filtering recommender
systems",
journal = j-TOIS,
volume = "22",
number = "1",
pages = "5--53",
month = jan,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sun Jan 11 10:24:10 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Middleton:2004:OUP,
author = "Stuart E. Middleton and Nigel R. Shadbolt and David C.
De Roure",
title = "Ontological user profiling in recommender systems",
journal = j-TOIS,
volume = "22",
number = "1",
pages = "54--88",
month = jan,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sun Jan 11 10:24:10 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hofmann:2004:LSM,
author = "Thomas Hofmann",
title = "Latent semantic models for collaborative filtering",
journal = j-TOIS,
volume = "22",
number = "1",
pages = "89--115",
month = jan,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sun Jan 11 10:24:10 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Huang:2004:AAR,
author = "Zan Huang and Hsinchun Chen and Daniel Zeng",
title = "Applying associative retrieval techniques to alleviate
the sparsity problem in collaborative filtering",
journal = j-TOIS,
volume = "22",
number = "1",
pages = "116--142",
month = jan,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sun Jan 11 10:24:10 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Deshpande:2004:IBT,
author = "Mukund Deshpande and George Karypis",
title = "Item-based top-{$N$} recommendation algorithms",
journal = j-TOIS,
volume = "22",
number = "1",
pages = "143--177",
month = jan,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sun Jan 11 10:24:10 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhai:2004:SSM,
author = "Chengxiang Zhai and John Lafferty",
title = "A study of smoothing methods for language models
applied to information retrieval",
journal = j-TOIS,
volume = "22",
number = "2",
pages = "179--214",
month = apr,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Mana-Lopez:2004:MSA,
author = "Manuel J. Ma{\~n}a-L{\'o}pez and Manuel {De Buenaga}
and Jos{\'e} M. G{\'o}mez-Hidalgo",
title = "Multidocument summarization: an added value to
clustering in interactive retrieval",
journal = j-TOIS,
volume = "22",
number = "2",
pages = "215--241",
month = apr,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lu:2004:ATM,
author = "Wen-Hsiang Lu and Lee-Feng Chien and Hsi-Jian Lee",
title = "Anchor text mining for translation of {Web} queries:
{A} transitive translation approach",
journal = j-TOIS,
volume = "22",
number = "2",
pages = "242--269",
month = apr,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Goncalves:2004:SSS,
author = "Marcos Andr{\'e} Gon{\c{c}}alves and Edward A. Fox and
Layne T. Watson and Neill A. Kipp",
title = "Streams, structures, spaces, scenarios, societies
(5s): a formal model for digital libraries",
journal = j-TOIS,
volume = "22",
number = "2",
pages = "270--312",
month = apr,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Fuhr:2004:XXQ,
author = "Norbert Fuhr and Kai Gro{\ss}johann",
title = "{XIRQL}: {An XML} query language based on information
retrieval concepts",
journal = j-TOIS,
volume = "22",
number = "2",
pages = "313--356",
month = apr,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bodoff:2004:RMH,
author = "David Bodoff",
title = "Relevance models to help estimate document and query
parameters",
journal = j-TOIS,
volume = "22",
number = "3",
pages = "357--380",
month = jul,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wu:2004:EMB,
author = "Xindong Wu and Chengqi Zhang and Shichao Zhang",
title = "Efficient mining of both positive and negative
association rules",
journal = j-TOIS,
volume = "22",
number = "3",
pages = "381--405",
month = jul,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Gladney:2004:TYD,
author = "Henry M. Gladney",
title = "Trustworthy 100-year digital objects: {Evidence} after
every witness is dead",
journal = j-TOIS,
volume = "22",
number = "3",
pages = "406--436",
month = jul,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Miller:2004:PTP,
author = "Bradley N. Miller and Joseph A. Konstan and John
Riedl",
title = "{PocketLens}: {Toward} a personal recommender system",
journal = j-TOIS,
volume = "22",
number = "3",
pages = "437--476",
month = jul,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{King:2004:DCB,
author = "Irwin King and Cheuk Hang Ng and Ka Cheung Sia",
title = "Distributed content-based visual information retrieval
system on peer-to-peer networks",
journal = j-TOIS,
volume = "22",
number = "3",
pages = "477--501",
month = jul,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Brafman:2004:QDM,
author = "Ronen I. Brafman and Carmel Domshlak and Solomon E.
Shimony",
title = "Qualitative decision making in adaptive presentation
of structured information",
journal = j-TOIS,
volume = "22",
number = "4",
pages = "503--539",
month = oct,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Park:2004:ALS,
author = "Seung-Taek Park and David M. Pennock and C. Lee Giles
and Robert Krovetz",
title = "Analysis of lexical signatures for improving
information persistence on the {World Wide Web}",
journal = j-TOIS,
volume = "22",
number = "4",
pages = "540--572",
month = oct,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Williams:2004:FPQ,
author = "Hugh E. Williams and Justin Zobel and Dirk Bahle",
title = "Fast phrase querying with combined indexes",
journal = j-TOIS,
volume = "22",
number = "4",
pages = "573--594",
month = oct,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Park:2004:ISI,
author = "Jinsoo Park and Sudha Ram",
title = "Information systems interoperability: {What} lies
beneath?",
journal = j-TOIS,
volume = "22",
number = "4",
pages = "595--632",
month = oct,
year = "2004",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Nov 4 08:03:37 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Williams:2005:IGI,
author = "Hugh E. Williams",
title = "Introduction to genomic information retrieval",
journal = j-TOIS,
volume = "23",
number = "1",
pages = "1--2",
month = jan,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 12 07:07:01 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Korodi:2005:ENM,
author = "Gergely Korodi and Ioan Tabus",
title = "An efficient normalized maximum likelihood algorithm
for {DNA} sequence compression",
journal = j-TOIS,
volume = "23",
number = "1",
pages = "3--34",
month = jan,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 12 07:07:01 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Sander:2005:MAS,
author = "J{\"o}rg Sander and Raymond T. Ng and Monica C.
Sleumer and Man Saint Yuen and Steven J. Jones",
title = "A methodology for analyzing {SAGE} libraries for
cancer profiling",
journal = j-TOIS,
volume = "23",
number = "1",
pages = "35--60",
month = jan,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 12 07:07:01 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tao:2005:HST,
author = "Yufei Tao and Dimitris Papadias",
title = "Historical spatio-temporal aggregation",
journal = j-TOIS,
volume = "23",
number = "1",
pages = "61--102",
month = jan,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 12 07:07:01 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Adomavicius:2005:ICI,
author = "Gediminas Adomavicius and Ramesh Sankaranarayanan and
Shahana Sen and Alexander Tuzhilin",
title = "Incorporating contextual information in recommender
systems using a multidimensional approach",
journal = j-TOIS,
volume = "23",
number = "1",
pages = "103--145",
month = jan,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 12 07:07:01 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Fox:2005:EIM,
author = "Steve Fox and Kuldeep Karnawat and Mark Mydland and
Susan Dumais and Thomas White",
title = "Evaluating implicit measures to improve {Web} search",
journal = j-TOIS,
volume = "23",
number = "2",
pages = "147--168",
month = apr,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 26 17:34:31 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cooper:2005:AHS,
author = "Brian F. Cooper and Hector Garcia-Molina",
title = "Ad hoc, self-supervising peer-to-peer search
networks",
journal = j-TOIS,
volume = "23",
number = "2",
pages = "169--200",
month = apr,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 26 17:34:31 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Xu:2005:CEF,
author = "Jennifer J. Xu and Hsinchun Chen",
title = "{CrimeNet} explorer: a framework for criminal network
knowledge discovery",
journal = j-TOIS,
volume = "23",
number = "2",
pages = "201--226",
month = apr,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Apr 26 17:34:31 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wei:2005:MBA,
author = "Yan Zheng Wei and Luc Moreau and Nicholas R.
Jennings",
title = "A market-based approach to recommender systems",
journal = j-TOIS,
volume = "23",
number = "3",
pages = "227--266",
month = jul,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Sep 22 11:21:45 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Park:2005:NDR,
author = "Laurence A. F. Park and Kotagiri Ramamohanarao and
Marimuthu Palaniswami",
title = "A novel document retrieval method using the discrete
wavelet transform",
journal = j-TOIS,
volume = "23",
number = "3",
pages = "267--298",
month = jul,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Sep 22 11:21:45 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Gladney:2005:TYD,
author = "H. M. Gladney and R. A. Lorie",
title = "Trustworthy 100-year digital objects: durable encoding
for when it's too late to ask",
journal = j-TOIS,
volume = "23",
number = "3",
pages = "299--324",
month = jul,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Sep 22 11:21:45 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{White:2005:EIF,
author = "Ryen W. White and Ian Ruthven and Joemon M. Jose and
C. J. {Van Rijsbergen}",
title = "Evaluating implicit feedback models using searcher
simulations",
journal = j-TOIS,
volume = "23",
number = "3",
pages = "325--361",
month = jul,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Thu Sep 22 11:21:45 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chuang:2005:TGT,
author = "Shui-Lung Chuang and Lee-Feng Chien",
title = "Taxonomy generation for text segments: a practical
{Web}-based approach",
journal = j-TOIS,
volume = "23",
number = "4",
pages = "363--396",
month = oct,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Oct 25 06:41:53 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Possas:2005:SBV,
author = "Bruno P{\^o}ssas and Nivio Ziviani and Wagner {Meira,
Jr.} and Berthier Ribeiro-Neto",
title = "Set-based vector model: an efficient approach for
correlation-based ranking",
journal = j-TOIS,
volume = "23",
number = "4",
pages = "397--429",
month = oct,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Oct 25 06:41:53 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pant:2005:LCC,
author = "Gautam Pant and Padmini Srinivasan",
title = "Learning to crawl: {Comparing} classification
schemes",
journal = j-TOIS,
volume = "23",
number = "4",
pages = "430--462",
month = oct,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Oct 25 06:41:53 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ivory:2005:EWS,
author = "Melody Y. Ivory and Rodrick Megraw",
title = "Evolution of {Web} site design patterns",
journal = j-TOIS,
volume = "23",
number = "4",
pages = "463--497",
month = oct,
year = "2005",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Tue Oct 25 06:41:53 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zobel:2006:DVS,
author = "J. Zobel",
title = "Detection of video sequences using compact
signatures",
journal = j-TOIS,
volume = "24",
number = "1",
pages = "1--50",
month = jan,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1125857.1125858",
ISSN = "1046-8188",
bibdate = "Sat Apr 22 06:10:51 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Fagni:2006:BPW,
author = "Tiziano Fagni and Raffaele Perego and Fabrizio
Silvestri and Salvatore Orlando",
title = "Boosting the performance of {Web} search engines:
{Caching} and prefetching query results by exploiting
historical usage data",
journal = j-TOIS,
volume = "24",
number = "1",
pages = "51--78",
month = jan,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1125857.1125859",
ISSN = "1046-8188",
bibdate = "Sat Apr 22 06:10:51 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Qian:2006:SPB,
author = "Gang Qian and Qiang Zhu and Qiang Xue and Sakti
Pramanik",
title = "A space-partitioning-based indexing method for
multidimensional non-ordered discrete data spaces",
journal = j-TOIS,
volume = "24",
number = "1",
pages = "79--110",
month = jan,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1125857.1125860",
ISSN = "1046-8188",
bibdate = "Sat Apr 22 06:10:51 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{McDonald:2006:SCS,
author = "Daniel M. McDonald and Hsinchun Chen",
title = "Summary in context: {Searching} versus browsing",
journal = j-TOIS,
volume = "24",
number = "1",
pages = "111--141",
month = jan,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1125857.1125861",
ISSN = "1046-8188",
bibdate = "Sat Apr 22 06:10:51 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Marchionini:2006:TR,
author = "Gary Marchionini",
title = "{TOIS} reviewers 2003--2005",
journal = j-TOIS,
volume = "24",
number = "1",
pages = "142--143",
month = jan,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1125857.1125862",
ISSN = "1046-8188",
bibdate = "Sat Apr 22 06:10:51 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lee:2006:UEF,
author = "Hyowon Lee and Alan F. Smeaton and Noel E. O'Connor
and Barry Smyth",
title = "User evaluation of {F{\'\i}schl{\'a}r-News}: an
automatic broadcast news delivery system",
journal = j-TOIS,
volume = "24",
number = "2",
pages = "145--189",
month = apr,
year = "2006",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Wed Aug 23 09:31:12 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Gao:2006:MFM,
author = "Sheng Gao and Wen Wu and Chin-Hui Lee and Tat-Seng
Chua",
title = "A maximal figure-of-merit {(MFoM)-learning} approach
to robust classifier design for text categorization",
journal = j-TOIS,
volume = "24",
number = "2",
pages = "190--218",
month = apr,
year = "2006",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Wed Aug 23 09:31:12 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhou:2006:ERF,
author = "Zhi-Hua Zhou and Ke-Jia Chen and Hong-Bin Dai",
title = "Enhancing relevance feedback in image retrieval using
unlabeled data",
journal = j-TOIS,
volume = "24",
number = "2",
pages = "219--244",
month = apr,
year = "2006",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Wed Aug 23 09:31:12 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chen:2006:IIV,
author = "Keke Chen and Ling Liu",
title = "{iVIBRATE}: {Interactive} visualization-based
framework for clustering large datasets",
journal = j-TOIS,
volume = "24",
number = "2",
pages = "245--294",
month = apr,
year = "2006",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Wed Aug 23 09:31:12 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Jiang:2006:ECR,
author = "Jing Jiang and Chengxiang Zhai",
title = "Extraction of coherent relevant passages using hidden
{Markov} models",
journal = j-TOIS,
volume = "24",
number = "3",
pages = "295--319",
month = jul,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1165774.1165775",
ISSN = "1046-8188",
bibdate = "Wed Oct 11 07:12:08 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Shen:2006:QEW,
author = "Dou Shen and Rong Pan and Jian-Tao Sun and Jeffrey
Junfeng Pan and Kangheng Wu and Jie Yin and Qiang
Yang",
title = "Query enrichment for web-query classification",
journal = j-TOIS,
volume = "24",
number = "3",
pages = "320--352",
month = jul,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1165774.1165776",
ISSN = "1046-8188",
bibdate = "Wed Oct 11 07:12:08 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tsai:2006:CMS,
author = "Chih-Fong Tsai and Ken McGarry and John Tait",
title = "{CLAIRE}: a modular support vector image indexing and
classification system",
journal = j-TOIS,
volume = "24",
number = "3",
pages = "353--379",
month = jul,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1165774.1165777",
ISSN = "1046-8188",
bibdate = "Wed Oct 11 07:12:08 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yu:2006:LSC,
author = "Hong Yu and Won Kim and Vasileios Hatzivassiloglou and
John Wilbur",
title = "A large scale, corpus-based approach for automatically
disambiguating biomedical abbreviations",
journal = j-TOIS,
volume = "24",
number = "3",
pages = "380--404",
month = jul,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1165774.1165778",
ISSN = "1046-8188",
bibdate = "Wed Oct 11 07:12:08 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Abbreviations and acronyms are widely used in the
biomedical literature and many of them represent
important biomedical concepts. Because many
abbreviations are ambiguous (e.g., CAT denotes both
chloramphenicol acetyl transferase and computed axial
tomography, depending on the context), recognizing the
full form associated with each abbreviation is in most
cases equivalent to identifying the meaning of the
abbreviation. This, in turn, allows us to perform more
accurate natural language processing, information
extraction, and retrieval. In this study, we have
developed supervised approaches to identifying the full
forms of ambiguous abbreviations within the context
they appear. We first automatically assigned multiple
possible full forms for each abbreviation; we then
treated the in-context full-form prediction for each
specific abbreviation occurrence as a case of
word-sense disambiguation. We generated automatically a
dictionary of all possible full forms for each
abbreviation. We applied supervised machine-learning
algorithms for disambiguation. Because some of the
links between abbreviations and their corresponding
full forms are explicitly given in the text and can be
recovered automatically, we can use these explicit
links to automatically provide training data for
disambiguating the abbreviations that are not linked to
a full form within a text. We evaluated our methods on
over 150 thousand abstracts and obtain for coverage and
precision results of 82\% and 92\%, respectively, when
performed as tenfold cross-validation, and 79\% and
80\%, respectively, when evaluated against an external
set of abstracts in which the abbreviations are not
defined.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Baeza-Yates:2006:ISI,
author = "Ricardo Baeza-Yates and Norbert Fuhr and Yoelle
Maarek",
title = "Introduction to the special issue on {XML} retrieval",
journal = j-TOIS,
volume = "24",
number = "4",
pages = "405--406",
month = oct,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1185877.1185878",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:35 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Kamps:2006:AIN,
author = "Jaap Kamps and Maarten Marx and Maarten de Rijke and
B{\"o}rkur Sigurbj{\"o}rnsson",
title = "Articulating information needs in {XML} query
languages",
journal = j-TOIS,
volume = "24",
number = "4",
pages = "407--436",
month = oct,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1185877.1185879",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:35 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Document-centric XML is a mixture of text and
structure. With the increased availability of
document-centric XML documents comes a need for query
facilities in which both structural constraints and
constraints on the content of the documents can be
expressed. How does the expressiveness of languages for
querying XML documents help users to express their
information needs? We address this question from both
an experimental and a theoretical point of view. Our
experimental analysis compares a structure-ignorant
with a structure-aware retrieval approach using the
test suite of the INEX XML Retrieval Evaluation
Initiative. Theoretically, we create two mathematical
models of users' knowledge of a set of documents and
define query languages which exactly fit these models.
One of these languages corresponds to an XML version of
fielded search, the other to the INEX query language.
Our main experimental findings are: First, while
structure is used in varying degrees of complexity,
two-thirds of the queries can be expressed in a
fielded-search-like format which does not use the
hierarchical structure of the documents. Second,
three-quarters of the queries use constraints on the
context of the elements to be returned; these
contextual constraints cannot be captured by ordinary
keyword queries. Third, structure is used as a search
hint, and not as a strict requirement, when judged
against the underlying information need. Fourth, the
use of structure in queries functions as a precision
enhancing device.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Full-text XML querying; XML retrieval; XPath",
}
@Article{Crouch:2006:DER,
author = "Carolyn J. Crouch",
title = "Dynamic element retrieval in a structured
environment",
journal = j-TOIS,
volume = "24",
number = "4",
pages = "437--454",
month = oct,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1185877.1185880",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:35 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This research examines the feasibility of dynamic
element retrieval in a structured environment.
Structured documents and queries are represented in
extended vector form, based on a modification of the
basic vector space model suggested by Fox [1983]. A
method for the dynamic retrieval of XML elements, which
requires only a single indexing of the documents at the
level of the basic indexing node, is presented. This
method, which we refer to as flexible retrieval,
produces a rank ordered list of retrieved elements that
is equivalent to the result produced by the same
retrieval against an all-element index of the
collection. Flexible retrieval obviates the need for
storing either an all-element index or multiple indices
of the collection.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "dynamic element retrieval; flexible retrieval;
structured retrieval; vector space model; XML",
}
@Article{Lehtonen:2006:PHX,
author = "Miro Lehtonen",
title = "Preparing heterogeneous {XML} for full-text search",
journal = j-TOIS,
volume = "24",
number = "4",
pages = "455--474",
month = oct,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1185877.1185881",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:35 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "XML retrieval is facing new challenges when applied to
heterogeneous XML documents, where next to nothing
about the document structure can be taken for granted.
We have developed solutions where some of the
heterogeneity issues are addressed. Our fragment
selection algorithm selectively divides a heterogeneous
document collection into equi-sized fragments with
full-text content. If the content is considered too
data-oriented, it is not accepted. The algorithm needs
no information about element names. In addition, three
techniques for fragment expansion are presented, all of
which yield a 13--17\% average improvement in average
precision. These techniques and algorithms are among
the first steps in developing document-type-independent
indexing methods for the full text in heterogeneous XML
collections.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "heterogeneous documents; indexing; XML retrieval",
}
@Article{Geneves:2006:SSA,
author = "Pierre Genev{\`e}s and Nabil Laya{\"\i}da",
title = "A system for the static analysis of {XPath}",
journal = j-TOIS,
volume = "24",
number = "4",
pages = "475--502",
month = oct,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1185877.1185882",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:35 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "XPath is the standard language for navigating XML
documents and returning a set of matching nodes. We
present a sound and complete decision procedure for
containment of XPath queries, as well as other related
XPath decision problems such as satisfiability,
equivalence, overlap, and coverage. The considered
XPath fragment covers most of the language features
used in practice. Specifically, we propose a unifying
logic for XML, namely, the alternation-free modal
$\mu$-calculus with converse. We show how to translate
major XML concepts such as XPath and regular XML types
(including DTDs) into this logic. Based on these
embeddings, we show how XPath decision problems, in the
presence or absence of XML types, can be solved using a
decision procedure for $\mu$-calculus satisfiability.
We provide a complexity analysis of our system together
with practical experiments to illustrate the efficiency
of the approach for realistic scenarios.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Containment; equivalence; logic; query; XML; XPath",
}
@Article{Kazai:2006:ECG,
author = "Gabriella Kazai and Mounia Lalmas",
title = "{eXtended} cumulated gain measures for the evaluation
of content-oriented {XML} retrieval",
journal = j-TOIS,
volume = "24",
number = "4",
pages = "503--542",
month = oct,
year = "2006",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1185877.1185883",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:35 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We propose and evaluate a family of measures, the
eXtended Cumulated Gain (XCG) measures, for the
evaluation of content-oriented XML retrieval
approaches. Our aim is to provide an evaluation
framework that allows the consideration of dependency
among XML document components. In particular, two
aspects of dependency are considered: (1) near-misses,
which are document components that are structurally
related to relevant components, such as a neighboring
paragraph or container section, and (2) overlap, which
regards the situation wherein the same text fragment is
referenced multiple times, for example, when a
paragraph and its container section are both retrieved.
A further consideration is that the measures should be
flexible enough so that different models of user
behavior may be instantiated within. Both system- and
user-oriented aspects are investigated and both recall
and precision-like qualities are measured. We evaluate
the reliability of the proposed measures based on the
INEX 2004 test collection. For example, the effects of
assessment variation and topic set size on evaluation
stability are investigated, and the upper and lower
bounds of expected error rates are established. The
evaluation demonstrates that the XCG measures are
stable and reliable, and in particular, that the novel
measures of effort-precision and gain-recall ( ep / gr
) show comparable behavior to established IR measures
like precision and recall.",
acknowledgement = ack-nhfb,
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "cumulated gain; dependency; evaluation; INEX; metrics;
near-miss; overlap; XML retrieval",
}
@Article{Piwowarski:2007:PRU,
author = "B. Piwowarski and P. Gallinari and G. Dupret",
title = "Precision recall with user modeling {(PRUM)}:
{Application} to structured information retrieval",
journal = j-TOIS,
volume = "25",
number = "1",
pages = "1:1--1:??",
month = feb,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1198296.1198297",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:47 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Standard Information Retrieval (IR) metrics are not
well suited for new paradigms like XML or Web IR in
which retrievable information units are document
elements and/or sets of related documents. Part of the
problem stems from the classical hypotheses on the user
models: They do not take into account the structural or
logical context of document elements or the possibility
of navigation between units. This article proposes an
explicit and formal user model that encompasses a large
variety of user behaviors. Based on this model, we
extend the probabilistic precision-recall metric to
deal with the new IR paradigms.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Evaluation; information retrieval; measure;
precision-recall; Web; XML",
}
@Article{Lam:2007:NET,
author = "Wai Lam and Shing-Kit Chan and Ruizhang Huang",
title = "Named entity translation matching and learning: {With}
application for mining unseen translations",
journal = j-TOIS,
volume = "25",
number = "1",
pages = "2:1--2:??",
month = feb,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1198296.1198298",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:47 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article introduces a named entity matching model
that makes use of both semantic and phonetic evidence.
The matching of semantic and phonetic information is
captured by a unified framework via a bipartite graph
model. By considering various technical challenges of
the problem, including order insensitivity and partial
matching, this approach is less rigid than existing
approaches and highly robust. One major component is a
phonetic matching model which exploits similarity at
the phoneme level. Two learning algorithms for learning
the similarity information of basic phonemic matching
units based on training examples are investigated. By
applying the proposed named entity matching model, a
mining system is developed for discovering new named
entity translations from daily Web news. The system is
able to discover new name translations that cannot be
found in the existing bilingual dictionary.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "learning phonetic information; named entity
translation; Text mining",
}
@Article{Chai:2007:EIU,
author = "Joyce Y. Chai and Chen Zhang and Rong Jin",
title = "An empirical investigation of user term feedback in
text-based targeted image search",
journal = j-TOIS,
volume = "25",
number = "1",
pages = "3:1--3:??",
month = feb,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1198296.1198299",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:47 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Text queries are natural and intuitive for users to
describe their information needs. However, text-based
image retrieval faces many challenges. Traditional text
retrieval techniques on image descriptions have not
been very successful. This is mainly due to the
inconsistent textual descriptions and the discrepancies
between user queries and terms in the descriptions. To
investigate strategies to alleviate this vocabulary
problem, this article examines the role of user term
feedback in targeted image search that is based on
text-based image retrieval. Term feedback refers to the
feedback from a user on specific terms regarding their
relevance to a target image. Previous studies have
indicated the effectiveness of term feedback in
interactive text retrieval. However, in our experiments
on text-based image retrieval, the term feedback has
not been shown to be effective. Our results indicate
that, although term feedback has a positive effect by
allowing users to identify more relevant terms, it also
has a strong negative effect by providing more
opportunities for users to specify irrelevant terms. To
understand these different effects and their
implications, this article further analyzes important
factors that contribute to the utility of term feedback
and discusses the outlook of term feedback in
interactive text-based image retrieval.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Text-based interactive image retrieval; user term
feedback",
}
@Article{Talvensaari:2007:CEC,
author = "Tuomas Talvensaari and Jorma Laurikkala and Kalervo
J{\"a}rvelin and Martti Juhola and Heikki Keskustalo",
title = "Creating and exploiting a comparable corpus in
cross-language information retrieval",
journal = j-TOIS,
volume = "25",
number = "1",
pages = "4:1--4:??",
month = feb,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1198296.1198300",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:47 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We present a method for creating a comparable text
corpus from two document collections in different
languages. The collections can be very different in
origin. In this study, we build a comparable corpus
from articles by a Swedish news agency and a U.S.
newspaper. The keys with best resolution power were
extracted from the documents of one collection, the
source collection, by using the relative average term
frequency (RATF) value. The keys were translated into
the language of the other collection, the target
collection, with a dictionary-based query translation
program. The translated queries were run against the
target collection and an alignment pair was made if the
retrieved documents matched given date and similarity
score criteria. The resulting comparable collection was
used as a similarity thesaurus to translate queries
along with a dictionary-based translator. The combined
approaches outperformed translation schemes where
dictionary-based translation or corpus translation was
used alone.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "comparable corpora; Cross-language information
retrieval; query translation",
}
@Article{Ma:2007:IBP,
author = "Zhongming Ma and Gautam Pant and Olivia R. Liu Sheng",
title = "Interest-based personalized search",
journal = j-TOIS,
volume = "25",
number = "1",
pages = "5:1--5:??",
month = feb,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1198296.1198301",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:47 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Web search engines typically provide search results
without considering user interests or context. We
propose a personalized search approach that can easily
extend a conventional search engine on the client side.
Our mapping framework automatically maps a set of known
user interests onto a group of categories in the Open
Directory Project (ODP) and takes advantage of manually
edited data available in ODP for training text
classifiers that correspond to, and therefore
categorize and personalize search results according to
user interests. In two sets of controlled experiments,
we compare our personalized categorization system
(PCAT) with a list interface system (LIST) that mimics
a typical search engine and with a nonpersonalized
categorization system (CAT). In both experiments, we
analyze system performances on the basis of the type of
task and query length. We find that PCAT is preferable
to LIST for information gathering types of tasks and
for searches with short queries, and PCAT outperforms
CAT in both information gathering and finding types of
tasks, and for searches associated with free-form
queries. From the subjects' answers to a questionnaire,
we find that PCAT is perceived as a system that can
find relevant Web pages quicker and easier than LIST
and CAT.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "information retrieval; Open Directory; Personalized
search; user interest; user interface; World Wide Web",
}
@Article{Lin:2007:EPU,
author = "Jimmy Lin",
title = "An exploration of the principles underlying
redundancy-based factoid question answering",
journal = j-TOIS,
volume = "25",
number = "2",
pages = "6:1--6:??",
month = apr,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1229179.1229180",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The so-called ``redundancy-based'' approach to
question answering represents a successful strategy for
mining answers to factoid questions such as ``Who shot
Abraham Lincoln?'' from the World Wide Web. Through
contrastive and ablation experiments with Aranea, a
system that has performed well in several TREC QA
evaluations, this work examines the underlying
assumptions and principles behind redundancy-based
techniques. Specifically, we develop two theses: that
stable characteristics of data redundancy allow factoid
systems to rely on external ``black box'' components,
and that despite embodying a data-driven approach,
redundancy-based methods encode a substantial amount of
knowledge in the form of heuristics. Overall, this work
attempts to address the broader question of ``what
really matters'' and to provide guidance for future
researchers.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Data redundancy; Web search",
}
@Article{Joachims:2007:EAI,
author = "Thorsten Joachims and Laura Granka and Bing Pan and
Helene Hembrooke and Filip Radlinski and Geri Gay",
title = "Evaluating the accuracy of implicit feedback from
clicks and query reformulations in {Web} search",
journal = j-TOIS,
volume = "25",
number = "2",
pages = "7:1--7:??",
month = apr,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1229179.1229181",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article examines the reliability of implicit
feedback generated from clickthrough data and query
reformulations in World Wide Web (WWW) search.
Analyzing the users' decision process using eyetracking
and comparing implicit feedback against manual
relevance judgments, we conclude that clicks are
informative but biased. While this makes the
interpretation of clicks as absolute relevance
judgments difficult, we show that relative preferences
derived from clicks are reasonably accurate on average.
We find that such relative preferences are accurate not
only between results from an individual query, but
across multiple sets of results within chains of query
reformulations.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Clickthrough data; eye-tracking; implicit feedback;
query reformulations; user studies",
}
@Article{Cui:2007:SPM,
author = "Hang Cui and Min-Yen Kan and Tat-Seng Chua",
title = "Soft pattern matching models for definitional question
answering",
journal = j-TOIS,
volume = "25",
number = "2",
pages = "8:1--8:??",
month = apr,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1229179.1229182",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We explore probabilistic lexico-syntactic pattern
matching, also known as soft pattern matching, in a
definitional question answering system. Most current
systems use regular expression-based hard matching
patterns to identify definition sentences. Such rigid
surface matching often fares poorly when faced with
language variations. We propose two soft matching
models to address this problem: one based on bigrams
and the other on the Profile Hidden Markov Model
(PHMM). Both models provide a theoretically sound
method to model pattern matching as a probabilistic
process that generates token sequences. We demonstrate
the effectiveness of the models on definition sentence
retrieval for definitional question answering. We show
that both models significantly outperform the
state-of-the-art manually constructed hard matching
patterns on recent TREC data.\par
A critical difference between the two models is that
the PHMM has a more complex topology. We experimentally
show that the PHMM can handle language variations more
effectively but requires more training data to
converge.\par
While we evaluate soft pattern models only on
definitional question answering, we believe that both
models are generic and can be extended to other areas
where lexico-syntactic pattern matching can be
applied.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "definitional question answering; Soft patterns",
}
@Article{Beitzel:2007:ACW,
author = "Steven M. Beitzel and Eric C. Jensen and David D.
Lewis and Abdur Chowdhury and Ophir Frieder",
title = "Automatic classification of {Web} queries using very
large unlabeled query logs",
journal = j-TOIS,
volume = "25",
number = "2",
pages = "9:1--9:??",
month = apr,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1229179.1229183",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:51:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Accurate topical classification of user queries allows
for increased effectiveness and efficiency in
general-purpose Web search systems. Such classification
becomes critical if the system must route queries to a
subset of topic-specific and resource-constrained
back-end databases. Successful query classification
poses a challenging problem, as Web queries are short,
thus providing few features. This feature sparseness,
coupled with the constantly changing distribution and
vocabulary of queries, hinders traditional text
classification. We attack this problem by combining
multiple classifiers, including exact lookup and
partial matching in databases of manually classified
frequent queries, linear models trained by supervised
learning, and a novel approach based on mining
selectional preferences from a large unlabeled query
log. Our approach classifies queries without using
external sources of information, such as online Web
directories or the contents of retrieved pages, making
it viable for use in demanding operational
environments, such as large-scale Web search services.
We evaluate our approach using a large sample of
queries from an operational Web search engine and show
that our combined method increases recall by nearly
40\% over the best single method while maintaining
adequate precision. Additionally, we compare our
results to those from the 2005 KDD Cup and find that we
perform competitively despite our operational
restrictions. This suggests it is possible to topically
classify a significant portion of the query stream
without requiring external sources of information,
allowing for deployment in operationally restricted
environments.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Baralis:2007:AXQ,
author = "Elena Baralis and Paolo Garza and Elisa Quintarelli
and Letizia Tanca",
title = "Answering {XML} queries by means of data summaries",
journal = j-TOIS,
volume = "25",
number = "3",
pages = "10:1--10:??",
month = jul,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1247715.1247716",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:07 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "XML is a rather verbose representation of
semistructured data, which may require huge amounts of
storage space. We propose a summarized representation
of XML data, based on the concept of instance pattern,
which can both provide succinct information and be
directly queried. The physical representation of
instance patterns exploits itemsets or association
rules to summarize the content of XML datasets.
Instance patterns may be used for (possibly partially)
answering queries, either when fast and approximate
answers are required, or when the actual dataset is not
available, for example, it is currently unreachable.
Experiments on large XML documents show that instance
patterns allow a significant reduction in storage
space, while preserving almost entirely the
completeness of the query result. Furthermore, they
provide fast query answers and show good scalability on
the size of the dataset, thus overcoming the document
size limitation of most current XQuery engines.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Association rules; data mining; data summarization;
intensional answers; itemsets; semistructured data",
}
@Article{Cormack:2007:OSS,
author = "Gordon V. Cormack and Thomas R. Lynam",
title = "Online supervised spam filter evaluation",
journal = j-TOIS,
volume = "25",
number = "3",
pages = "11:1--11:??",
month = jul,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1247715.1247717",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:07 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Eleven variants of six widely used open-source spam
filters are tested on a chronological sequence of 49086
e-mail messages received by an individual from August
2003 through March 2004. Our approach differs from
those previously reported in that the test set is
large, comprises uncensored raw messages, and is
presented to each filter sequentially with incremental
feedback. Misclassification rates and Receiver
Operating Characteristic Curve measurements are
reported, with statistical confidence intervals.
Quantitative results indicate that content-based
filters can eliminate 98\% of spam while incurring
0.1\% legitimate email loss. Qualitative results
indicate that the risk of loss depends on the nature of
the message, and that messages likely to be lost may be
those that are less critical. More generally, our
methodology has been encapsulated in a free software
toolkit, which may used to conduct similar
experiments.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "email; Spam; text classification",
}
@Article{Zhou:2007:DPM,
author = "Changqing Zhou and Dan Frankowski and Pamela Ludford
and Shashi Shekhar and Loren Terveen",
title = "Discovering personally meaningful places: an
interactive clustering approach",
journal = j-TOIS,
volume = "25",
number = "3",
pages = "12:1--12:??",
month = jul,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1247715.1247718",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:07 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The discovery of a person's meaningful places involves
obtaining the physical locations and their labels for a
person's places that matter to his daily life and
routines. This problem is driven by the requirements
from emerging location-aware applications, which allow
a user to pose queries and obtain information in
reference to places, for example, ``home'', ``work'' or
``Northwest Health Club''. It is a challenge to map
from physical locations to personally meaningful places
due to a lack of understanding of what constitutes the
real users' personally meaningful places. Previous work
has explored algorithms to discover personal places
from location data. However, we know of no systematic
empirical evaluations of these algorithms, leaving
designers of location-aware applications in the dark
about their choices.\par Our work remedies this
situation. We extended a clustering algorithm to
discover places. We also defined a set of essential
evaluation metrics and an interactive evaluation
framework. We then conducted a large-scale experiment
that collected real users' location data and personally
meaningful places, and illustrated the utility of our
evaluation framework. Our results establish a baseline
that future work can measure itself against. They also
demonstrate that our algorithm discovers places with
reasonable accuracy and outperforms the well-known
K-Means clustering algorithm for place discovery.
Finally, we provide evidence that shapes more complex
than ``points'' are required to represent the full
range of people's everyday places.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "clustering algorithms; field studies; location-aware
applications; place discovery; Ubiquitous computing",
}
@Article{He:2007:SHP,
author = "Ben He and Iadh Ounis",
title = "On setting the hyper-parameters of term frequency
normalization for information retrieval",
journal = j-TOIS,
volume = "25",
number = "3",
pages = "13:1--13:??",
month = jul,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1247715.1247719",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:07 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The setting of the term frequency normalization
hyper-parameter suffers from the query dependence and
collection dependence problems, which remarkably hurt
the robustness of the retrieval performance. Our study
in this article investigates three term frequency
normalization methods, namely normalization 2, BM25's
normalization and the Dirichlet Priors normalization.
We tackle the query dependence problem by modifying the
query term weight using a Divergence From Randomness
term weighting model, and tackle the collection
dependence problem by measuring the correlation of the
normalized term frequency with the document length. Our
research hypotheses for the two problems, as well as an
automatic hyper-parameter setting methodology, are
extensively validated and evaluated on four Text
REtrieval Conference (TREC) collections.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "collection-dependence; information retrieval models;
Query-dependence; relevance feedback; term frequency
normalization; TREC experimentation",
}
@Article{Jones:2007:TPQ,
author = "Rosie Jones and Fernando Diaz",
title = "Temporal profiles of queries",
journal = j-TOIS,
volume = "25",
number = "3",
pages = "14:1--14:??",
month = jul,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1247715.1247720",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:07 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Documents with timestamps, such as email and news, can
be placed along a timeline. The timeline for a set of
documents returned in response to a query gives an
indication of how documents relevant to that query are
distributed in time. Examining the timeline of a query
result set allows us to characterize both how
temporally dependent the topic is, as well as how
relevant the results are likely to be. We outline
characteristic patterns in query result set timelines,
and show experimentally that we can automatically
classify documents into these classes. We also show
that properties of the query result set timeline can
help predict the mean average precision of a query.
These results show that meta-features associated with a
query can be combined with text retrieval techniques to
improve our understanding and treatment of text search
on documents with timestamps.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "ambiguity; event detection; language models; precision
prediction; query classification; temporal profiles;
Time",
}
@Article{Marchionini:2007:TRJ,
author = "Gary Marchionini",
title = "{TOIS} reviewers {January} 2006 through {May} 2007",
journal = j-TOIS,
volume = "25",
number = "4",
pages = "15:1--15:??",
month = oct,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1281485.1281486",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:16 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bailey:2007:AHT,
author = "Christopher Bailey and Wendy Hall and David E. Millard
and Mark J. Weal",
title = "Adaptive hypermedia through contextualized open
hypermedia structures",
journal = j-TOIS,
volume = "25",
number = "4",
pages = "16:1--16:??",
month = oct,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1281485.1281487",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:16 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The aim of this article is to produce an alternative
view of the adaptive hypermedia (AH) domain from a
contextually-aware open hypermedia (OH) perspective. We
believe that a wide range of AH techniques can be
supported with a small number of OH structures, which
can be combined together to create more complex
effects, possibly simplifying the development of new AH
systems.\par
In this work we reexamine Brusilovsky's taxonomy of AH
techniques from a structural OH perspective. We also
show that it is possible to identify and model common
structures across the taxonomy of adaptive techniques.
An agent-based adaptive hypermedia system called HA 3 L
is presented, which uses these OH structures to provide
a straightforward implementation of a variety of
adaptive hypermedia techniques. This enables us to
reflect on the structural equivalence of many of the
techniques, demonstrates the advantages of the OH
approach, and can inform the design of future adaptive
hypermedia systems.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "adaptive hypermedia; Adaptive techniques; FOHM;
hypermedia structure; open hypermedia",
}
@Article{Fang:2007:SMT,
author = "Xiao Fang and Olivia R. Liu Sheng and Michael Chau",
title = "{ServiceFinder}: a method towards enhancing service
portals",
journal = j-TOIS,
volume = "25",
number = "4",
pages = "17:1--17:??",
month = oct,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1281485.1281488",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:16 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The rapid advancement of Internet technologies enables
more and more educational institutes, companies, and
government agencies to provide services, namely online
services, through web portals. With hundreds of online
services provided through a web portal, it is critical
to design web portals, namely service portals, through
which online services can be easily accessed by their
consumers. This article addresses this critical issue
from the perspective of service selection, that is, how
to select a small number of service-links (i.e.,
hyperlinks pointing to online services) to be featured
in the homepage of a service portal such that users can
be directed to find the online services they seek most
effectively. We propose a mathematically formulated
metric to measure the effectiveness of the selected
service-links in directing users to locate their
desired online services and formally define the service
selection problem. A solution method, ServiceFinder, is
then proposed. Using real-world data obtained from the
Utah State Government service portal, we show that
ServiceFinder outperforms both the current practice of
service selection and previous algorithms for adaptive
website design. We also show that the performance of
ServiceFinder is close to that of the optimal solution
resulting from exhaustive search.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "online service; Service portal; service selection",
}
@Article{Majumder:2007:YYA,
author = "Prasenjit Majumder and Mandar Mitra and Swapan K.
Parui and Gobinda Kole and Pabitra Mitra and
Kalyankumar Datta",
title = "{YASS}: {Yet} another suffix stripper",
journal = j-TOIS,
volume = "25",
number = "4",
pages = "18:1--18:??",
month = oct,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1281485.1281489",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:16 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Stemmers attempt to reduce a word to its stem or root
form and are used widely in information retrieval tasks
to increase the recall rate. Most popular stemmers
encode a large number of language-specific rules built
over a length of time. Such stemmers with comprehensive
rules are available only for a few languages. In the
absence of extensive linguistic resources for certain
languages, statistical language processing tools have
been successfully used to improve the performance of IR
systems. In this article, we describe a
clustering-based approach to discover equivalence
classes of root words and their morphological variants.
A set of string distance measures are defined, and the
lexicon for a given text collection is clustered using
the distance measures to identify these equivalence
classes. The proposed approach is compared with
Porter's and Lovin's stemmers on the AP and WSJ
subcollections of the Tipster dataset using 200
queries. Its performance is comparable to that of
Porter's and Lovin's stemmers, both in terms of average
precision and the total number of relevant documents
retrieved. The proposed stemming algorithm also
provides consistent improvements in retrieval
performance for French and Bengali, which are currently
resource-poor.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Bengali; clustering; corpus; French; Indian languages;
stemming; string similarity",
}
@Article{Pinto:2007:NXM,
author = "Alberto Pinto and Goffredo Haus",
title = "A novel {XML} music information retrieval method using
graph invariants",
journal = j-TOIS,
volume = "25",
number = "4",
pages = "19:1--19:??",
month = oct,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1281485.1281490",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:16 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The increasing diffusion of XML languages for the
encoding of domain-specific multimedia information
raises the need for new information retrieval models
that can fully exploit structural information. An XML
language specifically designed for music like MX allows
queries to be made directly on the thematic material.
The main advantage of such a system is that it can
handle symbolic, notational, and audio objects at the
same time through a multilayered structure. On the
model side, common music information retrieval methods
do not take into account the inner structure of melodic
themes and the metric relationships between
notes.\par
In this article we deal with two main topics: a novel
architecture based on a new XML language for music and
a new model of melodic themes based on graph
theory.\par
This model takes advantage of particular graph
invariants that can be linked to melodic themes as
metadata in order to characterize all their possible
modifications through specific transformations and that
can be exploited in filtering algorithms. We provide a
similarity function and show through an evaluation
stage how it improves existing methods, particularly in
the case of same-structured themes.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Graphs; invariants; melodic similarity; metadata;
music; music information retrieval; structural
properties; XML",
}
@Article{Gerstel:2007:RHI,
author = "Ori Gerstel and Shay Kutten and Eduardo Sany Laber and
Rachel Matichin and David Peleg and Artur Alves Pessoa
and Criston Souza",
title = "Reducing human interactions in {Web} directory
searches",
journal = j-TOIS,
volume = "25",
number = "4",
pages = "20:1--20:??",
month = oct,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1281485.1281491",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:16 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Consider a website containing a collection of webpages
with data such as in Yahoo or the Open Directory
project. Each page is associated with a weight
representing the frequency with which that page is
accessed by users. In the tree hierarchy
representation, accessing each page requires the user
to travel along the path leading to it from the root.
By enhancing the index tree with additional edges
(hotlinks) one may reduce the access cost of the
system. In other words, the hotlinks reduce the
expected number of steps needed to reach a leaf page
from the tree root, assuming that the user knows which
hotlinks to take. The hotlink enhancement problem
involves finding a set of hotlinks minimizing this
cost.\par
This article proposes the first exact algorithm for the
hotlink enhancement problem. This algorithm runs in
polynomial time for trees with logarithmic depth.
Experiments conducted with real data show that
significant improvement in the expected number of
accesses per search can be achieved in websites using
this algorithm. These experiments also suggest that the
simple and much faster heuristic proposed previously by
Czyzowicz et al. [2003] creates hotlinks that are
nearly optimal in the time savings they provide to the
user.\par
The version of the hotlink enhancement problem in which
the weight distribution on the leaves is unknown is
discussed as well. We present a polynomial-time
algorithm that is optimal for any tree for any depth.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "algorithms; directory tree; Hotlink; hotlist;
hyperlink",
}
@Article{Jensen:2007:RES,
author = "Eric C. Jensen and Steven M. Beitzel and Abdur
Chowdhury and Ophir Frieder",
title = "Repeatable evaluation of search services in dynamic
environments",
journal = j-TOIS,
volume = "26",
number = "1",
pages = "1:1--1:??",
month = nov,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1292591.1292592",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:26 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In dynamic environments, such as the World Wide Web, a
changing document collection, query population, and set
of search services demands frequent repetition of
search effectiveness (relevance) evaluations.
Reconstructing static test collections, such as in
TREC, requires considerable human effort, as large
collection sizes demand judgments deep into retrieved
pools. In practice it is common to perform shallow
evaluations over small numbers of live engines (often
pairwise, engine A vs. engine B) without system
pooling. Although these evaluations are not intended to
construct reusable test collections, their utility
depends on conclusions generalizing to the query
population as a whole. We leverage the bootstrap
estimate of the reproducibility probability of
hypothesis tests in determining the query sample sizes
required to ensure this, finding they are much larger
than those required for static collections. We propose
a semiautomatic evaluation framework to reduce this
effort. We validate this framework against a manual
evaluation of the top ten results of ten Web search
engines across 896 queries in navigational and
informational tasks. Augmenting manual judgments with
pseudo-relevance judgments mined from Web taxonomies
reduces both the chances of missing a correct pairwise
conclusion, and those of finding an errant conclusion,
by approximately 50\%.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Evaluation; Web search",
}
@Article{Pirkola:2007:FBI,
author = "Ari Pirkola and Jarmo Toivonen and Heikki Keskustalo
and Kalervo J{\"a}rvelin",
title = "Frequency-based identification of correct translation
equivalents {(FITE)} obtained through transformation
rules",
journal = j-TOIS,
volume = "26",
number = "1",
pages = "2:1--2:??",
month = nov,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1292591.1292593",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:26 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We devised a novel statistical technique for the
identification of the translation equivalents of source
words obtained by transformation rule based translation
(TRT). The effectiveness of the technique called
frequency-based identification of translation
equivalents ( FITE ) was tested using biological and
medical cross-lingual spelling variants and
out-of-vocabulary (OOV) words in Spanish--English and
Finnish-English TRT. The results showed that, depending
on the source language and frequency corpus, FITE-TRT
(the identification of translation equivalents from
TRT's translation set by means of the FITE technique)
may achieve high translation recall. In the case of the
Web as the frequency corpus, translation recall was
89.2\%--91.0\% for Spanish--English FITE-TRT. For both
language pairs FITE-TRT achieved high translation
precision: 95.0\%--98.8\%. The technique also reliably
identified native source language words: source words
that cannot be correctly translated by TRT.
Dictionary-based CLIR augmented with FITE-TRT performed
substantially better than basic dictionary-based CLIR
where OOV keys were kept intact. FITE-TRT with Web
document frequencies was the best technique among
several fuzzy translation/matching approaches tested in
cross-language retrieval experiments. We also discuss
the application of FITE-TRT in the automatic
construction of multilingual dictionaries.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Cross-language information retrieval; fuzzy matching;
OOV words; transformation rules; transliteration",
}
@Article{Agosti:2007:FMA,
author = "Maristella Agosti and Nicola Ferro",
title = "A formal model of annotations of digital content",
journal = j-TOIS,
volume = "26",
number = "1",
pages = "3:1--3:??",
month = nov,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1292591.1292594",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:26 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article is a study of the themes and issues
concerning the annotation of digital contents, such as
textual documents, images, and multimedia documents in
general. These digital contents are automatically
managed by different kinds of digital library
management systems and more generally by different
kinds of information management systems.\par
Even though this topic has already been partially
studied by other researchers, the previous research
work on annotations has left many open issues. These
issues concern the lack of clarity about what an
annotation is, what its features are, and how it is
used. These issues are mainly due to the fact that
models and systems for annotations have only been
developed for specific purposes. As a result, there is
only a fragmentary picture of the annotation and its
management, and this is tied to specific contexts of
use and lacks-general validity.\par
The aim of the article is to provide a unified and
integrated picture of the annotation, ranging from
defining what an annotation is to providing a formal
model. The key ideas of the model are: the distinction
between the meaning and the sign of the annotation,
which represent the semantics and the materialization
of an annotation, respectively; the clear formalization
of the temporal dimension involved with annotations;
and the introduction of a distributed hypertext between
digital contents and annotations. Therefore, the
proposed formal model captures both syntactic and
semantic aspects of the annotations. Furthermore, it is
built on previously existing models and may be seen as
an extension of them.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Annotation; digital content; digital library system;
foundations; hypertext",
}
@Article{Im:2007:DOS,
author = "Il Im and Alexander Hars",
title = "Does a one-size recommendation system fit all? the
effectiveness of collaborative filtering based
recommendation systems across different domains and
search modes",
journal = j-TOIS,
volume = "26",
number = "1",
pages = "4:1--4:??",
month = nov,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1292591.1292595",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:26 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Collaborative filtering (CF) is a personalization
technology that generates recommendations for users
based on others' evaluations. CF is used by numerous
e-commerce Web sites for providing personalized
recommendations. Although much research has focused on
refining collaborative filtering algorithms, little is
known about the effects of user and domain
characteristics on the accuracy of collaborative
filtering systems. In this study, the effects of two
factors---product domain and users' search mode---on
the accuracy of CF are investigated. The effects of
those factors are tested using data collected from two
experiments in two different product domains, and from
two large CF datasets, EachMovie and Book-Crossing. The
study shows that the search mode of the users strongly
influences the accuracy of the recommendations. CF
works better when users look for specific information
than when they search for general information. The
accuracy drops significantly when data from different
modes are mixed. The study also shows that CF is more
accurate for knowledge domains than for consumer
product domains. The results of this study imply that
for more accurate recommendations, collaborative
filtering systems should be able to identify and handle
users' mode of search, even within the same domain and
user group.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Collaborative filtering; recommendation systems",
}
@Article{Darwish:2007:ECV,
author = "Kareem Darwish and Walid Magdy",
title = "Error correction vs. query garbling for {Arabic OCR}
document retrieval",
journal = j-TOIS,
volume = "26",
number = "1",
pages = "5:1--5:??",
month = nov,
year = "2007",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1292591.1292596",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:26 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Due to the existence of large numbers of legacy
documents (such as old books and newspapers), improving
retrieval effectiveness for OCR'ed documents continues
to be an important problem. This article compares the
effect of OCR error correction with and without
language modeling and the effect of query garbling with
weighted structured queries on the retrieval of OCR
degraded Arabic documents. The results suggest that
moderate error correction does not yield statistically
significant improvement in retrieval effectiveness when
indexing and searching using n-grams. Also, reversing
error correction models to perform query garbling in
conjunction with weighted structured queries yields
improved retrieval effectiveness. Lastly, using very
good error correction that utilizes language modeling
yields the best improvement in retrieval
effectiveness.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Arabic Retrieval; OCR Correction; OCR Retrieval",
}
@Article{Ipeirotis:2008:CAH,
author = "Panagiotis G. Ipeirotis and Luis Gravano",
title = "Classification-aware hidden-web text database
selection",
journal = j-TOIS,
volume = "26",
number = "2",
pages = "6:1--6:??",
month = mar,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1344411.1344412",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:34 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Many valuable text databases on the web have
noncrawlable contents that are ``hidden'' behind search
interfaces. Metasearchers are helpful tools for
searching over multiple such ``hidden-web'' text
databases at once through a unified query interface. An
important step in the metasearching process is database
selection, or determining which databases are the most
relevant for a given user query. The state-of-the-art
database selection techniques rely on statistical
summaries of the database contents, generally including
the database vocabulary and associated word
frequencies. Unfortunately, hidden-web text databases
typically do not export such summaries, so previous
research has developed algorithms for constructing
approximate content summaries from document samples
extracted from the databases via querying. We present a
novel ``focused-probing'' sampling algorithm that
detects the topics covered in a database and adaptively
extracts documents that are representative of the topic
coverage of the database. Our algorithm is the first to
construct content summaries that include the
frequencies of the words in the database.
Unfortunately, Zipf's law practically guarantees that
for any relatively large database, content summaries
built from moderately sized document samples will fail
to cover many low-frequency words; in turn, incomplete
content summaries might negatively affect the database
selection process, especially for short queries with
infrequent words. To enhance the sparse document
samples and improve the database selection decisions,
we exploit the fact that topically similar databases
tend to have similar vocabularies, so samples extracted
from databases with a similar topical focus can
complement each other. We have developed two database
selection algorithms that exploit this observation. The
first algorithm proceeds hierarchically and selects the
best categories for a query, and then sends the query
to the appropriate databases in the chosen categories.
The second algorithm uses ``shrinkage,'' a statistical
technique for improving parameter estimation in the
face of sparse data, to enhance the database content
summaries with category-specific words. We describe how
to modify existing database selection algorithms to
adaptively decide (at runtime) whether shrinkage is
beneficial for a query. A thorough evaluation over a
variety of databases, including 315 real web databases
as well as TREC data, suggests that the proposed
sampling methods generate high-quality content
summaries and that the database selection algorithms
produce significantly more relevant database selection
decisions and overall search results than existing
algorithms.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "database selection; Distributed information retrieval;
web search",
}
@Article{Abbasi:2008:WSA,
author = "Ahmed Abbasi and Hsinchun Chen",
title = "Writeprints: a stylometric approach to identity-level
identification and similarity detection in cyberspace",
journal = j-TOIS,
volume = "26",
number = "2",
pages = "7:1--7:??",
month = mar,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1344411.1344413",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:34 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "One of the problems often associated with online
anonymity is that it hinders social accountability, as
substantiated by the high levels of cybercrime.
Although identity cues are scarce in cyberspace,
individuals often leave behind textual identity traces.
In this study we proposed the use of stylometric
analysis techniques to help identify individuals based
on writing style. We incorporated a rich set of
stylistic features, including lexical, syntactic,
structural, content-specific, and idiosyncratic
attributes. We also developed the Writeprints technique
for identification and similarity detection of
anonymous identities. Writeprints is a Karhunen-Loeve
transforms-based technique that uses a sliding window
and pattern disruption algorithm with individual
author-level feature sets. The Writeprints technique
and extended feature set were evaluated on a testbed
encompassing four online datasets spanning different
domains: email, instant messaging, feedback comments,
and program code. Writeprints outperformed benchmark
techniques, including SVM, Ensemble SVM, PCA, and
standard Karhunen-Loeve transforms, on the
identification and similarity detection tasks with
accuracy as high as 94\% when differentiating between
100 authors. The extended feature set also
significantly outperformed a baseline set of features
commonly used in previous research. Furthermore,
individual-author-level feature sets generally
outperformed use of a single group of attributes.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "discourse; online text; style classification;
Stylometry; text mining",
}
@Article{Lau:2008:TBR,
author = "Raymond Y. K. Lau and Peter D. Bruza and Dawei Song",
title = "Towards a belief-revision-based adaptive and
context-sensitive information retrieval system",
journal = j-TOIS,
volume = "26",
number = "2",
pages = "8:1--8:??",
month = mar,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1344411.1344414",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:34 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In an adaptive information retrieval (IR) setting, the
information seekers' beliefs about which terms are
relevant or nonrelevant will naturally fluctuate. This
article investigates how the theory of belief revision
can be used to model adaptive IR. More specifically,
belief revision logic provides a rich representation
scheme to formalize retrieval contexts so as to
disambiguate vague user queries. In addition, belief
revision theory underpins the development of an
effective mechanism to revise user profiles in
accordance with information seekers' changing
information needs. It is argued that information
retrieval contexts can be extracted by means of the
information-flow text mining method so as to realize a
highly autonomous adaptive IR system. The extra bonus
of a belief-based IR model is that its retrieval
behavior is more predictable and explanatory. Our
initial experiments show that the belief-based adaptive
IR system is as effective as a classical adaptive IR
system. To our best knowledge, this is the first
successful implementation and evaluation of a
logic-based adaptive IR model which can efficiently
process large IR collections.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "adaptive information retrieval; Belief revision;
information flow; retrieval context; text mining",
}
@Article{deMoura:2008:LBP,
author = "Edleno Silva de Moura and Celia Francisca dos Santos
and Bruno Dos santos de Araujo and Altigran Soares da
Silva and Pavel Calado and Mario A. Nascimento",
title = "Locality-Based pruning methods for web search",
journal = j-TOIS,
volume = "26",
number = "2",
pages = "9:1--9:??",
month = mar,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1344411.1344415",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:34 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article discusses a novel approach developed for
static index pruning that takes into account the
locality of occurrences of words in the text. We use
this new approach to propose and experiment on simple
and effective pruning methods that allow a fast
construction of the pruned index. The methods proposed
here are especially useful for pruning in environments
where the document database changes continuously, such
as large-scale web search engines. Extensive
experiments are presented showing that the proposed
methods can achieve high compression rates while
maintaining the quality of results for the most common
query types present in modern search engines, namely,
conjunctive and phrase queries. In the experiments, our
locality-based pruning approach allowed reducing search
engine indices to 30\% of their original size, with
almost no reduction in precision at the top answers.
Furthermore, we conclude that even an extremely simple
locality-based pruning method can be competitive when
compared to complex methods that do not rely on
locality information.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "indexing; information retrieval; Pruning; search;
search engines; web search",
}
@Article{Wang:2008:DSZ,
author = "Xuanhui Wang and Tao Tao and Jian-Tao Sun and Azadeh
Shakery and Chengxiang Zhai",
title = "{DirichletRank}: {Solving} the zero-one gap problem of
{PageRank}",
journal = j-TOIS,
volume = "26",
number = "2",
pages = "10:1--10:??",
month = mar,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1344411.1344416",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:34 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Link-based ranking algorithms are among the most
important techniques to improve web search. In
particular, the PageRank algorithm has been
successfully used in the Google search engine and has
been attracting much attention recently. However, we
find that PageRank has a ``zero-one gap'' problem
which, to the best of our knowledge, has not been
addressed in any previous work. This problem can be
potentially exploited to spam PageRank results and make
the state-of-the-art link-based antispamming techniques
ineffective. The zero-one gap problem arises as a
result of the current ad hoc way of computing
transition probabilities in the random surfing model.
We therefore propose a novel DirichletRank algorithm
which calculates these probabilities using Bayesian
estimation with a Dirichlet prior. DirichletRank is a
variant of PageRank, but does not have the problem of
zero-one gap and can be analytically shown
substantially more resistant to some link spams than
PageRank. Experiment results on TREC data show that
DirichletRank can achieve better retrieval accuracy
than PageRank due to its more reasonable allocation of
transition probabilities. More importantly, experiments
on the TREC dataset and another real web dataset from
the Webgraph project show that, compared with the
original PageRank, DirichletRank is more stable under
link perturbation and is significantly more robust
against both manually identified web spams and several
simulated link spams. DirichletRank can be computed as
efficiently as PageRank, and thus is scalable to
large-scale web applications.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "DirichletRank; link analysis; PageRank; spamming;
zero-one gap",
}
@Article{Cohen:2008:RTD,
author = "Sara Cohen and Carmel Domshlak and Naama Zwerdling",
title = "On ranking techniques for desktop search",
journal = j-TOIS,
volume = "26",
number = "2",
pages = "11:1--11:??",
month = mar,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1344411.1344417",
ISSN = "1046-8188",
bibdate = "Thu Jun 12 16:52:34 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Users tend to store huge amounts of files, of various
formats, on their personal computers. As a result,
finding a specific, desired file within the file system
is a challenging task. This article addresses the
desktop search problem by considering various
techniques for ranking results of a search query over
the file system. First, basic ranking techniques, which
are based on various file features (e.g., file name,
access date, file size, etc.), are considered and their
effectiveness is empirically analyzed. Next, two
learning-based ranking schemes are presented, and are
shown to be significantly more effective than the basic
ranking methods. Finally, a novel ranking technique,
based on query selectiveness, is considered for use
during the cold-start period of the system. This method
is also shown to be empirically effective, even though
it does not involve any learning.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Desktop search; personal information management;
ranking",
}
@Article{Abbasi:2008:SAM,
author = "Ahmed Abbasi and Hsinchun Chen and Arab Salem",
title = "Sentiment analysis in multiple languages: {Feature}
selection for opinion classification in {Web} forums",
journal = j-TOIS,
volume = "26",
number = "3",
pages = "12:1--12:??",
month = jun,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1361684.1361685",
ISSN = "1046-8188",
bibdate = "Thu Jun 19 08:32:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The Internet is frequently used as a medium for
exchange of information and opinions, as well as
propaganda dissemination. In this study the use of
sentiment analysis methodologies is proposed for
classification of Web forum opinions in multiple
languages. The utility of stylistic and syntactic
features is evaluated for sentiment classification of
English and Arabic content. Specific feature extraction
components are integrated to account for the linguistic
characteristics of Arabic. The entropy weighted genetic
algorithm (EWGA) is also developed, which is a
hybridized genetic algorithm that incorporates the
information-gain heuristic for feature selection. EWGA
is designed to improve performance and get a better
assessment of key features. The proposed features and
techniques are evaluated on a benchmark movie review
dataset and U.S. and Middle Eastern Web forum postings.
The experimental results using EWGA with SVM indicate
high performance levels, with accuracies of over 91\\%
on the benchmark dataset as well as the U.S. and Middle
Eastern forums. Stylistic features significantly
enhanced performance across all testbeds while EWGA
also outperformed other feature selection methods,
indicating the utility of these features and techniques
for document-level classification of sentiments.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "feature selection; opinion mining; Sentiment analysis;
text classification",
}
@Article{Wu:2008:ITI,
author = "Ho Chung Wu and Robert Wing Pong Luk and Kam Fai Wong
and Kui Lam Kwok",
title = "Interpreting {TF-IDF} term weights as making relevance
decisions",
journal = j-TOIS,
volume = "26",
number = "3",
pages = "13:1--13:??",
month = jun,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1361684.1361686",
ISSN = "1046-8188",
bibdate = "Thu Jun 19 08:32:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "A novel probabilistic retrieval model is presented. It
forms a basis to interpret the TF-IDF term weights as
making relevance decisions. It simulates the local
relevance decision-making for every location of a
document, and combines all of these ``local'' relevance
decisions as the ``document-wide'' relevance decision
for the document. The significance of interpreting
TF-IDF in this way is the potential to: (1) establish a
unifying perspective about information retrieval as
relevance decision-making; and (2) develop advanced
TF-IDF-related term weights for future elaborate
retrieval models. Our novel retrieval model is
simplified to a basic ranking formula that directly
corresponds to the TF-IDF term weights. In general, we
show that the term-frequency factor of the ranking
formula can be rendered into different term-frequency
factors of existing retrieval systems. In the basic
ranking formula, the remaining quantity $-\log
p(\bar{r}| t \in d)$ is interpreted as the probability
of randomly picking a nonrelevant usage (denoted by
$\bar{r}$) of term $t$. Mathematically, we show that
this quantity can be approximated by the inverse
document-frequency (IDF). Empirically, we show that
this quantity is related to IDF, using four reference
TREC ad hoc retrieval data collections.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Information retrieval; relevance decision; term
weight",
}
@Article{Melucci:2008:BIR,
author = "Massimo Melucci",
title = "A basis for information retrieval in context",
journal = j-TOIS,
volume = "26",
number = "3",
pages = "14:1--14:??",
month = jun,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1361684.1361687",
ISSN = "1046-8188",
bibdate = "Thu Jun 19 08:32:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Information retrieval (IR) models based on vector
spaces have been investigated for a long time.
Nevertheless, they have recently attracted much
research interest. In parallel, context has been
rediscovered as a crucial issue in information
retrieval. This article presents a principled approach
to modeling context and its role in ranking information
objects using vector spaces. First, the article
outlines how a basis of a vector space naturally
represents context, both its properties and factors.
Second, a ranking function computes the probability of
context in the objects represented in a vector space,
namely, the probability that a contextual factor has
affected the preparation of an object.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Personalization; probability; quantum mechanics;
vector-space model",
}
@Article{Altingovde:2008:ICB,
author = "Ismail Sengor Altingovde and Engin Demir and Fazli Can
and {\"O}zg{\"u}r Ulusoy",
title = "Incremental cluster-based retrieval using compressed
cluster-skipping inverted files",
journal = j-TOIS,
volume = "26",
number = "3",
pages = "15:1--15:??",
month = jun,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1361684.1361688",
ISSN = "1046-8188",
bibdate = "Thu Jun 19 08:32:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We propose a unique cluster-based retrieval (CBR)
strategy using a new cluster-skipping inverted file for
improving query processing efficiency. The new inverted
file incorporates cluster membership and centroid
information along with the usual document information
into a single structure. In our incremental-CBR
strategy, during query evaluation, both best(-matching)
clusters and the best(-matching) documents of such
clusters are computed together with a single
posting-list access per query term. As we switch from
term to term, the best clusters are recomputed and can
dynamically change. During query-document matching,
only relevant portions of the posting lists
corresponding to the best clusters are considered and
the rest are skipped. The proposed approach is
essentially tailored for environments where inverted
files are compressed, and provides substantial
efficiency improvement while yielding comparable, or
sometimes better, effectiveness figures. Our
experiments with various collections show that the
incremental-CBR strategy using a compressed
cluster-skipping inverted file significantly improves
CPU time efficiency, regardless of query length. The
new compressed inverted file imposes an acceptable
storage overhead in comparison to a typical inverted
file. We also show that our approach scales well with
the collection size.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Best match; cluster-based retrieval (CBR);
cluster-skipping inverted index structure (CS-IIS);
full search (FS); index compression; inverted index
structure (IIS); query processing",
}
@Article{Wang:2008:URM,
author = "Jun Wang and Arjen P. de Vries and Marcel J. T.
Reinders",
title = "Unified relevance models for rating prediction in
collaborative filtering",
journal = j-TOIS,
volume = "26",
number = "3",
pages = "16:1--16:??",
month = jun,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1361684.1361689",
ISSN = "1046-8188",
bibdate = "Thu Jun 19 08:32:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Collaborative filtering aims at predicting a user's
interest for a given item based on a collection of user
profiles. This article views collaborative filtering as
a problem highly related to information retrieval,
drawing an analogy between the concepts of users and
items in recommender systems and queries and documents
in text retrieval.\par
We present a probabilistic user-to-item relevance
framework that introduces the concept of relevance into
the related problem of collaborative filtering. Three
different models are derived, namely, a user-based, an
item-based, and a unified relevance model, and we
estimate their rating predictions from three sources:
the user's own ratings for different items, other
users' ratings for the same item, and ratings from
different but similar users for other but similar
items.\par
To reduce the data sparsity encountered when estimating
the probability density function of the relevance
variable, we apply the nonparametric (data-driven)
density estimation technique known as the Parzen-window
method (or kernel-based density estimation). Using a
Gaussian window function, the similarity between users
and/or items would, however, be based on Euclidean
distance. Because the collaborative filtering
literature has reported improved prediction accuracy
when using cosine similarity, we generalize the
Parzen-window method by introducing a projection
kernel.\par
Existing user-based and item-based approaches
correspond to two simplified instantiations of our
framework. User-based and item-based collaborative
filterings represent only a partial view of the
prediction problem, where the unified relevance model
brings these partial views together under the same
umbrella. Experimental results complement the
theoretical insights with improved recommendation
accuracy. The unified model is more robust to data
sparsity because the different types of ratings are
used in concert.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Collaborative filtering; personalization;
recommendation",
}
@Article{Losada:2008:AMB,
author = "David E. Losada and Leif Azzopardi",
title = "Assessing multivariate {Bernoulli} models for
information retrieval",
journal = j-TOIS,
volume = "26",
number = "3",
pages = "17:1--17:??",
month = jun,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1361684.1361690",
ISSN = "1046-8188",
bibdate = "Thu Jun 19 08:32:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Although the seminal proposal to introduce language
modeling in information retrieval was based on a
multivariate Bernoulli model, the predominant modeling
approach is now centered on multinomial models.
Language modeling for retrieval based on multivariate
Bernoulli distributions is seen inefficient and
believed less effective than the multinomial model. In
this article, we examine the multivariate Bernoulli
model with respect to its successor and examine its
role in future retrieval systems. In the context of
Bayesian learning, these two modeling approaches are
described, contrasted, and compared both theoretically
and computationally. We show that the query likelihood
following a multivariate Bernoulli distribution
introduces interesting retrieval features which may be
useful for specific retrieval tasks such as sentence
retrieval. Then, we address the efficiency aspect and
show that algorithms can be designed to perform
retrieval efficiently for multivariate Bernoulli
models, before performing an empirical comparison to
study the behaviorial aspects of the models. A series
of comparisons is then conducted on a number of test
collections and retrieval tasks to determine the
empirical and practical differences between the
different models. Our results indicate that for
sentence retrieval the multivariate Bernoulli model can
significantly outperform the multinomial model.
However, for the other tasks the multinomial model
provides consistently better performance (and in most
cases significantly so). An analysis of the various
retrieval characteristics reveals that the multivariate
Bernoulli model tends to promote long documents whose
nonquery terms are informative. While this is
detrimental to the task of document retrieval
(documents tend to contain considerable nonquery
content), it is valuable for other tasks such as
sentence retrieval, where the retrieved elements are
very short and focused.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Information retrieval; language models; multinomial;
multivariate Bernoulli",
}
@Article{Barreau:2008:IKR,
author = "Deborah Barreau and Robert Capra and Susan Dumais and
William Jones and Manuel P{\'e}rez-Qui{\~n}ones",
title = "Introduction to keeping, refinding and sharing
personal information",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "18:1--18:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402257",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Teevan:2008:HPR,
author = "Jaime Teevan",
title = "How people recall, recognize, and reuse search
results",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "19:1--19:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402258",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "When a person issues a query, that person has
expectations about the search results that will be
returned. These expectations can be based on the
current information need, but are also influenced by
how the searcher believes the search engine works,
where relevant results are expected to be ranked, and
any previous searches the individual has run on the
topic. This paper looks in depth at how the
expectations people develop about search result lists
during an initial query affect their perceptions of and
interactions with future repeat search result lists.
Three studies are presented that give insight into how
people recall, recognize, and reuse results. The first
study (a study of {\em recall\/}) explores what people
recall about previously viewed search result lists. The
second study (a study of {\em recognition\/}) builds on
the first to reveal that people often recognize a
result list as one they have seen before even when it
is quite different. As long as those aspects that the
searcher remembers about the initial list remain the
same, other aspects can change significantly. This is
advantageous because, as the third study (a study of
{\em reuse\/}) shows, when a result list appears to
have changed, people have trouble re-using the
previously viewed content in the list. They are less
likely to find what they are looking for, less happy
with the result quality, more likely to find the task
hard, and more likely to take a long time searching.
Although apparent consistency is important for reuse,
people's inability to recognize change makes
consistency without stagnation possible. New relevant
results can be presented where old results have been
forgotten, making both old and new content easy to
find.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "dynamic information; personal information management;
recall; recognition; Refinding; reuse; search",
}
@Article{Bergman:2008:ISE,
author = "Ofer Bergman and Ruth Beyth-Marom and Rafi Nachmias
and Noa Gradovitch and Steve Whittaker",
title = "Improved search engines and navigation preference in
personal information management",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "20:1--20:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402259",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Traditionally users access their personal files mainly
by using folder navigation. We evaluate whether recent
improvements in desktop search have changed this
fundamental aspect of Personal Information Management
(PIM). We tested this in two studies using the same
questionnaire: (a) The Windows Study --- a longitudinal
comparison of {\em Google Desktop\/} and {\em Windows
XP Search Companion}, and (b) The Mac Study --- a large
scale comparison of Mac {\em Spotlight\/} and {\em
Sherlock}. There were few effects for improved search.
First, regardless of search engine, there was a strong
navigation preference: on average, users estimated that
they used navigation for 56--68\% of file retrieval
events but searched for only 4--15\% of events. Second,
the effect of improving the quality of the search
engine on search usage was limited and inconsistent.
Third, search was used mainly as a last resort when
users could not remember file location. Finally, there
was no evidence that using improved desktop search
engines leads people to change their filing habits to
become less reliant on hierarchical file organization.
We conclude by offering theoretical explanations for
navigation preference, relating to differences between
PIM and Internet retrieval, and suggest alternative
design directions for PIM systems.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "files retrieval; navigation preference; Personal
information management; personal search engines; search
preference; user study",
}
@Article{Elsweiler:2008:EME,
author = "David Elsweiler and Mark Baillie and Ian Ruthven",
title = "Exploring memory in email refinding",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "21:1--21:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402260",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Human memory plays an important role in personal
information management (PIM). Several scholars have
noted that people refind information based on what they
remember and it has been shown that people adapt their
management strategies to compensate for the limitations
of memory. Nevertheless, little is known about what
people tend to remember about their personal
information and how they use their memories to refind.
The aim of this article is to increase our
understanding of the role that memory plays in the
process of refinding personal information.
Concentrating on email re-finding, we report on a user
study that investigates what attributes of email
messages participants remember when trying to refind.
We look at how the attributes change in different
scenarios and examine the factors which impact on what
is remembered.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Email refinding; information refinding; memory; user
study",
}
@Article{Siersdorfer:2008:MMM,
author = "Stefan Siersdorfer and Sergej Sizov",
title = "Meta methods for model sharing in personal information
systems",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "22:1--22:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402261",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article introduces a methodology for
automatically organizing document collections into
thematic categories for Personal Information Management
(PIM) through collaborative sharing of machine learning
models in an efficient and privacy-preserving way. Our
objective is to combine multiple independently learned
models from several users to construct an advanced
ensemble-based decision model by taking the knowledge
of multiple users into account in a decentralized
manner, for example, in a peer-to-peer overlay network.
High accuracy of the corresponding supervised
(classification) and unsupervised (clustering) methods
is achieved by restrictively leaving out uncertain
documents rather than assigning them to inappropriate
topics or clusters with low confidence. We introduce a
formal probabilistic model for the resulting ensemble
based meta methods and explain how it can be used for
constructing estimators and for goal-oriented tuning.
Comprehensive evaluation results on different reference
data sets illustrate the viability of our approach.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Classification; clustering; meta methods;
peer-to-peer; personal information management;
restrictive methods",
}
@Article{Hicks:2008:OMP,
author = "B. J. Hicks and A. Dong and R. Palmer and H. C.
Mcalpine",
title = "Organizing and managing personal electronic files: a
mechanical engineer's perspective",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "23:1--23:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402262",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article deals with the organization and
management of the computer files handled by mechanical
engineers on their personal computers. In engineering
organizations, a wide variety of electronic files
(documents) are necessary to support both business
processes and the activities of design and manufacture.
Whilst a large number of files and hence information is
formally archived, a significant amount of additional
information and knowledge resides in electronic files
on personal computers. The widespread use of these
personal information stores means that all information
is retained. However, its reuse is problematic for all
but the individual as a result of the naming and
organization of the files. To begin to address this
issue, a study of the use and current practices for
managing personal electronic files is described. The
study considers the fundamental classes of files
handled by engineers and analyses the organization of
these files across the personal computers of 40
participants. The study involves a questionnaire and an
electronic audit. The results of these qualitative and
quantitative elements are used to elicit an
understanding of the practices and requirements of
engineers for managing personal electronic files. A
potential scheme for naming and organizing personal
electronic files is discussed as one possible way to
satisfy these requirements. The aim of the scheme is to
balance the personal nature of data storage with the
need for personal records to be shared with others to
support knowledge reuse in engineering organizations.
Although this article is concerned with mechanical
engineers, the issues dealt with are relevant to
knowledge-based industries and, in particular, teams of
knowledge workers.",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "directory and file naming conventions; Engineers; file
sharing and file recognition and recall; information
management",
}
@Article{Bernstein:2008:ISH,
author = "Michael Bernstein and Max {Van Kleek} and David Karger
and M. C. Schraefel",
title = "Information scraps: {How} and why information eludes
our personal information management tools",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "24:1--24:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402263",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In this article we investigate {\em information
scraps\/} --- personal information where content has
been scribbled on Post-it notes, scrawled on the
corners of sheets of paper, stuck in our pockets, sent
in email messages to ourselves, and stashed in
miscellaneous digital text files. Information scraps
encode information ranging from ideas and sketches to
notes, reminders, shipment tracking numbers, driving
directions, and even poetry. Although information
scraps are ubiquitous, we have much still to learn
about these loose forms of information practice. Why do
we keep information scraps outside of our traditional
PIM applications? What role do information scraps play
in our overall information practice? How might PIM
applications be better designed to accommodate and
support information scraps' creation, manipulation and
retrieval?\par
We pursued these questions by studying the information
scrap practices of 27 knowledge workers at five
organizations. Our observations shed light on
information scraps' content, form, media, and location.
From this data, we elaborate on the typical information
scrap lifecycle, and identify common roles that
information scraps play: temporary storage, archiving,
work-in-progress, reminding, and management of unusual
data. These roles suggest a set of unmet design needs
in current PIM tools: lightweight entry, unconstrained
content, flexible use and adaptability, visibility, and
mobility.",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "information scraps; note taking; Personal information
management",
}
@Article{Marchionini:2008:ERM,
author = "Gary Marchionini",
title = "Editorial: {Reviewer} merits and review control in an
age of electronic manuscript management systems",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "25:1--25:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402264",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Peer review is an important resource of scholarly
communities and must be managed and nurtured carefully.
Electronic manuscript management systems have begun to
improve some aspects of workflow for conferences and
journals but also raise issues related to reviewer
roles and reputations and the control of reviews over
time. Professional societies should make their policies
related to reviews and reviewer histories clear to
authors and reviewers, develop strategies and tools to
facilitate good and timely reviews, and facilitate the
training of new reviewers.",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "manuscript management systems; Peer review",
}
@Article{Marchionini:2008:TRJ,
author = "Gary Marchionini",
title = "{TOIS} reviewers {June 2007} through {May 2008}",
journal = j-TOIS,
volume = "26",
number = "4",
pages = "26:1--26:??",
month = sep,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1402256.1402265",
ISSN = "1046-8188",
bibdate = "Mon Oct 6 15:21:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Piwowarski:2008:SCR,
author = "Benjamin Piwowarski and Andrew Trotman and Mounia
Lalmas",
title = "Sound and complete relevance assessment for {XML}
retrieval",
journal = j-TOIS,
volume = "27",
number = "1",
pages = "1:1--1:??",
month = dec,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1416950.1416951",
ISSN = "1046-8188",
bibdate = "Tue Dec 23 13:49:17 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In information retrieval research, comparing retrieval
approaches requires test collections consisting of
documents, user requests and relevance assessments.
Obtaining relevance assessments that are as sound and
complete as possible is crucial for the comparison of
retrieval approaches. In XML retrieval, the problem of
obtaining sound and complete relevance assessments is
further complicated by the structural relationships
between retrieval results.\par
A major difference between XML retrieval and flat
document retrieval is that the relevance of elements
(the retrievable units) is not independent of that of
related elements. This has major consequences for the
gathering of relevance assessments. This article
describes investigations into the creation of sound and
complete relevance assessments for the evaluation of
content-oriented XML retrieval as carried out at INEX,
the evaluation campaign for XML retrieval. The
campaign, now in its seventh year, has had three
substantially different approaches to gather
assessments and has finally settled on a highlighting
method for marking relevant passages within documents
--- even though the objective is to collect assessments
at element level. The different methods of gathering
assessments at INEX are discussed and contrasted. The
highlighting method is shown to be the most reliable of
the methods.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "evaluation; INEX; passage retrieval; relevance
assessment; XML; XML retrieval",
}
@Article{Moffat:2008:RBP,
author = "Alistair Moffat and Justin Zobel",
title = "Rank-biased precision for measurement of retrieval
effectiveness",
journal = j-TOIS,
volume = "27",
number = "1",
pages = "2:1--2:??",
month = dec,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1416950.1416952",
ISSN = "1046-8188",
bibdate = "Tue Dec 23 13:49:17 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "A range of methods for measuring the effectiveness of
information retrieval systems has been proposed. These
are typically intended to provide a quantitative
single-value summary of a document ranking relative to
a query. However, many of these measures have failings.
For example, recall is not well founded as a measure of
satisfaction, since the user of an actual system cannot
judge recall. Average precision is derived from recall,
and suffers from the same problem. In addition, average
precision lacks key stability properties that are
needed for robust experiments. In this article, we
introduce a new effectiveness metric, {\em rank-biased
precision}, that avoids these problems. Rank-biased
precision is derived from a simple model of user
behavior, is robust if answer rankings are extended to
greater depths, and allows accurate quantification of
experimental uncertainty, even when only partial
relevance judgments are available.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "average precision; pooling; precision; Recall;
relevance",
}
@Article{Zheleva:2008:TSR,
author = "Elena Zheleva and Aleksander Kolcz and Lise Getoor",
title = "Trusting spam reporters: a reporter-based reputation
system for email filtering",
journal = j-TOIS,
volume = "27",
number = "1",
pages = "3:1--3:??",
month = dec,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1416950.1416953",
ISSN = "1046-8188",
bibdate = "Tue Dec 23 13:49:17 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Spam is a growing problem; it interferes with valid
email and burdens both email users and service
providers. In this work, we propose a reactive
spam-filtering system based on reporter reputation for
use in conjunction with existing spam-filtering
techniques. The system has a trust-maintenance
component for users, based on their spam-reporting
behavior. The challenge that we consider is that of
maintaining a reliable system, not vulnerable to
malicious users, that will provide early spam-campaign
detection to reduce the costs incurred by users and
systems. We report on the utility of a reputation
system for spam filtering that makes use of the
feedback of trustworthy users. We evaluate our proposed
framework, using actual complaint feedback from a large
population of users, and validate its spam-filtering
performance on a collection of real email traffic over
several weeks. To test the broader implication of the
system, we create a model of the behavior of malicious
reporters, and we simulate the system under various
assumptions using a synthetic dataset.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "reputation systems; Spam filtering; trust",
}
@Article{Yeh:2008:EPH,
author = "Jui-Feng Yeh and Chung-Hsien Wu and Liang-Chih Yu and
Yu-Sheng Lai",
title = "Extended probabilistic {HAL} with close temporal
association for psychiatric query document retrieval",
journal = j-TOIS,
volume = "27",
number = "1",
pages = "4:1--4:??",
month = dec,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1416950.1416954",
ISSN = "1046-8188",
bibdate = "Tue Dec 23 13:49:17 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Psychiatric query document retrieval can assist
individuals to locate query documents relevant to their
depression-related problems efficiently and
effectively. By referring to relevant documents,
individuals can understand how to alleviate their
depression-related symptoms according to
recommendations from health professionals. This work
presents an extended probabilistic {\em Hyperspace
Analog to Language\/} ({\em epHAL\/}) model to achieve
this aim. The epHAL incorporates the close temporal
associations between words in query documents to
represent word cooccurrence relationships in a
high-dimensional context space. The information flow
mechanism further combines the query words in the epHAL
space to infer related words for effective information
retrieval. The language model perplexity is considered
as the criterion for model optimization. Finally, the
epHAL is adopted for psychiatric query document
retrieval, and indicates its superiority in information
retrieval over traditional approaches.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Hyperspace Analog to Language (HAL) model; information
flow; Information retrieval; query documents",
}
@Article{Kerne:2008:CMI,
author = "Andruid Kerne and Eunyee Koh and Steven M. Smith and
Andrew Webb and Blake Dworaczyk",
title = "{combinFormation}: Mixed-initiative composition of
image and text surrogates promotes information
discovery",
journal = j-TOIS,
volume = "27",
number = "1",
pages = "5:1--5:??",
month = dec,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1416950.1416955",
ISSN = "1046-8188",
bibdate = "Tue Dec 23 13:49:17 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "combinFormation is a mixed-initiative creativity
support tool for searching, browsing, organizing, and
integrating information. Images and text are connected
to represent surrogates (enhanced bookmarks),
optimizing the use of human cognitive facilities.
Composition, an alternative to lists and spatial
hypertext, is used to represent a collection of
surrogates as a connected whole, using principles from
art and design. This facilitates the creative process
of {\em information discovery}, in which humans develop
new ideas while finding and collecting information. To
provoke the user to think about the large space of
potentially relevant information resources, a
generative agent proactively engages in collecting
information resources, forming image and text
surrogates, and composing them visually. The agent
develops the collection and its visual representation
over time, enabling the user to see ideas and
relationships. To keep the human in control, we develop
interactive mechanisms for authoring the composition
and directing the agent. In a field study in an
interdisciplinary course on The Design Process, over a
hundred students alternated using combinFormation and
Google+Word to collect prior work on information
discovery invention assignments. The students that used
combinFormation's mixed-initiative composition of image
and text surrogates performed better.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "clustering; collections; creative cognition;
Creativity support tools; exploratory search; field
study; focused crawler; information discovery;
mixed-initiative systems; relevance feedback;
semantics; software agents",
}
@Article{Lin:2008:TAF,
author = "Jimmy Lin and Philip Wu and Eileen Abels",
title = "Toward automatic facet analysis and need negotiation:
{Lessons} from mediated search",
journal = j-TOIS,
volume = "27",
number = "1",
pages = "6:1--6:??",
month = dec,
year = "2008",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1416950.1416956",
ISSN = "1046-8188",
bibdate = "Tue Dec 23 13:49:17 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This work explores the hypothesis that interactions
between a trained human search intermediary and an
information seeker can inform the design of interactive
IR systems. We discuss results from a controlled
Wizard-of-Oz case study, set in the context of the TREC
2005 HARD track evaluation, in which a trained
intermediary executed an integrated search and
interaction strategy based on conceptual facet analysis
and informed by need negotiation techniques common in
reference interviews. Having a human ``in the loop''
yielded large improvements over fully automated systems
as measured by standard ranked-retrieval metrics,
demonstrating the value of mediated search. We present
a detailed analysis of the intermediary's actions to
gain a deeper understanding of what worked and why. One
contribution is a taxonomy of clarification types
informed both by empirical results and existing
theories in library and information science. We discuss
how these findings can guide the development of future
systems. Overall, this work illustrates how studying
human information-seeking processes can lead to better
information retrieval applications.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "interactive information retrieval; Reference
interview",
}
@Article{Rodriguez:2009:AMG,
author = "Marko A. Rodriguez and Johan Bollen and Herbert {Van
De Sompel}",
title = "Automatic metadata generation using associative
networks",
journal = j-TOIS,
volume = "27",
number = "2",
pages = "7:1--7:??",
month = feb,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1462198.1462199",
ISSN = "1046-8188",
bibdate = "Thu Mar 5 17:50:07 MST 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In spite of its tremendous value, metadata is
generally sparse and incomplete, thereby hampering the
effectiveness of digital information services. Many of
the existing mechanisms for the automated creation of
metadata rely primarily on content analysis which can
be costly and inefficient. The automatic metadata
generation system proposed in this article leverages
resource relationships generated from existing metadata
as a medium for propagation from metadata-rich to
metadata-poor resources. Because of its independence
from content analysis, it can be applied to a wide
variety of resource media types and is shown to be
computationally inexpensive. The proposed method
operates through two distinct phases. Occurrence and
cooccurrence algorithms first generate an associative
network of repository resources leveraging existing
repository metadata. Second, using the associative
network as a substrate, metadata associated with
metadata-rich resources is propagated to metadata-poor
resources by means of a discrete-form spreading
activation algorithm. This article discusses the
general framework for building associative networks, an
algorithm for disseminating metadata through such
networks, and the results of an experiment and
validation of the proposed method using a standard
bibliographic dataset.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Associative networks; metadata generation;
particle-swarms",
}
@Article{Park:2009:ALS,
author = "Laurence A. F. Park and Kotagiri Ramamohanarao",
title = "An analysis of latent semantic term self-correlation",
journal = j-TOIS,
volume = "27",
number = "2",
pages = "8:1--8:??",
month = feb,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1462198.1462200",
ISSN = "1046-8188",
bibdate = "Thu Mar 5 17:50:07 MST 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Latent semantic analysis (LSA) is a generalized vector
space method that uses dimension reduction to generate
term correlations for use during the information
retrieval process. We hypothesized that even though the
dimension reduction establishes correlations between
terms, the dimension reduction is causing a degradation
in the correlation of a term to itself
(self-correlation). In this article, we have proven
that there is a direct relationship to the size of the
LSA dimension reduction and the LSA self-correlation.
We have also shown that by altering the LSA term
self-correlations we gain a substantial increase in
precision, while also reducing the computation required
during the information retrieval process.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Latent semantic analysis; term correlation",
}
@Article{Chen:2009:ATF,
author = "Chien Chin Chen and Meng Chang Chen and Ming-Syan
Chen",
title = "An adaptive threshold framework for event detection
using {HMM}-based life profiles",
journal = j-TOIS,
volume = "27",
number = "2",
pages = "9:1--9:??",
month = feb,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1462198.1462201",
ISSN = "1046-8188",
bibdate = "Thu Mar 5 17:50:07 MST 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "When an event occurs, it attracts attention of
information sources to publish related documents along
its lifespan. The task of event detection is to
automatically identify events and their related
documents from a document stream, which is a set of
chronologically ordered documents collected from
various information sources. Generally, each event has
a distinct activeness development so that its status
changes continuously during its lifespan. When an event
is active, there are a lot of related documents from
various information sources. In contrast when it is
inactive, there are very few documents, but they are
focused. Previous works on event detection did not
consider the characteristics of the event's activeness,
and used rigid thresholds for event detection. We
propose a concept called life profile, modeled by a
hidden Markov model, to model the activeness trends of
events. In addition, a general event detection
framework, LIPED, which utilizes the learned life
profiles and the burst-and-diverse characteristic to
adjust the event detection thresholds adaptively, can
be incorporated into existing event detection methods.
Based on the official TDT corpus and contest rules, the
evaluation results show that existing detection methods
that incorporate LIPED achieve better performance in
the cost and F1 metrics, than without.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "clustering; Event detection; hidden Markov models;
life profiles; TDT; topic detection",
}
@Article{Tryfonopoulos:2009:IFQ,
author = "Christos Tryfonopoulos and Manolis Koubarakis and
Yannis Drougas",
title = "Information filtering and query indexing for an
information retrieval model",
journal = j-TOIS,
volume = "27",
number = "2",
pages = "10:1--10:??",
month = feb,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1462198.1462202",
ISSN = "1046-8188",
bibdate = "Thu Mar 5 17:50:07 MST 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In the information filtering paradigm, clients
subscribe to a server with continuous queries or
profiles that express their information needs. Clients
can also publish documents to servers. Whenever a
document is published, the continuous queries
satisfying this document are found and notifications
are sent to appropriate clients. This article deals
with the filtering problem that needs to be solved
efficiently by each server: Given a database of
continuous queries {\em db\/} and a document $d$, find
all queries $q \in {\em db\/}$ that match $d$. We
present data structures and indexing algorithms that
enable us to solve the filtering problem efficiently
for large databases of queries expressed in the model
{\em AWP}. {\em AWP\/} is based on named attributes
with values of type text, and its query language
includes Boolean and word proximity operators.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Information filtering; performance evaluation; query
indexing algorithms; selective dissemination of
information",
}
@Article{Xue:2009:ULM,
author = "Gui-Rong Xue and Jie Han and Yong Yu and Qiang Yang",
title = "User language model for collaborative personalized
search",
journal = j-TOIS,
volume = "27",
number = "2",
pages = "11:1--11:??",
month = feb,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1462198.1462203",
ISSN = "1046-8188",
bibdate = "Thu Mar 5 17:50:07 MST 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Traditional personalized search approaches rely solely
on individual profiles to construct a user model. They
are often confronted by two major problems: data
sparseness and cold-start for new individuals. Data
sparseness refers to the fact that most users only
visit a small portion of Web pages and hence a very
sparse user-term relationship matrix is generated,
while cold-start for new individuals means that the
system cannot conduct any personalization without
previous browsing history. Recently, community-based
approaches were proposed to use the group's social
behaviors as a supplement to personalization. However,
these approaches only consider the commonality of a
group of users and still cannot satisfy the diverse
information needs of different users. In this article,
we present a new approach, called collaborative
personalized search. It considers not only the
commonality factor among users for defining group user
profiles and global user profiles, but also the
specialties of individuals. Then, a statistical user
language model is proposed to integrate the individual
model, group user model and global user model together.
In this way, the probability that a user will like a
Web page is calculated through a two-step smoothing
mechanism. First, a global user model is used to smooth
the probability of unseen terms in the individual
profiles and provide aggregated behavior of global
users. Then, in order to precisely describe individual
interests by looking at the behaviors of similar users,
users are clustered into groups and group-user models
are constructed. The group-user models are integrated
into an overall model through a cluster-based language
model. The behaviors of the group users can be utilized
to enhance the performance of personalized search. This
model can alleviate the two aforementioned problems and
provide a more effective personalized search than
previous approaches. Large-scale experimental
evaluations are conducted to show that the proposed
approach substantially improves the relevance of a
search over several competitive methods.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "clustering; cold-start; Collaborative personalized
search; data Sparseness; smoothing; user language
model",
}
@Article{Schumaker:2009:TAS,
author = "Robert P. Schumaker and Hsinchun Chen",
title = "Textual analysis of stock market prediction using
breaking financial news: {The} {AZFin} text system",
journal = j-TOIS,
volume = "27",
number = "2",
pages = "12:1--12:??",
month = feb,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1462198.1462204",
ISSN = "1046-8188",
bibdate = "Thu Mar 5 17:50:07 MST 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Our research examines a predictive machine learning
approach for financial news articles analysis using
several different textual representations: bag of
words, noun phrases, and named entities. Through this
approach, we investigated 9,211 financial news articles
and 10,259,042 stock quotes covering the S\&P 500
stocks during a five week period. We applied our
analysis to estimate a discrete stock price twenty
minutes after a news article was released. Using a
support vector machine (SVM) derivative specially
tailored for discrete numeric prediction and models
containing different stock-specific variables, we show
that the model containing both article terms and stock
price at the time of article release had the best
performance in closeness to the actual future stock
price (MSE 0.04261), the same direction of price
movement as the future price (57.1\% directional
accuracy) and the highest return using a simulated
trading engine (2.06\% return). We further investigated
the different textual representations and found that a
Proper Noun scheme performs better than the de facto
standard of Bag of Words in all three metrics.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "prediction; stock market; SVM",
}
@Article{Kurland:2009:CLM,
author = "Oren Kurland and Lillian Lee",
title = "Clusters, language models, and ad hoc information
retrieval",
journal = j-TOIS,
volume = "27",
number = "3",
pages = "13:1--13:??",
month = may,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1508850.1508851",
ISSN = "1046-8188",
bibdate = "Wed May 20 13:44:20 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The language-modeling approach to information
retrieval provides an effective statistical framework
for tackling various problems and often achieves
impressive empirical performance. However, most
previous work on language models for information
retrieval focused on document-specific characteristics,
and therefore did not take into account the structure
of the surrounding corpus, a potentially rich source of
additional information. We propose a novel algorithmic
framework in which information provided by
document-based language models is enhanced by the
incorporation of information drawn from {\em
clusters\/} of similar documents. Using this framework,
we develop a suite of new algorithms. Even the simplest
typically outperforms the standard language-modeling
approach in terms of mean average precision (MAP) and
recall, and our new {\em interpolation\/} algorithm
posts statistically significant performance
improvements for both metrics over all six corpora
tested. An important aspect of our work is the way we
model corpus structure. In contrast to most previous
work on cluster-based retrieval that partitions the
corpus, we demonstrate the effectiveness of a simple
strategy based on a nearest-neighbors approach that
produces overlapping clusters.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "aspect models; cluster hypothesis; cluster-based
language models; clustering; interpolation model;
Language modeling; smoothing",
}
@Article{Shokouhi:2009:RRM,
author = "Milad Shokouhi and Justin Zobel",
title = "Robust result merging using sample-based score
estimates",
journal = j-TOIS,
volume = "27",
number = "3",
pages = "14:1--14:??",
month = may,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1508850.1508852",
ISSN = "1046-8188",
bibdate = "Wed May 20 13:44:20 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In federated information retrieval, a query is routed
to multiple collections and a single answer list is
constructed by combining the results. Such metasearch
provides a mechanism for locating documents on the
hidden Web and, by use of sampling, can proceed even
when the collections are uncooperative. However, the
similarity scores for documents returned from different
collections are not comparable, and, in uncooperative
environments, document scores are unlikely to be
reported. We introduce a new merging method for
uncooperative environments, in which similarity scores
for the sampled documents held for each collection are
used to estimate global scores for the documents
returned per query. This method requires no assumptions
about properties such as the retrieval models used.
Using experiments on a wide range of collections, we
show that in many cases our merging methods are
significantly more effective than previous
techniques.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "distributed information retrieval; result fusion;
Result merging; uncooperative collections",
}
@Article{Candan:2009:SSE,
author = "K. Sel{\c{c}}uk Candan and Mehmet E. D{\"o}nderler and
Terri Hedgpeth and Jong Wook Kim and Qing Li and Maria
Luisa Sapino",
title = "{SEA}: {Segment-enrich-annotate} paradigm for adapting
dialog-based content for improved accessibility",
journal = j-TOIS,
volume = "27",
number = "3",
pages = "15:1--15:??",
month = may,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1508850.1508853",
ISSN = "1046-8188",
bibdate = "Wed May 20 13:44:20 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "While navigation within complex information spaces is
a problem for all users, the problem is most evident
with individuals who are blind who cannot simply
locate, point, and click on a link in hypertext
documents with a mouse. Users who are blind have to
listen searching for the link in the document using
only the keyboard and a screen reader program, which
may be particularly inefficient in large documents with
many links or deep hierarchies that are hard to
navigate. Consequently, they are especially penalized
when the information being searched is hidden under
multiple layers of indirections. In this article, we
introduce a {\em segment-enrich-annotate\/} (SEA)
paradigm for adapting digital content with deep
structures for improved accessibility. In particular,
we instantiate and evaluate this paradigm through the
iCare-Assistant, an assistive system for helping
students who are blind in accessing Web and electronic
course materials. Our evaluations, involving the
participation of students who are blind, showed that
the iCare-Assistant system, built based on the SEA
paradigm, reduces the navigational overhead
significantly and enables user who are blind access
complex online course servers effectively.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "annotation; assistive technology for blind users;
educational discussion boards and Web sites;
segmentation; Web navigational aids",
}
@Article{Hoi:2009:SSB,
author = "Steven C. H. Hoi and Rong Jin and Jianke Zhu and
Michael R. Lyu",
title = "Semisupervised {SVM} batch mode active learning with
applications to image retrieval",
journal = j-TOIS,
volume = "27",
number = "3",
pages = "16:1--16:??",
month = may,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1508850.1508854",
ISSN = "1046-8188",
bibdate = "Wed May 20 13:44:20 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Support vector machine (SVM) active learning is one
popular and successful technique for relevance feedback
in content-based image retrieval (CBIR). Despite the
success, conventional SVM active learning has two main
drawbacks. First, the performance of SVM is usually
limited by the number of labeled examples. It often
suffers a poor performance for the small-sized labeled
examples, which is the case in relevance feedback.
Second, conventional approaches do not take into
account the redundancy among examples, and could select
multiple examples that are similar (or even identical).
In this work, we propose a novel scheme for explicitly
addressing the drawbacks. It first learns a kernel
function from a mixture of labeled and unlabeled data,
and therefore alleviates the problem of small-sized
training data. The kernel will then be used for a batch
mode active learning method to identify the most
informative and diverse examples via a min-max
framework. Two novel algorithms are proposed to solve
the related combinatorial optimization: the first
approach approximates the problem into a quadratic
program, and the second solves the combinatorial
optimization approximately by a greedy algorithm that
exploits the merits of submodular functions. Extensive
experiments with image retrieval using both natural
photo images and medical images show that the proposed
algorithms are significantly more effective than the
state-of-the-art approaches. A demo is available at
http://msm.cais.ntu.edu.sg/LSCBIR/.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "active learning; batch mode active learning;
Content-based image retrieval; human-computer
interaction; semisupervised learning; support vector
machines",
}
@Article{Huang:2009:BCS,
author = "Zi Huang and Heng Tao Shen and Jie Shao and Xiaofang
Zhou and Bin Cui",
title = "Bounded coordinate system indexing for real-time video
clip search",
journal = j-TOIS,
volume = "27",
number = "3",
pages = "17:1--17:??",
month = may,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1508850.1508855",
ISSN = "1046-8188",
bibdate = "Wed May 20 13:44:20 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Recently, video clips have become very popular online.
The massive influx of video clips has created an urgent
need for video search engines to facilitate retrieving
relevant clips. Different from traditional long videos,
a video clip is a short video often expressing a moment
of significance. Due to the high complexity of video
data, efficient video clip search from large databases
turns out to be very challenging. We propose a novel
video clip representation model called the {\em Bounded
Coordinate System\/} (BCS), which is the first single
representative capturing the dominating content and
content --- changing trends of a video clip. It
summarizes a video clip by a coordinate system, where
each of its coordinate axes is identified by principal
component analysis (PCA) and bounded by the range of
data projections along the axis. The similarity measure
of BCS considers the operations of translation,
rotation, and scaling for coordinate system matching.
Particularly, rotation and scaling reflect the
difference of content tendencies. Compared with the
quadratic time complexity of existing methods, the time
complexity of measuring BCS similarity is linear. The
compact video representation together with its linear
similarity measure makes real-time search from video
clip collections feasible. To further improve the
retrieval efficiency for large video databases, a
two-dimensional transformation method called {\em
Bidistance Transformation\/} (BDT) is introduced to
utilize a pair of optimal reference points with respect
to bidirectional axes in BCS. Our extensive performance
study on a large database of more than 30,000 video
clips demonstrates that BCS achieves very high search
accuracy according to human judgment. This indicates
that content tendencies are important in determining
the meanings of video clips and confirms that BCS can
capture the inherent moment of video clip to some
extent that better resembles human perception. In
addition, BDT outperforms existing indexing methods
greatly. Integration of the BCS model and BDT indexing
can achieve real-time search from large video clip
databases.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "indexing; query processing; summarization; Video
search",
}
@Article{Shen:2009:NFE,
author = "Jialie Shen and John Shepherd and Bin Cui and Kian-Lee
Tan",
title = "A novel framework for efficient automated singer
identification in large music databases",
journal = j-TOIS,
volume = "27",
number = "3",
pages = "18:1--18:??",
month = may,
year = "2009",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1508850.1508856",
ISSN = "1046-8188",
bibdate = "Wed May 20 13:44:20 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Over the past decade, there has been explosive growth
in the availability of multimedia data, particularly
image, video, and music. Because of this, content-based
music retrieval has attracted attention from the
multimedia database and information retrieval
communities. Content-based music retrieval requires us
to be able to automatically identify particular
characteristics of music data. One such characteristic,
useful in a range of applications, is the
identification of the singer in a musical piece.
Unfortunately, existing approaches to this problem
suffer from either low accuracy or poor scalability. In
this article, we propose a novel scheme, called {\em
Hybrid Singer Identifier\/} (HSI), for efficient
automated singer recognition. HSI uses multiple
low-level features extracted from both vocal and
nonvocal music segments to enhance the identification
process; it achieves this via a hybrid architecture
that builds profiles of individual singer
characteristics based on statistical mixture models. An
extensive experimental study on a large music database
demonstrates the superiority of our method over
state-of-the-art approaches in terms of effectiveness,
efficiency, scalability, and robustness.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "classification; EM algorithm; evaluation; Gaussian
mixture models; Music retrieval; singer identification;
statistical modeling",
}
@Article{Boldi:2009:PFD,
author = "Paolo Boldi and Massimo Santini and Sebastiano Vigna",
title = "{PageRank}: {Functional} dependencies",
journal = j-TOIS,
volume = "27",
number = "4",
pages = "19:1--19:??",
month = nov,
year = "2009",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:02 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Dang:2009:BFP,
author = "Edward Kai Fung Dang and Ho Chung Wu and Robert Wing
Pong Luk and Kam Fai Wong",
title = "Building a framework for the probability ranking
principle by a family of expected weighted rank",
journal = j-TOIS,
volume = "27",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2009",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:02 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Guiver:2009:FGT,
author = "John Guiver and Stefano Mizzaro and Stephen
Robertson",
title = "A few good topics: {Experiments} in topic set
reduction for retrieval evaluation",
journal = j-TOIS,
volume = "27",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2009",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:02 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Dupplaw:2009:DSB,
author = "David Dupplaw and Srinandan Dasmahapatra and Bo Hu and
Paul Lewis and Nigel Shadbolt",
title = "A distributed, service-based framework for knowledge
applications with multimedia",
journal = j-TOIS,
volume = "27",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2009",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:02 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{White:2009:CSE,
author = "Ryen W. White and Eric Horvitz",
title = "Cyberchondria: {Studies} of the escalation of medical
concerns in {Web} search",
journal = j-TOIS,
volume = "27",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2009",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:02 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Rosaci:2009:MDR,
author = "Domenico Rosaci and Giuseppe M. L. Sarn{\'e} and
Salvatore Garruzzo",
title = "{MUADDIB}: a distributed recommender system supporting
device adaptivity",
journal = j-TOIS,
volume = "27",
number = "4",
pages = "24:1--24:??",
month = nov,
year = "2009",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:02 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Blanco:2010:PSP,
author = "Roi Blanco and Alvaro Barreiro",
title = "Probabilistic static pruning of inverted files",
journal = j-TOIS,
volume = "28",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2010",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:04 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chia:2010:SLB,
author = "Tee Kiah Chia and Khe Chai Sim and Haizhou Li and Hwee
Tou Ng",
title = "Statistical lattice-based spoken document retrieval",
journal = j-TOIS,
volume = "28",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2010",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:04 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tagarelli:2010:SCX,
author = "Andrea Tagarelli and Sergio Greco",
title = "Semantic clustering of {XML} documents",
journal = j-TOIS,
volume = "28",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2010",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:04 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Rosen-Zvi:2010:LAT,
author = "Michal Rosen-Zvi and Chaitanya Chemudugunta and Thomas
Griffiths and Padhraic Smyth and Mark Steyvers",
title = "Learning author-topic models from text corpora",
journal = j-TOIS,
volume = "28",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2010",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Mon Mar 15 12:37:04 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Puppin:2010:TCS,
author = "Diego Puppin and Fabrizio Silvestri and Raffaele
Perego and Ricardo Baeza-Yates",
title = "Tuning the capacity of search engines: {Load-driven}
routing and incremental caching to reduce and balance
the load",
journal = j-TOIS,
volume = "28",
number = "2",
pages = "5:1--5:??",
month = may,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1740592.1740593",
ISSN = "1046-8188",
bibdate = "Mon Jun 21 17:30:54 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article introduces an architecture for a
document-partitioned search engine, based on a novel
approach combining collection selection and load
balancing, called {\em load-driven routing}. By
exploiting the query-vector document model, and the
incremental caching technique, our architecture can
compute very high quality results for any query, with
only a fraction of the computational load used in a
typical document-partitioned architecture. By trading
off a small fraction of the results, our technique
allows us to strongly reduce the computing pressure to
a search engine back-end; we are able to retrieve more
than 2/3 of the top-5 results for a given query with
only 10\% the computing load needed by a configuration
where the query is processed by each index partition.
Alternatively, we can slightly increase the load up to
25\% to improve precision and get more than 80\% of the
top-5 results. In fact, the flexibility of our system
allows a wide range of different configurations, so as
to easily respond to different needs in result quality
or restrictions in computing power. More important, the
system configuration can be adjusted dynamically in
order to fit unexpected query peaks or unpredictable
failures. This article wraps up some recent works by
the authors, showing the results obtained by tests
conducted on 6 million documents, 2,800,000 queries and
real query cost timing as measured on an actual
index.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "collection selection; Distributed IR; incremental
caching; Web search engines",
}
@Article{Gao:2010:EQL,
author = "Wei Gao and Cheng Niu and Jian-Yun Nie and Ming Zhou
and Kam-Fai Wong and Hsiao-Wuen Hon",
title = "Exploiting query logs for cross-lingual query
suggestions",
journal = j-TOIS,
volume = "28",
number = "2",
pages = "6:1--6:??",
month = may,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1740592.1740594",
ISSN = "1046-8188",
bibdate = "Mon Jun 21 17:30:54 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Query suggestion aims to suggest relevant queries for
a given query, which helps users better specify their
information needs. Previous work on query suggestion
has been limited to the same language. In this article,
we extend it to cross-lingual query suggestion (CLQS):
for a query in one language, we suggest similar or
relevant queries in other languages. This is very
important to the scenarios of cross-language
information retrieval (CLIR) and other related
cross-lingual applications. Instead of relying on
existing query translation technologies for CLQS, we
present an effective means to map the input query of
one language to queries of the other language in the
query log. Important monolingual and cross-lingual
information such as word translation relations and word
co-occurrence statistics, and so on, are used to
estimate the cross-lingual query similarity with a
discriminative model. Benchmarks show that the
resulting CLQS system significantly outperforms a
baseline system that uses dictionary-based query
translation. Besides, we evaluate CLQS with
French-English and Chinese--English CLIR tasks on
TREC-6 and NTCIR-4 collections, respectively. The CLIR
experiments using typical retrieval models demonstrate
that the CLQS-based approach has significantly higher
effectiveness than several traditional query
translation methods. We find that when combined with
pseudo-relevance feedback, the effectiveness of CLIR
using CLQS is enhanced for different pairs of
languages.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Cross-language information retrieval; query expansion;
query log; query suggestion; query translation",
}
@Article{Kolbe:2010:ENN,
author = "Dashiell Kolbe and Qiang Zhu and Sakti Pramanik",
title = "Efficient $k$-nearest neighbor searching in nonordered
discrete data spaces",
journal = j-TOIS,
volume = "28",
number = "2",
pages = "7:1--7:??",
month = may,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1740592.1740595",
ISSN = "1046-8188",
bibdate = "Mon Jun 21 17:30:54 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Numerous techniques have been proposed in the past for
supporting efficient {\em k\/} -nearest neighbor ({\em
k\/} -NN) queries in continuous data spaces. Limited
work has been reported in the literature for {\em k\/}
-NN queries in a nonordered discrete data space (NDDS).
Performing {\em k\/} -NN queries in an NDDS raises new
challenges. The Hamming distance is usually used to
measure the distance between two vectors (objects) in
an NDDS. Due to the coarse granularity of the Hamming
distance, a {\em k\/} -NN query in an NDDS may lead to
a high degree of nondeterminism for the query result.
We propose a new distance measure, called
Granularity-Enhanced Hamming (GEH) distance, which
effectively reduces the number of candidate solutions
for a query. We have also implemented {\em k\/} -NN
queries using multidimensional database indexing in
NDDSs. Further, we use the properties of our
multidimensional NDDS index to derive the probability
of encountering valid neighbors within specific regions
of the index. This probability is used to develop a new
search ordering heuristic. Our experiments on synthetic
and genomic data sets demonstrate that our index-based
{\em k\/} -NN algorithm is efficient in finding {\em
k\/} -NNs in both uniform and nonuniform data sets in
NDDSs and that our heuristics are effective in
improving the performance of such queries.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "database; distance measurement; nearest neighbor;
nonordered discrete data space; Similarity search;
spatial indexing",
}
@Article{Wan:2010:ENK,
author = "Xiaojun Wan and Jianguo Xiao",
title = "Exploiting neighborhood knowledge for single document
summarization and keyphrase extraction",
journal = j-TOIS,
volume = "28",
number = "2",
pages = "8:1--8:??",
month = may,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1740592.1740596",
ISSN = "1046-8188",
bibdate = "Mon Jun 21 17:30:54 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Document summarization and keyphrase extraction are
two related tasks in the IR and NLP fields, and both of
them aim at extracting condensed representations from a
single text document. Existing methods for single
document summarization and keyphrase extraction usually
make use of only the information contained in the
specified document. This article proposes using a small
number of nearest neighbor documents to improve
document summarization and keyphrase extraction for the
specified document, under the assumption that the
neighbor documents could provide additional knowledge
and more clues. The specified document is expanded to a
small document set by adding a few neighbor documents
close to the document, and the graph-based ranking
algorithm is then applied on the expanded document set
to make use of both the local information in the
specified document and the global information in the
neighbor documents. Experimental results on the
Document Understanding Conference (DUC) benchmark
datasets demonstrate the effectiveness and robustness
of our proposed approaches. The cross-document sentence
relationships in the expanded document set are
validated to be beneficial to single document
summarization, and the word cooccurrence relationships
in the neighbor documents are validated to be very
helpful to single document keyphrase extraction.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Document summarization; graph-based ranking; keyphrase
extraction; neighborhood knowledge",
}
@Article{Kelly:2010:EPN,
author = "Diane Kelly and Xin Fu and Chirag Shah",
title = "Effects of position and number of relevant documents
retrieved on users' evaluations of system performance",
journal = j-TOIS,
volume = "28",
number = "2",
pages = "9:1--9:??",
month = may,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1740592.1740597",
ISSN = "1046-8188",
bibdate = "Mon Jun 21 17:30:54 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Information retrieval research has demonstrated that
system performance does not always correlate positively
with user performance, and that users often assign
positive evaluation scores to search systems even when
they are unable to complete tasks successfully. This
research investigated the relationship between
objective measures of system performance and users'
perceptions of that performance. In this study,
subjects evaluated the performance of four search
systems whose search results were manipulated
systematically to produce different orderings and
numbers of relevant documents. Three laboratory studies
were conducted with a total of eighty-one subjects. The
first two studies investigated the effect of the order
of five relevant and five nonrelevant documents in a
search results list containing ten results on subjects'
evaluations. The third study investigated the effect of
varying the number of relevant documents in a search
results list containing ten results on subjects'
evaluations. Results demonstrate linear relationships
between subjects' evaluations and the position of
relevant documents in a search results list and the
total number of relevant documents retrieved. Of the
two, number of relevant documents retrieved was a
stronger predictor of subjects' evaluation ratings and
resulted in subjects using a greater range of
evaluation scores.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "precision; presentation of search results; ranking;
satisfaction; Search performance; user evaluation of
performance",
}
@Article{Brisaboa:2010:DLT,
author = "Nieves Brisaboa and Antonio Fari{\~n}a and Gonzalo
Navarro and Jos{\'e} Param{\'a}",
title = "Dynamic lightweight text compression",
journal = j-TOIS,
volume = "28",
number = "3",
pages = "10:1--10:??",
month = jun,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1777432.1777433",
ISSN = "1046-8188",
bibdate = "Tue Jul 6 15:53:00 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We address the problem of adaptive compression of
natural language text, considering the case where the
receiver is much less powerful than the sender, as in
mobile applications. Our techniques achieve compression
ratios around 32\% and require very little effort from
the receiver. Furthermore, the receiver is not only
lighter, but it can also search the compressed text
with less work than that necessary to decompress it.
This is a novelty in two senses: it breaks the usual
compressor/decompressor symmetry typical of adaptive
schemes, and it contradicts the long-standing
assumption that only semistatic codes could be searched
more efficiently than the uncompressed text. Our novel
compression methods are preferable in several aspects
over the existing adaptive and semistatic compressors
for natural language texts.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "adaptive natural language text compression; compressed
pattern matching; real-time transmission; searching
compressed texts; text compression",
}
@Article{Wu:2010:AVG,
author = "Gang Wu and Yimin Wei",
title = "{Arnoldi} versus {GMRES} for computing {PageRank}: a
theoretical contribution to {Google}'s {PageRank}
problem",
journal = j-TOIS,
volume = "28",
number = "3",
pages = "11:1--11:28",
month = jun,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1777432.1777434",
ISSN = "1046-8188",
bibdate = "Tue Jul 6 15:53:00 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "PageRank is one of the most important ranking
techniques used in today's search engines. A recent
very interesting research track focuses on exploiting
efficient numerical methods to speed up the computation
of PageRank, among which the Arnoldi-type algorithm and
the GMRES algorithm are competitive candidates. In
essence, the former deals with the PageRank problem
from an eigenproblem, while the latter from a linear
system, point of view. However, there is little known
about the relations between the two approaches for
PageRank. In this article, we focus on a theoretical
and numerical comparison of the two approaches.
Numerical experiments illustrate the effectiveness of
our theoretical results.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "Arnoldi; GMRES; Google; Krylov subspace; PageRank; Web
ranking",
}
@Article{Li:2010:LCG,
author = "Xiao Li and Ye-Yi Wang and Dou Shen and Alex Acero",
title = "Learning with click graph for query intent
classification",
journal = j-TOIS,
volume = "28",
number = "3",
pages = "12:1--12:??",
month = jun,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1777432.1777435",
ISSN = "1046-8188",
bibdate = "Tue Jul 6 15:53:00 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Topical query classification, as one step toward
understanding users' search intent, is gaining
increasing attention in information retrieval. Previous
works on this subject primarily focused on enrichment
of query features, for example, by augmenting queries
with search engine results. In this work, we
investigate a completely orthogonal approach ---
instead of improving feature representation, we aim at
drastically increasing the amount of training data. To
this end, we propose two semisupervised learning
methods that exploit user click-through data. In one
approach, we infer class memberships of unlabeled
queries from those of labeled ones according to their
proximities in a click graph; and then use these
automatically labeled queries to train classifiers
using query terms as features. In a second approach,
click graph learning and query classifier training are
conducted jointly with an integrated objective. Our
methods are evaluated in two applications, product
intent and job intent classification. In both cases, we
expand the training data by over two orders of
magnitude, leading to significant improvements in
classification performance. An additional finding is
that with a large amount of training data obtained in
this fashion, a classifier based on simple query term
features can outperform those using state-of-the-art,
augmented features.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "click graph; query classification; semisupervised
learning; user intent",
}
@Article{Harabagiu:2010:UTT,
author = "Sanda Harabagiu and Finley Lacatusu",
title = "Using topic themes for multi-document summarization",
journal = j-TOIS,
volume = "28",
number = "3",
pages = "13:1--13:??",
month = jun,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1777432.1777436",
ISSN = "1046-8188",
bibdate = "Tue Jul 6 15:53:00 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The problem of using topic representations for
multidocument summarization (MDS) has received
considerable attention recently. Several topic
representations have been employed for producing
informative and coherent summaries. In this article, we
describe five previously known topic representations
and introduce two novel representations of topics based
on topic themes. We present eight different methods of
generating multidocument summaries and evaluate each of
these methods on a large set of topics used in past DUC
workshops. Our evaluation results show a significant
improvement in the quality of summaries based on topic
themes over MDS methods that use other alternative
topic representations.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "summarization; topic representations; topic themes",
}
@Article{Maslennikov:2010:CRI,
author = "Mstislav Maslennikov and Tat-Seng Chua",
title = "Combining relations for information extraction from
free text",
journal = j-TOIS,
volume = "28",
number = "3",
pages = "14:1--14:??",
month = jun,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1777432.1777437",
ISSN = "1046-8188",
bibdate = "Tue Jul 6 15:53:00 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Relations between entities of the same semantic type
tend to be sparse in free texts. Therefore, combining
relations is the key to effective information
extraction (IE) on free text datasets with a small set
of training samples. Previous approaches to
bootstrapping for IE used different types of relations,
such as dependency or co-occurrence, and faced the
problems of paraphrasing and misalignment of instances.
To cope with these problems, we propose a framework
that integrates several types of relations. After
extracting candidate entities, our framework evaluates
relations between them at the phrasal, dependency,
semantic frame, and discourse levels. For each of these
levels, we build a classifier that outputs a score for
relation instances. In order to integrate these scores,
we propose three strategies: (1) integrate evaluation
scores from each relation classifier; (2) incorporate
the elimination of negatively labeled instances in a
previous strategy; and (3) add cascading of extracted
relations into strategy (1). Our framework improves the
state-of-art results for supervised systems by 8\%,
15\%, 3\%, and 5\% on MUC4 (terrorism); MUC6
(management succession); ACE RDC 2003 (news, general
types); and ACE RDC 2003 (news, specific types) domains
respectively.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "bootstrapping; dependency relations; discourse
relations; information extraction; semantic relations",
}
@Article{Lauw:2010:SST,
author = "Hady W. Lauw and Ee-Peng Lim and Hweehwa Pang and
Teck-Tim Tan",
title = "{STEvent}: {Spatio-temporal} event model for social
network discovery",
journal = j-TOIS,
volume = "28",
number = "3",
pages = "15:1--15:??",
month = jun,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1777432.1777438",
ISSN = "1046-8188",
bibdate = "Tue Jul 6 15:53:00 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Spatio-temporal data concerning the movement of
individuals over space and time contains latent
information on the associations among these
individuals. Sources of spatio-temporal data include
usage logs of mobile and Internet technologies. This
article defines a spatio-temporal event by the
co-occurrences among individuals that indicate
potential associations among them. Each spatio-temporal
event is assigned a weight based on the precision and
uniqueness of the event. By aggregating the weights of
events relating two individuals, we can determine the
strength of association between them. We conduct
extensive experimentation to investigate both the
efficacy of the proposed model as well as the
computational complexity of the proposed algorithms.
Experimental results on three real-life spatio-temporal
datasets cross-validate each other, lending greater
confidence on the reliability of our proposed model.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "data mining; social network; spatio-temporal
databases",
}
@Article{Ko:2010:PMA,
author = "Jeongwoo Ko and Luo Si and Eric Nyberg and Teruko
Mitamura",
title = "Probabilistic models for answer-ranking in
multilingual question-answering",
journal = j-TOIS,
volume = "28",
number = "3",
pages = "16:1--16:??",
month = jun,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1777432.1777439",
ISSN = "1046-8188",
bibdate = "Tue Jul 6 15:53:00 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article presents two probabilistic models for
answering ranking in the multilingual
question-answering (QA) task, which finds exact answers
to a natural language question written in different
languages. Although some probabilistic methods have
been utilized in traditional monolingual
answer-ranking, limited prior research has been
conducted for answer-ranking in multilingual
question-answering with formal methods. This article
first describes a probabilistic model that predicts the
probabilities of correctness for individual answers in
an independent way. It then proposes a novel
probabilistic method to jointly predict the correctness
of answers by considering both the correctness of
individual answers as well as their correlations. As
far as we know, this is the first probabilistic
framework that proposes to model the correctness and
correlation of answer candidates in multilingual
question-answering and provide a novel approach to
design a flexible and extensible system architecture
for answer selection in multilingual QA. An extensive
set of experiments were conducted to show the
effectiveness of the proposed probabilistic methods in
English-to-Chinese and English-to-Japanese
cross-lingual QA, as well as English, Chinese, and
Japanese monolingual QA using TREC and NTCIR
questions.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
keywords = "answer selection; answer-merging; answer-ranking;
probabilistic graphical model; question-answering",
}
@Article{Tan:2010:CBI,
author = "Qingzhao Tan and Prasenjit Mitra",
title = "Clustering-based incremental {Web} crawling",
journal = j-TOIS,
volume = "28",
number = "4",
pages = "17:1--17:??",
month = nov,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1852102.1852103",
ISSN = "1046-8188",
bibdate = "Tue Nov 23 10:24:49 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "When crawling resources, for example, number of
machines, crawl-time, and so on, are limited, so a
crawler has to decide an optimal order in which to
crawl and recrawl Web pages. Ideally, crawlers should
request only those Web pages that have changed since
the last crawl; in practice, a crawler may not know
whether a Web page has changed before downloading it.
In this article, we identify features of Web pages that
are correlated to their change frequency. We design a
crawling algorithm that clusters Web pages based on
features that correlate to their change frequencies
obtained by examining past history.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Kurland:2010:PHS,
author = "Oren Kurland and Lillian Lee",
title = "{PageRank} without hyperlinks: {Structural} reranking
using links induced by language models",
journal = j-TOIS,
volume = "28",
number = "4",
pages = "18:1--18:??",
month = nov,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1852102.1852104",
ISSN = "1046-8188",
bibdate = "Tue Nov 23 10:24:49 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The ad hoc retrieval task is to find documents in a
corpus that are relevant to a query. Inspired by the
PageRank and HITS (hubs and authorities) algorithms for
Web search, we propose a structural reranking approach
to ad-hoc retrieval that applies to settings with no
hyperlink information. We reorder the documents in an
initially retrieved set by exploiting implicit
asymmetric relationships among them. We consider
generation links, which indicate that the language
model induced from one document assigns high
probability to the text of another. We study a number
of reranking criteria based on measures of centrality
in the graphs formed by generation links, and show that
integrating centrality into standard
language-model-based retrieval is quite effective at
improving precision at top ranks; the best resultant
performance is comparable, and often superior, to that
of a state-of-the-art pseudo-feedback-based retrieval
approach.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Magalhaes:2010:ITF,
author = "Jo{\~a}o Magalh{\~a}es and Stefan R{\"u}ger",
title = "An information-theoretic framework for
semantic-multimedia retrieval",
journal = j-TOIS,
volume = "28",
number = "4",
pages = "19:1--19:??",
month = nov,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1852102.1852105",
ISSN = "1046-8188",
bibdate = "Tue Nov 23 10:24:49 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article is set in the context of searching text
and image repositories by keyword. We develop a unified
probabilistic framework for text, image, and combined
text and image retrieval that is based on the detection
of keywords (concepts) using automated image annotation
technology. Our framework is deeply rooted in
information theory and lends itself to use with other
media types. We estimate a statistical model in a
multimodal feature space for each possible query
keyword. The key element of our framework is to
identify feature space transformations that make them
comparable in complexity and density. We select the
optimal multimodal feature space with a minimum
description length criterion from a set of candidate
feature spaces that are computed with the
average-mutual-information criterion for the text part
and hierarchical expectation maximization for the
visual part of the data.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Webber:2010:SMI,
author = "William Webber and Alistair Moffat and Justin Zobel",
title = "A similarity measure for indefinite rankings",
journal = j-TOIS,
volume = "28",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1852102.1852106",
ISSN = "1046-8188",
bibdate = "Tue Nov 23 10:24:49 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Ranked lists are encountered in research and daily
life and it is often of interest to compare these lists
even when they are incomplete or have only some members
in common. An example is document rankings returned for
the same query by different search engines. A measure
of the similarity between incomplete rankings should
handle nonconjointness, weight high ranks more heavily
than low, and be monotonic with increasing depth of
evaluation; but no measure satisfying all these
criteria currently exists. In this article, we propose
a new measure having these qualities, namely
rank-biased overlap (RBO). The RBO measure is based on
a simple probabilistic user model.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Clements:2010:TDE,
author = "Maarten Clements and Arjen P. {De Vries} and Marcel J.
T. Reinders",
title = "The task-dependent effect of tags and ratings on
social media access",
journal = j-TOIS,
volume = "28",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1852102.1852107",
ISSN = "1046-8188",
bibdate = "Tue Nov 23 10:24:49 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Recently, online social networks have emerged that
allow people to share their multimedia files, retrieve
interesting content, and discover like-minded people.
These systems often provide the possibility to annotate
the content with tags and ratings. Using a random walk
through the social annotation graph, we have combined
these annotations into a retrieval model that
effectively balances the personal preferences and
opinions of like-minded users into a single relevance
ranking for either content, tags, or people. We use
this model to identify the influence of different
annotation methods and system design aspects on common
ranking tasks in social content systems. Our results
show that a combination of rating and tagging
information can improve tasks like search and
recommendation.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Huang:2010:MND,
author = "Zi Huang and Bo Hu and Hong Cheng and Heng Tao Shen
and Hongyan Liu and Xiaofang Zhou",
title = "Mining near-duplicate graph for cluster-based
reranking of {Web} video search results",
journal = j-TOIS,
volume = "28",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1852102.1852108",
ISSN = "1046-8188",
bibdate = "Tue Nov 23 10:24:49 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Recently, video search reranking has been an effective
mechanism to improve the initial text-based ranking
list by incorporating visual consistency among the
result videos. While existing methods attempt to rerank
all the individual result videos, they suffer from
several drawbacks. In this article, we propose a new
video reranking paradigm called cluster-based video
reranking (CVR). The idea is to first construct a video
near-duplicate graph representing the visual similarity
relationship among videos, followed by identifying the
near-duplicate clusters from the video near-duplicate
graph, then ranking the obtained near-duplicate
clusters based on cluster properties and intercluster
links, and finally for each ranked cluster, a
representative video is selected and returned.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Culpepper:2010:ESI,
author = "J. Shane Culpepper and Alistair Moffat",
title = "Efficient set intersection for inverted indexing",
journal = j-TOIS,
volume = "29",
number = "1",
pages = "1:1--1:??",
month = dec,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1877766.1877767",
ISSN = "1046-8188",
bibdate = "Thu Dec 23 17:15:03 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Conjunctive Boolean queries are a key component of
modern information retrieval systems, especially when
Web-scale repositories are being searched. A
conjunctive query q is equivalent to a $|q|$-way
intersection over ordered sets of integers, where each
set represents the documents containing one of the
terms, and each integer in each set is an ordinal
document identifier. As is the case with many computing
applications, there is tension between the way in which
the data is represented, and the ways in which it is to
be manipulated. In particular, the sets representing
index data for typical document collections are highly
compressible, but are processed using random access
techniques, meaning that methods for carrying out set
intersections must be alert to issues to do with access
patterns and data representation.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Transier:2010:EBA,
author = "Frederik Transier and Peter Sanders",
title = "Engineering basic algorithms of an in-memory text
search engine",
journal = j-TOIS,
volume = "29",
number = "1",
pages = "2:1--2:??",
month = dec,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1877766.1877768",
ISSN = "1046-8188",
bibdate = "Thu Dec 23 17:15:03 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Inverted index data structures are the key to fast
text search engines. We first investigate one of the
predominant operation on inverted indexes, which asks
for intersecting two sorted lists of document IDs of
different lengths. We explore compression and
performance of different inverted list data structures.
In particular, we present Lookup, a new data structure
that allows intersection in expected time linear in the
smaller list. Based on this result, we present the
algorithmic core of a full text data base that allows
fast Boolean queries, phrase queries, and document
reporting using less space than the input text. The
system uses a carefully choreographed combination of
classical data compression techniques and
inverted-index-based search data structures.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Krikon:2010:UIP,
author = "Eyal Krikon and Oren Kurland and Michael Bendersky",
title = "Utilizing inter-passage and inter-document
similarities for reranking search results",
journal = j-TOIS,
volume = "29",
number = "1",
pages = "3:1--3:??",
month = dec,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1877766.1877769",
ISSN = "1046-8188",
bibdate = "Thu Dec 23 17:15:03 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We present a novel language-model-based approach to
reranking search results; that is, reordering the
documents in an initially retrieved list so as to
improve precision at top ranks. Our model integrates
whole-document information with that induced from
passages. Specifically, inter-passage, inter-document,
and query-based similarities, which constitute a rich
source of information, are combined in our model.
Empirical evaluation shows that the
precision-at-top-ranks performance of our model is
substantially better than that of the initial ranking
upon which reranking is performed. Furthermore, the
performance is substantially better than that of a
commonly used passage-based document ranking method
that does not exploit inter-item similarities.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Minkov:2010:IGW,
author = "Einat Minkov and William W. Cohen",
title = "Improving graph-walk-based similarity with reranking:
{Case} studies for personal information management",
journal = j-TOIS,
volume = "29",
number = "1",
pages = "4:1--4:??",
month = dec,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1877766.1877770",
ISSN = "1046-8188",
bibdate = "Thu Dec 23 17:15:03 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Relational or semistructured data is naturally
represented by a graph, where nodes denote entities and
directed typed edges represent the relations between
them. Such graphs are heterogeneous, describing
different types of objects and links. We represent
personal information as a graph that includes messages,
terms, persons, dates, and other object types, and
relations like sent-to and has-term. Given the graph,
we apply finite random graph walks to induce a measure
of entity similarity, which can be viewed as a tool for
performing search in the graph. Experiments conducted
using personal email collections derived from the Enron
corpus and other corpora show how the different tasks
of alias finding, threading, and person name
disambiguation can be all addressed as search queries
in this framework, where the graph-walk-based
similarity metric is preferable to alternative
approaches, and further improvements are achieved with
learning.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{DellAmico:2010:DFP,
author = "Matteo Dell'Amico and Licia Capra",
title = "Dependable filtering: {Philosophy} and realizations",
journal = j-TOIS,
volume = "29",
number = "1",
pages = "5:1--5:??",
month = dec,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1877766.1877771",
ISSN = "1046-8188",
bibdate = "Thu Dec 23 17:15:03 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Digital content production and distribution has
radically changed our business models. An unprecedented
volume of supply is now on offer, whetted by the demand
of millions of users from all over the world. Since
users cannot be expected to browse through millions of
different items to find what they might like, filtering
has become a popular technique to connect supply and
demand: trusted users are first identified, and their
opinions are then used to create recommendations. In
this domain, users' trustworthiness has been measured
according to one of the following two criteria: taste
similarity (i.e., ``I trust those who agree with me''),
or social ties (i.e., ``I trust my friends, and the
people that my friends trust'').",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Choudhury:2010:ECU,
author = "Munmun De Choudhury and Hari Sundaram and Ajita John
and Doree Duncan Seligmann",
title = "Extraction, characterization and utility of
prototypical communication groups in the blogosphere",
journal = j-TOIS,
volume = "29",
number = "1",
pages = "6:1--6:??",
month = dec,
year = "2010",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1877766.1877772",
ISSN = "1046-8188",
bibdate = "Thu Dec 23 17:15:03 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article analyzes communication within a set of
individuals to extract the representative prototypical
groups and provides a novel framework to establish the
utility of such groups. Corporations may want to
identify representative groups (which are indicative of
the overall communication set) because it is easier to
track the prototypical groups rather than the entire
set. This can be useful for advertising, identifying
``hot'' spots of resource consumption as well as in
mining representative moods or temperature of a
community. Our framework has three parts: extraction,
characterization, and utility of prototypical groups.
First, we extract groups by developing features
representing communication dynamics of the
individuals.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Fang:2011:DEI,
author = "Hui Fang and Tao Tao and Chengxiang Zhai",
title = "Diagnostic Evaluation of Information Retrieval
Models",
journal = j-TOIS,
volume = "29",
number = "2",
pages = "7:1--7:??",
month = apr,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1961209.1961210",
ISSN = "1046-8188",
bibdate = "Tue May 3 17:57:26 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Developing effective retrieval models is a
long-standing central challenge in information
retrieval research. In order to develop more effective
models, it is necessary to understand the deficiencies
of the current retrieval models and the relative
strengths of each of them. In this article, we propose
a general methodology to analytically and
experimentally diagnose the weaknesses of a retrieval
function, which provides guidance on how to further
improve its performance. Our methodology is motivated
by the empirical observation that good retrieval
performance is closely related to the use of various
retrieval heuristics. We connect the weaknesses and
strengths of a retrieval function with its
implementations of these retrieval heuristics, and
propose two strategies to check how well a retrieval
function implements the desired retrieval heuristics.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Egozi:2011:CBI,
author = "Ofer Egozi and Shaul Markovitch and Evgeniy
Gabrilovich",
title = "Concept-Based Information Retrieval Using Explicit
Semantic Analysis",
journal = j-TOIS,
volume = "29",
number = "2",
pages = "8:1--8:??",
month = apr,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1961209.1961211",
ISSN = "1046-8188",
bibdate = "Tue May 3 17:57:26 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Information retrieval systems traditionally rely on
textual keywords to index and retrieve documents.
Keyword-based retrieval may return inaccurate and
incomplete results when different keywords are used to
describe the same concept in the documents and in the
queries. Furthermore, the relationship between these
related keywords may be semantic rather than syntactic,
and capturing it thus requires access to comprehensive
human world knowledge. Concept-based retrieval methods
have attempted to tackle these difficulties by using
manually built thesauri, by relying on term
cooccurrence data, or by extracting latent word
relationships and concepts from a corpus. In this
article we introduce a new concept-based retrieval
approach based on Explicit Semantic Analysis (ESA), a
recently proposed method that augments keyword-based
text representation with concept-based features,
automatically extracted from massive human knowledge
repositories such as Wikipedia.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ma:2011:IRS,
author = "Hao Ma and Tom Chao Zhou and Michael R. Lyu and Irwin
King",
title = "Improving Recommender Systems by Incorporating Social
Contextual Information",
journal = j-TOIS,
volume = "29",
number = "2",
pages = "9:1--9:??",
month = apr,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1961209.1961212",
ISSN = "1046-8188",
bibdate = "Tue May 3 17:57:26 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Due to their potential commercial value and the
associated great research challenges, recommender
systems have been extensively studied by both academia
and industry recently. However, the data sparsity
problem of the involved user-item matrix seriously
affects the recommendation quality. Many existing
approaches to recommender systems cannot easily deal
with users who have made very few ratings. In view of
the exponential growth of information generated by
online users, social contextual information analysis is
becoming important for many Web applications. In this
article, we propose a factor analysis approach based on
probabilistic matrix factorization to alleviate the
data sparsity and poor prediction accuracy problems by
incorporating social contextual information, such as
social networks and social tags.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Mei:2011:CVR,
author = "Tao Mei and Bo Yang and Xian-Sheng Hua and Shipeng
Li",
title = "Contextual Video Recommendation by Multimodal
Relevance and User Feedback",
journal = j-TOIS,
volume = "29",
number = "2",
pages = "10:1--10:??",
month = apr,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1961209.1961213",
ISSN = "1046-8188",
bibdate = "Tue May 3 17:57:26 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With Internet delivery of video content surging to an
unprecedented level, video recommendation, which
suggests relevant videos to targeted users according to
their historical and current viewings or preferences,
has become one of most pervasive online video services.
This article presents a novel contextual video
recommendation system, called VideoReach, based on
multimodal content relevance and user feedback. We
consider an online video usually consists of different
modalities (i.e., visual and audio track, as well as
associated texts such as query, keywords, and
surrounding text). Therefore, the recommended videos
should be relevant to current viewing in terms of
multimodal relevance. We also consider that different
parts of videos are with different degrees of interest
to a user, as well as different features and modalities
have different contributions to the overall
relevance.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Vallet:2011:EUB,
author = "David Vallet and Frank Hopfgartner and Joemon M. Jose
and Pablo Castells",
title = "Effects of Usage-Based Feedback on Video Retrieval:
{A} Simulation-Based Study",
journal = j-TOIS,
volume = "29",
number = "2",
pages = "11:1--11:??",
month = apr,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1961209.1961214",
ISSN = "1046-8188",
bibdate = "Tue May 3 17:57:26 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We present a model for exploiting community-based
usage information for video retrieval, where implicit
usage information from past users is exploited in order
to provide enhanced assistance in video retrieval
tasks, and alleviate the effects of the semantic gap
problem. We propose a graph-based model for all types
of implicit and explicit feedback, in which the
relevant usage information is represented. Our model is
designed to capture the complex interactions of a user
with an interactive video retrieval system, including
the representation of sequences of user-system
interaction during a search session. Building upon this
model, four recommendation strategies are defined and
evaluated.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Sun:2011:IIR,
author = "Bingjun Sun and Prasenjit Mitra and C. Lee Giles and
Karl T. Mueller",
title = "Identifying, Indexing, and Ranking Chemical Formulae
and Chemical Names in Digital Documents",
journal = j-TOIS,
volume = "29",
number = "2",
pages = "12:1--12:??",
month = apr,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1961209.1961215",
ISSN = "1046-8188",
bibdate = "Tue May 3 17:57:26 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "End-users utilize chemical search engines to search
for chemical formulae and chemical names. Chemical
search engines identify and index chemical formulae and
chemical names appearing in text documents to support
efficient search and retrieval in the future.
Identifying chemical formulae and chemical names in
text automatically has been a hard problem that has met
with varying degrees of success in the past. We propose
algorithms for chemical formula and chemical name
tagging using Conditional Random Fields (CRFs) and
Support Vector Machines (SVMs) that achieve higher
accuracy than existing (published) methods. After
chemical entities have been identified in text
documents, they must be indexed.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{SanPedro:2011:CRY,
author = "Jose {San Pedro} and Stefan Siersdorfer and Mark
Sanderson",
title = "Content redundancy in {YouTube} and its application to
video tagging",
journal = j-TOIS,
volume = "29",
number = "3",
pages = "13:1--13:??",
month = jul,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1993036.1993037",
ISSN = "1046-8188",
bibdate = "Tue Jul 19 18:04:21 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The emergence of large-scale social Web communities
has enabled users to share online vast amounts of
multimedia content. An analysis of YouTube reveals a
high amount of redundancy, in the form of videos with
overlapping or duplicated content. We use robust
content-based video analysis techniques to detect
overlapping sequences between videos. Based on the
output of these techniques, we present an in-depth
study of duplication and content overlap in YouTube,
and analyze various dependencies between content
overlap and meta data such as video titles, views,
video ratings, and tags. As an application, we show
that content-based links provide useful information for
generating new tag assignments.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Schedl:2011:EMS,
author = "Markus Schedl and Tim Pohle and Peter Knees and
Gerhard Widmer",
title = "Exploring the music similarity space on the {Web}",
journal = j-TOIS,
volume = "29",
number = "3",
pages = "14:1--14:??",
month = jul,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1993036.1993038",
ISSN = "1046-8188",
bibdate = "Tue Jul 19 18:04:21 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article comprehensively addresses the problem of
similarity measurement between music artists via
text-based features extracted from Web pages. To this
end, we present a thorough evaluation of different
term-weighting strategies, normalization methods,
aggregation functions, and similarity measurement
techniques. In large-scale genre classification
experiments carried out on real-world artist
collections, we analyze several thousand combinations
of settings/parameters that influence the similarity
calculation process, and investigate in which way they
impact the quality of the similarity estimates.
Accurate similarity measures for music are vital for
many applications, such as automated playlist
generation, music recommender systems, music
information systems, or intelligent user interfaces to
access music collections by means beyond text-based
browsing.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yan:2011:TSG,
author = "Xin Yan and Raymond Y. K. Lau and Dawei Song and Xue
Li and Jian Ma",
title = "Toward a semantic granularity model for
domain-specific information retrieval",
journal = j-TOIS,
volume = "29",
number = "3",
pages = "15:1--15:??",
month = jul,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1993036.1993039",
ISSN = "1046-8188",
bibdate = "Tue Jul 19 18:04:21 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Both similarity-based and popularity-based document
ranking functions have been successfully applied to
information retrieval (IR) in general. However, the
dimension of semantic granularity also should be
considered for effective retrieval. In this article, we
propose a semantic granularity-based IR model that
takes into account the three dimensions, namely
similarity, popularity, and semantic granularity, to
improve domain-specific search. In particular, a
concept-based computational model is developed to
estimate the semantic granularity of documents with
reference to a domain ontology. Semantic granularity
refers to the levels of semantic detail carried by an
information item. The results of our benchmark
experiments confirm that the proposed semantic
granularity based IR model performs significantly
better than the similarity-based baseline in both a
bio-medical and an agricultural domain.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bast:2011:FCH,
author = "Hannah Bast and Marjan Celikik",
title = "Fast construction of the {HYB} index",
journal = j-TOIS,
volume = "29",
number = "3",
pages = "16:1--16:??",
month = jul,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/1993036.1993040",
ISSN = "1046-8188",
bibdate = "Tue Jul 19 18:04:21 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "As shown in a series of recent works, the HYB index is
an alternative to the inverted index (INV) that enables
very fast prefix searches, which in turn is the basis
for fast processing of many other types of advanced
queries, including autocompletion, faceted search,
error-tolerant search, database-style select and join,
and semantic search. In this work we show that HYB can
be constructed at least as fast as INV, and often up to
twice as fast. This is because HYB, by its nature,
requires only a half-inversion of the data and allows
an efficient in-place instead of the traditional
merge-based index construction.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Macdonald:2011:UBA,
author = "Craig Macdonald and Iadh Ounis and Nicola Tonellotto",
title = "Upper-bound approximations for dynamic pruning",
journal = j-TOIS,
volume = "29",
number = "4",
pages = "17:1--17:??",
month = dec,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2037661.2037662",
ISSN = "1046-8188",
bibdate = "Thu Dec 15 09:18:39 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Dynamic pruning strategies for information retrieval
systems can increase querying efficiency without
decreasing effectiveness by using upper bounds to
safely omit scoring documents that are unlikely to make
the final retrieved set. Often, such upper bounds are
pre-calculated at indexing time for a given weighting
model. However, this precludes changing, adapting or
training the weighting model without recalculating the
upper bounds. Instead, upper bounds should be
approximated at querying time from various statistics
of each term to allow on-the-fly adaptation of the
applied retrieval strategy. This article, by using
uniform notation, formulates the problem of determining
a term upper-bound given a weighting model and
discusses the limitations of existing approximations.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chen:2011:RFA,
author = "Keke Chen and Jing Bai and Zhaohui Zheng",
title = "Ranking function adaptation with boosting trees",
journal = j-TOIS,
volume = "29",
number = "4",
pages = "18:1--18:??",
month = dec,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2037661.2037663",
ISSN = "1046-8188",
bibdate = "Thu Dec 15 09:18:39 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Machine-learned ranking functions have shown successes
in Web search engines. With the increasing demands on
developing effective ranking functions for different
search domains, we have seen a big bottleneck, that is,
the problem of insufficient labeled training data,
which has significantly slowed the development and
deployment of machine-learned ranking functions for
different domains. There are two possible approaches to
address this problem: (1) combining labeled training
data from similar domains with the small target-domain
labeled data for training or (2) using pairwise
preference data extracted from user clickthrough log
for the target domain for training. In this article, we
propose a new approach called tree-based ranking
function adaptation (Trada) to effectively utilize
these data sources for training cross-domain ranking
functions.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Paik:2011:GEE,
author = "Jiaul H. Paik and Mandar Mitra and Swapan K. Parui and
Kalervo J{\"a}rvelin",
title = "{GRAS}: an effective and efficient stemming algorithm
for information retrieval",
journal = j-TOIS,
volume = "29",
number = "4",
pages = "19:1--19:??",
month = dec,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2037661.2037664",
ISSN = "1046-8188",
bibdate = "Thu Dec 15 09:18:39 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "A novel graph-based language-independent stemming
algorithm suitable for information retrieval is
proposed in this article. The main features of the
algorithm are retrieval effectiveness, generality, and
computational efficiency. We test our approach on seven
languages (using collections from the TREC, CLEF, and
FIRE evaluation platforms) of varying morphological
complexity. Significant performance improvement over
plain word-based retrieval, three other
language-independent morphological normalizers, as well
as rule-based stemmers is demonstrated.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Parameswaran:2011:RSC,
author = "Aditya Parameswaran and Petros Venetis and Hector
Garcia-Molina",
title = "Recommendation systems with complex constraints: a
course recommendation perspective",
journal = j-TOIS,
volume = "29",
number = "4",
pages = "20:1--20:??",
month = dec,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2037661.2037665",
ISSN = "1046-8188",
bibdate = "Thu Dec 15 09:18:39 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We study the problem of making recommendations when
the objects to be recommended must also satisfy
constraints or requirements. In particular, we focus on
course recommendations: the courses taken by a student
must satisfy requirements (e.g., take two out of a set
of five math courses) in order for the student to
graduate. Our work is done in the context of the
CourseRank system, used by students to plan their
academic program at Stanford University. Our goal is to
recommend to these students courses that not only help
satisfy constraints, but that are also desirable (e.g.,
popular or taken by similar students).",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2011:CBR,
author = "Jiajun Liu and Zi Huang and Heng Tao Shen and Bin
Cui",
title = "Correlation-based retrieval for heavily changed
near-duplicate videos",
journal = j-TOIS,
volume = "29",
number = "4",
pages = "21:1--21:??",
month = dec,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2037661.2037666",
ISSN = "1046-8188",
bibdate = "Thu Dec 15 09:18:39 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The unprecedented and ever-growing number of Web
videos nowadays leads to the massive existence of
near-duplicate videos. Very often, some near-duplicate
videos exhibit great content changes, while the user
perceives little information change, for example, color
features change significantly when transforming a color
video with a blue filter. These feature changes
contribute to low-level video similarity computations,
making conventional similarity-based near-duplicate
video retrieval techniques incapable of accurately
capturing the implicit relationship between two
near-duplicate videos with fairly large content
modifications. In this paper, we introduce a new
dimension for near-duplicate video retrieval. Different
from existing near-duplicate video retrieval approaches
which are based on video-content similarity, we explore
the correlation between two videos.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Balog:2011:QME,
author = "Krisztian Balog and Marc Bron and Maarten {De Rijke}",
title = "Query modeling for entity search based on terms,
categories, and examples",
journal = j-TOIS,
volume = "29",
number = "4",
pages = "22:1--22:??",
month = dec,
year = "2011",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2037661.2037667",
ISSN = "1046-8188",
bibdate = "Thu Dec 15 09:18:39 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Users often search for entities instead of documents,
and in this setting, are willing to provide extra
input, in addition to a series of query terms, such as
category information and example entities. We propose a
general probabilistic framework for entity search to
evaluate and provide insights in the many ways of using
these types of input for query modeling. We focus on
the use of category information and show the advantage
of a category-based representation over a term-based
representation, and also demonstrate the effectiveness
of category-based expansion using example entities.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Farina:2012:WBS,
author = "Antonio Fari{\~n}a and Nieves R. Brisaboa and Gonzalo
Navarro and Francisco Claude and {\'A}ngeles S. Places
and Eduardo Rodr{\'\i}guez",
title = "Word-based self-indexes for natural language text",
journal = j-TOIS,
volume = "30",
number = "1",
pages = "1:1--1:??",
month = feb,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2094072.2094073",
ISSN = "1046-8188",
bibdate = "Wed Feb 29 16:22:15 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The inverted index supports efficient full-text
searches on natural language text collections. It
requires some extra space over the compressed text that
can be traded for search speed. It is usually fast for
single-word searches, yet phrase searches require more
expensive intersections. In this article we introduce a
different kind of index. It replaces the text using
essentially the same space required by the compressed
text alone (compression ratio around 35\%). Within this
space it supports not only decompression of arbitrary
passages, but efficient word and phrase searches.
Searches are orders of magnitude faster than those over
inverted indexes when looking for phrases, and still
faster on single-word searches when little space is
available.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Altingovde:2012:SIP,
author = "Ismail S. Altingovde and Rifat Ozcan and {\"O}zg{\"u}r
Ulusoy",
title = "Static index pruning in {Web} search engines: Combining
term and document popularities with query views",
journal = j-TOIS,
volume = "30",
number = "1",
pages = "2:1--2:??",
month = feb,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2094072.2094074",
ISSN = "1046-8188",
bibdate = "Wed Feb 29 16:22:15 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Static index pruning techniques permanently remove a
presumably redundant part of an inverted file, to
reduce the file size and query processing time. These
techniques differ in deciding which parts of an index
can be removed safely; that is, without changing the
top-ranked query results. As defined in the literature,
the query view of a document is the set of query terms
that access to this particular document, that is,
retrieves this document among its top results. In this
paper, we first propose using query views to improve
the quality of the top results compared against the
original results. We incorporate query views in a
number of static pruning strategies, namely
term-centric, document-centric, term popularity based
and document access popularity based approaches, and
show that the new strategies considerably outperform
their counterparts especially for the higher levels of
pruning and for both disjunctive and conjunctive query
processing.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bhatia:2012:SFT,
author = "Sumit Bhatia and Prasenjit Mitra",
title = "Summarizing figures, tables, and algorithms in
scientific publications to augment search results",
journal = j-TOIS,
volume = "30",
number = "1",
pages = "3:1--3:??",
month = feb,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2094072.2094075",
ISSN = "1046-8188",
bibdate = "Wed Feb 29 16:22:15 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Increasingly, special-purpose search engines are being
built to enable the retrieval of document-elements like
tables, figures, and algorithms [Bhatia et al. 2010;
Liu et al. 2007; Hearst et al. 2007]. These search
engines present a thumbnail view of document-elements,
some document metadata such as the title of the papers
and their authors, and the caption of the
document-element. While some authors in some
disciplines write carefully tailored captions,
generally, the author of a document assumes that the
caption will be read in the context of the text in the
document. When the caption is presented out of context
as in a document-element-search-engine result, it may
not contain enough information to help the end-user
understand what the content of the document-element
is.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Carterette:2012:MTS,
author = "Benjamin A. Carterette",
title = "Multiple testing in statistical analysis of
systems-based information retrieval experiments",
journal = j-TOIS,
volume = "30",
number = "1",
pages = "4:1--4:??",
month = feb,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2094072.2094076",
ISSN = "1046-8188",
bibdate = "Wed Feb 29 16:22:15 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "High-quality reusable test collections and formal
statistical hypothesis testing together support a
rigorous experimental environment for information
retrieval research. But as Armstrong et al. [2009b]
recently argued, global analysis of experiments
suggests that there has actually been little real
improvement in ad hoc retrieval effectiveness over
time. We investigate this phenomenon in the context of
simultaneous testing of many hypotheses using a fixed
set of data. We argue that the most common approaches
to significance testing ignore a great deal of
information about the world. Taking into account even a
fairly small amount of this information can lead to
very different conclusions about systems than those
that have appeared in published literature.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Broschart:2012:HPP,
author = "Andreas Broschart and Ralf Schenkel",
title = "High-performance processing of text queries with
tunable pruned term and term pair indexes",
journal = j-TOIS,
volume = "30",
number = "1",
pages = "5:1--5:??",
month = feb,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2094072.2094077",
ISSN = "1046-8188",
bibdate = "Wed Feb 29 16:22:15 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Term proximity scoring is an established means in
information retrieval for improving result quality of
full-text queries. Integrating such proximity scores
into efficient query processing, however, has not been
equally well studied. Existing methods make use of
precomputed lists of documents where tuples of terms,
usually pairs, occur together, usually incurring a huge
index size compared to term-only indexes. This article
introduces a joint framework for trading off index size
and result quality, and provides optimization
techniques for tuning precomputed indexes towards
either maximal result quality or maximal query
processing performance under controlled result quality,
given an upper bound for the index size.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chapelle:2012:LSV,
author = "Olivier Chapelle and Thorsten Joachims and Filip
Radlinski and Yisong Yue",
title = "Large-scale validation and analysis of interleaved
search evaluation",
journal = j-TOIS,
volume = "30",
number = "1",
pages = "6:1--6:??",
month = feb,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2094072.2094078",
ISSN = "1046-8188",
bibdate = "Wed Feb 29 16:22:15 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Interleaving is an increasingly popular technique for
evaluating information retrieval systems based on
implicit user feedback. While a number of isolated
studies have analyzed how this technique agrees with
conventional offline evaluation approaches and other
online techniques, a complete picture of its efficiency
and effectiveness is still lacking. In this paper we
extend and combine the body of empirical evidence
regarding interleaving, and provide a comprehensive
analysis of interleaving using data from two major
commercial search engines and a retrieval system for
scientific literature. In particular, we analyze the
agreement of interleaving with manual relevance
judgments and observational implicit feedback measures,
estimate the statistical efficiency of interleaving,
and explore the relative performance of different
interleaving variants.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cao:2012:AEC,
author = "Xin Cao and Gao Cong and Bin Cui and Christian S.
Jensen and Quan Yuan",
title = "Approaches to Exploring Category Information for
Question Retrieval in Community Question-Answer
Archives",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "7:1--7:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180869",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Community Question Answering (CQA) is a popular type
of service where users ask questions and where answers
are obtained from other users or from historical
question-answer pairs. CQA archives contain large
volumes of questions organized into a hierarchy of
categories. As an essential function of CQA services,
question retrieval in a CQA archive aims to retrieve
historical question-answer pairs that are relevant to a
query question. This article presents several new
approaches to exploiting the category information of
questions for improving the performance of question
retrieval, and it applies these approaches to existing
question retrieval models, including a state-of-the-art
question retrieval model. Experiments conducted on real
CQA data demonstrate that the proposed techniques are
effective and efficient and are capable of
outperforming a variety of baseline methods
significantly.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Miotto:2012:PMC,
author = "Riccardo Miotto and Nicola Orio",
title = "A Probabilistic Model to Combine Tags and Acoustic
Similarity for Music Retrieval",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "8:1--8:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180870",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The rise of the Internet has led the music industry to
a transition from physical media to online products and
services. As a consequence, current online music
collections store millions of songs and are constantly
being enriched with new content. This has created a
need for music technologies that allow users to
interact with these extensive collections efficiently
and effectively. Music search and discovery may be
carried out using tags, matching user interests and
exploiting content-based acoustic similarity. One major
issue in music information retrieval is how to combine
such noisy and heterogeneous information sources in
order to improve retrieval effectiveness. With this aim
in mind, the article explores a novel music retrieval
framework based on combining tags and acoustic
similarity through a probabilistic graph-based
representation of a collection of songs. The retrieval
function highlights the path across the graph that most
likely observes a user query and is used to improve
state-of-the-art music search and discovery engines by
delivering more relevant ranking lists. Indeed, by
means of an empirical evaluation, we show how the
proposed approach leads to better performances than
retrieval strategies which rank songs according to
individual information sources alone or which use a
combination of them.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tigelaar:2012:PPI,
author = "Almer S. Tigelaar and Djoerd Hiemstra and Dolf
Trieschnigg",
title = "Peer-to-Peer Information Retrieval: An Overview",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "9:1--9:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180871",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Peer-to-peer technology is widely used for file
sharing. In the past decade a number of prototype
peer-to-peer information retrieval systems have been
developed. Unfortunately, none of these has seen
widespread real-world adoption and thus, in contrast
with file sharing, information retrieval is still
dominated by centralized solutions. In this article we
provide an overview of the key challenges for
peer-to-peer information retrieval and the work done so
far. We want to stimulate and inspire further research
to overcome these challenges. This will open the door
to the development and large-scale deployment of
real-world peer-to-peer information retrieval systems
that rival existing centralized client-server solutions
in terms of scalability, performance, user
satisfaction, and freedom.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pal:2012:EQS,
author = "Aditya Pal and F. Maxwell Harper and Joseph A.
Konstan",
title = "Exploring Question Selection Bias to Identify Experts
and Potential Experts in Community Question Answering",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "10:1--10:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180872",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Community Question Answering (CQA) services enable
their users to exchange knowledge in the form of
questions and answers. These communities thrive as a
result of a small number of highly active users,
typically called experts, who provide a large number of
high-quality useful answers. Expert identification
techniques enable community managers to take measures
to retain the experts in the community. There is
further value in identifying the experts during the
first few weeks of their participation as it would
allow measures to nurture and retain them. In this
article we address two problems: (a) How to identify
current experts in CQA? and (b) How to identify users
who have potential of becoming experts in future
(potential experts)? In particular, we propose a
probabilistic model that captures the selection
preferences of users based on the questions they choose
for answering. The probabilistic model allows us to run
machine learning methods for identifying experts and
potential experts. Our results over several popular CQA
datasets indicate that experts differ considerably from
ordinary users in their selection preferences; enabling
us to predict experts with higher accuracy over several
baseline models. We show that selection preferences can
be combined with baseline measures to improve the
predictive performance even further.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Shtok:2012:PQP,
author = "Anna Shtok and Oren Kurland and David Carmel and Fiana
Raiber and Gad Markovits",
title = "Predicting Query Performance by Query-Drift
Estimation",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "11:1--11:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180873",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Predicting query performance, that is, the
effectiveness of a search performed in response to a
query, is a highly important and challenging problem.
We present a novel approach to this task that is based
on measuring the standard deviation of retrieval scores
in the result list of the documents most highly ranked.
We argue that for retrieval methods that are based on
document-query surface-level similarities, the standard
deviation can serve as a surrogate for estimating the
presumed amount of query drift in the result list, that
is, the presence (and dominance) of aspects or topics
not related to the query in documents in the list.
Empirical evaluation demonstrates the prediction
effectiveness of our approach for several retrieval
models. Specifically, the prediction quality often
transcends that of current state-of-the-art prediction
methods.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Savoy:2012:AAB,
author = "Jacques Savoy",
title = "Authorship Attribution Based on Specific Vocabulary",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "12:1--12:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180874",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In this article we propose a technique for computing a
standardized Z score capable of defining the specific
vocabulary found in a text (or part thereof) compared
to that of an entire corpus. Assuming that the term
occurrence follows a binomial distribution, this method
is then applied to weight terms (words and punctuation
symbols in the current study), representing the lexical
specificity of the underlying text. In a final stage,
to define an author profile we suggest averaging these
text representations and then applying them along with
a distance measure to derive a simple and efficient
authorship attribution scheme. To evaluate this
algorithm and demonstrate its effectiveness, we develop
two experiments, the first based on 5,408 newspaper
articles ( Glasgow Herald ) written in English by 20
distinct authors and the second on 4,326 newspaper
articles ( La Stampa ) written in Italian by 20
distinct authors. These experiments demonstrate that
the suggested classification scheme tends to perform
better than the Delta rule method based on the most
frequent words, better than the chi-square distance
based on word profiles and punctuation marks, better
than the KLD scheme based on a predefined set of words,
and better than the na{\"\i}ve Bayes approach.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Nie:2012:OIS,
author = "Liqiang Nie and Meng Wang and Zheng-Jun Zha and
Tat-Seng Chua",
title = "Oracle in Image Search: a Content-Based Approach to
Performance Prediction",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "13:1--13:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180875",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article studies a novel problem in image search.
Given a text query and the image ranking list returned
by an image search system, we propose an approach to
automatically predict the search performance. We
demonstrate that, in order to estimate the mathematical
expectations of Average Precision (AP) and Normalized
Discounted Cumulative Gain (NDCG), we only need to
predict the relevance probability of each image. We
accomplish the task with a query-adaptive graph-based
learning based on the images' ranking order and visual
content. We validate our approach with a large-scale
dataset that contains the image search results of 1,165
queries from 4 popular image search engines. Empirical
studies demonstrate that our approach is able to
generate predictions that are highly correlated with
the real search performance. Based on the proposed
image search performance prediction scheme, we
introduce three applications: image metasearch,
multilingual image search, and Boolean image search.
Comprehensive experiments are conducted to validate our
approach.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Guttenbrunner:2012:MFE,
author = "Mark Guttenbrunner and Andreas Rauber",
title = "A Measurement Framework for Evaluating Emulators for
Digital Preservation",
journal = j-TOIS,
volume = "30",
number = "2",
pages = "14:1--14:??",
month = may,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2180868.2180876",
ISSN = "1046-8188",
bibdate = "Wed May 23 17:07:22 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Accessible emulation is often the method of choice for
maintaining digital objects, specifically complex ones
such as applications, business processes, or electronic
art. However, validating the emulator's ability to
faithfully reproduce the original behavior of digital
objects is complicated. This article presents an
evaluation framework and a set of tests that allow
assessment of the degree to which system emulation
preserves original characteristics and thus significant
properties of digital artifacts. The original system,
hardware, and software properties are described.
Identical environment is then recreated via emulation.
Automated user input is used to eliminate potential
confounders. The properties of a rendered form of the
object are then extracted automatically or manually
either in a target state, a series of states, or as a
continuous stream. The concepts described in this
article enable preservation planners to evaluate how
emulation affects the behavior of digital objects
compared to their behavior in the original environment.
We also review how these principles can and should be
applied to the evaluation of migration and other
preservation strategies as a general principle of
evaluating the invocation and faithful rendering of
digital objects and systems. The article concludes with
design requirements for emulators developed for digital
preservation tasks.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Larson:2012:SIS,
author = "Martha Larson and Franciska de Jong and Wessel Kraaij
and Steve Renals",
title = "Special issue on searching speech",
journal = j-TOIS,
volume = "30",
number = "3",
pages = "15:1--15:??",
month = aug,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2328967.2328968",
ISSN = "1046-8188",
bibdate = "Thu Sep 6 09:43:05 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2012:DPC,
author = "Dong Wang and Simon King and Joe Frankel and
Ravichander Vipperla and Nicholas Evans and Rapha{\"e}l
Troncy",
title = "Direct posterior confidence for out-of-vocabulary
spoken term detection",
journal = j-TOIS,
volume = "30",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2328967.2328969",
ISSN = "1046-8188",
bibdate = "Thu Sep 6 09:43:05 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Spoken term detection (STD) is a key technology for
spoken information retrieval. As compared to the
conventional speech transcription and keyword spotting,
STD is an open-vocabulary task and has to address
out-of-vocabulary (OOV) terms. Approaches based on
subword units, for example phones, are widely used to
solve the OOV issue; however, performance on OOV terms
is still substantially inferior to that of
in-vocabulary (INV) terms. The performance degradation
on OOV terms can be attributed to a multitude of
factors. One particular factor we address in this
article is the unreliable confidence estimation caused
by weak acoustic and language modeling due to the
absence of OOV terms in the training corpora. We
propose a direct posterior confidence derived from a
discriminative model, such as multilayer perceptron
(MLP). The new confidence considers a wide-range
acoustic context which is usually important for speech
recognition and retrieval; moreover, it localizes on
detected speech segments and therefore avoids the
impact of long-span word context which is usually
unreliable for OOV term detection. In this article, we
first develop an extensive discussion about the
modeling weakness problem associated with OOV terms,
and then propose our approach to address this problem
based on direct poster confidence. Our experiments
carried out on spontaneous and conversational
multiparty meeting speech, demonstrate that the
proposed technique provides a significant improvement
in STD performance as compared to conventional
lattice-based confidence, in particular for OOV terms.
Furthermore, the new confidence estimation approach is
fused with other advanced techniques for OOV treatment,
such as stochastic pronunciation modeling and
discriminative confidence normalization. This leads to
an integrated solution for OOV term detection that
results in a large performance improvement.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Luz:2012:NSP,
author = "Saturnino Luz",
title = "The nonverbal structure of patient case discussions in
multidisciplinary medical team meetings",
journal = j-TOIS,
volume = "30",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2328967.2328970",
ISSN = "1046-8188",
bibdate = "Thu Sep 6 09:43:05 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Meeting analysis has a long theoretical tradition in
social psychology, with established practical
ramifications in computer science, especially in
computer supported cooperative work. More recently, a
good deal of research has focused on the issues of
indexing and browsing multimedia records of meetings.
Most research in this area, however, is still based on
data collected in laboratories, under somewhat
artificial conditions. This article presents an
analysis of the discourse structure and spontaneous
interactions at real-life multidisciplinary medical
team meetings held as part of the work routine in a
major hospital. It is hypothesized that the
conversational structure of these meetings, as
indicated by sequencing and duration of vocalizations,
enables segmentation into individual patient case
discussions. The task of segmenting audio-visual
records of multidisciplinary medical team meetings is
described as a topic segmentation task, and a method
for automatic segmentation is proposed. An empirical
evaluation based on hand labelled data is presented,
which determines the optimal length of vocalization
sequences for segmentation, and establishes the
competitiveness of the method with approaches based on
more complex knowledge sources. The effectiveness of
Bayesian classification as a segmentation method, and
its applicability to meeting segmentation in other
domains are discussed.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tejedor:2012:CML,
author = "Javier Tejedor and Michal Fapso and Igor Sz{\"o}ke and
Jan `Honza' Cernock{\'y} and Frantisek Gr{\'e}zl",
title = "Comparison of methods for language-dependent and
language-independent query-by-example spoken term
detection",
journal = j-TOIS,
volume = "30",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2328967.2328971",
ISSN = "1046-8188",
bibdate = "Thu Sep 6 09:43:05 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article investigates query-by-example (QbE)
spoken term detection (STD), in which the query is not
entered as text, but selected in speech data or spoken.
Two feature extractors based on neural networks (NN)
are introduced: the first producing phone-state
posteriors and the second making use of a compressive
NN layer. They are combined with three different QbE
detectors: while the Gaussian mixture model/hidden
Markov model (GMM/HMM) and dynamic time warping (DTW)
both work on continuous feature vectors, the third one,
based on weighted finite-state transducers (WFST),
processes phone lattices. QbE STD is compared to two
standard STD systems with text queries: acoustic
keyword spotting and WFST-based search of phone strings
in phone lattices. The results are reported on four
languages (Czech, English, Hungarian, and Levantine
Arabic) using standard metrics: equal error rate (EER)
and two versions of popular figure-of-merit (FOM).
Language-dependent and language-independent cases are
investigated; the latter being particularly interesting
for scenarios lacking standard resources to train
speech recognition systems. While the DTW and GMM/HMM
approaches produce the best results for a
language-dependent setup depending on the target
language, the GMM/HMM approach performs the best
dealing with a language-independent setup. As far as
WFSTs are concerned, they are promising as they allow
for indexing and fast search.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Comas:2012:SFQ,
author = "Pere R. Comas and Jordi Turmo and Llu{\'\i}s
M{\`a}rquez",
title = "{Sibyl}, a factoid question-answering system for
spoken documents",
journal = j-TOIS,
volume = "30",
number = "3",
pages = "19:1--19:??",
month = aug,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2328967.2328972",
ISSN = "1046-8188",
bibdate = "Thu Sep 6 09:43:05 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In this article, we present a factoid
question-answering system, Sibyl, specifically tailored
for question answering (QA) on spoken-word documents.
This work explores, for the first time, which
techniques can be robustly adapted from the usual QA on
written documents to the more difficult spoken document
scenario. More specifically, we study new information
retrieval (IR) techniques designed or speech, and
utilize several levels of linguistic information for
the speech-based QA task. These include named-entity
detection with phonetic information, syntactic parsing
applied to speech transcripts, and the use of
coreference resolution. Sibyl is largely based on
supervised machine-learning techniques, with special
focus on the answer extraction step, and makes little
use of handcrafted knowledge. Consequently, it should
be easily adaptable to other domains and languages.
Sibyl and all its modules are extensively evaluated on
the European Parliament Plenary Sessions English
corpus, comparing manual with automatic transcripts
obtained by three different automatic speech
recognition (ASR) systems that exhibit significantly
different word error rates. This data belongs to the
CLEF 2009 track for QA on speech transcripts. The main
results confirm that syntactic information is very
useful for learning to rank question candidates,
improving results on both manual and automatic
transcripts, unless the ASR quality is very low. At the
same time, our experiments on coreference resolution
reveal that the state-of-the-art technology is not
mature enough to be effectively exploited for QA with
spoken documents. Overall, the performance of Sibyl is
comparable or better than the state-of-the-art on this
corpus, confirming the validity of our approach.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Moon:2012:OLF,
author = "Taesup Moon and Wei Chu and Lihong Li and Zhaohui
Zheng and Yi Chang",
title = "An Online Learning Framework for Refining Recency
Search Results with User Click Feedback",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382439",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Traditional machine-learned ranking systems for Web
search are often trained to capture stationary
relevance of documents to queries, which have limited
ability to track nonstationary user intention in a
timely manner. In recency search, for instance, the
relevance of documents to a query on breaking news
often changes significantly over time, requiring
effective adaptation to user intention. In this
article, we focus on recency search and study a number
of algorithms to improve ranking results by leveraging
user click feedback. Our contributions are threefold.
First, we use commercial search engine sessions
collected in a random exploration bucket for reliable
offline evaluation of these algorithms, which provides
an unbiased comparison across algorithms without online
bucket tests. Second, we propose an online learning
approach that reranks and improves the search results
for recency queries near real-time based on user
clicks. This approach is very general and can be
combined with sophisticated click models. Third, our
empirical comparison of a dozen algorithms on
real-world search data suggests importance of a few
algorithmic choices in these applications, including
generalization across different query-document pairs,
specialization to popular queries, and near real-time
adaptation of user clicks for reranking.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2012:DTT,
author = "Hongyan Liu and Jun He and Yingqin Gu and Hui Xiong
and Xiaoyong Du",
title = "Detecting and Tracking Topics and Events from {Web}
Search Logs",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382440",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Recent years have witnessed increased efforts on
detecting topics and events from Web search logs, since
this kind of data not only capture web content but also
reflect the users' activities. However, the majority of
existing work is focused on exploiting clustering
techniques for topic and event detection. Due to the
huge size and the evolving nature of Web data, existing
clustering approaches are limited to meet the real-time
demand. To that end, in this article, we propose a
method called LETD to detect evolving topics in a
timely manner. Also, we design the techniques to
extract events from topics and to infer the evolving
relationship among the events. For topic detection, we
first provide a measurement to select the important
URLs, which are most likely to describe a real-life
topic. Then, starting from these selected URLs, we
exploit the local expansion method to find other
topic-related URLs. Moreover, in the LETD framework, we
design algorithms based on Random Walk and Markov
Random Fields (MRF), respectively. Because the LETD
method exploits a divide-and-conquer strategy to
process the data, it is more efficient than existing
methods based on clustering techniques. To better
illustrate the LETD framework, we develop a demo system
StoryTeller which can discover hot topics and events,
infer the evolving relationships among events, and
visualize information in a storytelling way. This demo
system can provide a global view of the topic
development and help users target the interesting
events more conveniently. Finally, experimental results
on real-world Microsoft click-through data have shown
that StoryTeller can find real-life hot topics and
meaningful evolving relationships among events, and has
also demonstrated the efficiency and effectiveness of
the LETD method.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Abbasi:2012:DFM,
author = "Ahmed Abbasi and Fatemeh `Mariam' Zahedi and Siddharth
Kaza",
title = "Detecting Fake Medical {Web} Sites Using Recursive
Trust Labeling",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382441",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Fake medical Web sites have become increasingly
prevalent. Consequently, much of the health-related
information and advice available online is inaccurate
and/or misleading. Scores of medical institution Web
sites are for organizations that do not exist and more
than 90\% of online pharmacy Web sites are fraudulent.
In addition to monetary losses exacted on unsuspecting
users, these fake medical Web sites have severe public
safety ramifications. According to a World Health
Organization report, approximately half the drugs sold
on the Web are counterfeit, resulting in thousands of
deaths. In this study, we propose an adaptive learning
algorithm called recursive trust labeling (RTL). RTL
uses underlying content and graph-based classifiers,
coupled with a recursive labeling mechanism, for
enhanced detection of fake medical Web sites. The
proposed method was evaluated on a test bed
encompassing nearly 100 million links between 930,000
Web sites, including 1,000 known legitimate and fake
medical sites. The experimental results revealed that
RTL was able to significantly improve fake medical Web
site detection performance over 19 comparison content
and graph-based methods, various meta-learning
techniques, and existing adaptive learning approaches,
with an overall accuracy of over 94\%. Moreover, RTL
was able to attain high performance levels even when
the training dataset composed of as little as 30 Web
sites. With the increased popularity of eHealth and
Health 2.0, the results have important implications for
online trust, security, and public safety.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Adomavicius:2012:SRA,
author = "Gediminas Adomavicius and Jingjing Zhang",
title = "Stability of Recommendation Algorithms",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382442",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The article explores stability as a new measure of
recommender systems performance. Stability is defined
to measure the extent to which a recommendation
algorithm provides predictions that are consistent with
each other. Specifically, for a stable algorithm,
adding some of the algorithm's own predictions to the
algorithm's training data (for example, if these
predictions were confirmed as accurate by users) would
not invalidate or change the other predictions. While
stability is an interesting theoretical property that
can provide additional understanding about
recommendation algorithms, we believe stability to be a
desired practical property for recommender systems
designers as well, because unstable recommendations can
potentially decrease users' trust in recommender
systems and, as a result, reduce users' acceptance of
recommendations. In this article, we also provide an
extensive empirical evaluation of stability for six
popular recommendation algorithms on four real-world
datasets. Our results suggest that stability
performance of individual recommendation algorithms is
consistent across a variety of datasets and settings.
In particular, we find that model-based recommendation
algorithms consistently demonstrate higher stability
than neighborhood-based collaborative filtering
techniques. In addition, we perform a comprehensive
empirical analysis of many important factors (e.g., the
sparsity of original rating data, normalization of
input data, the number of new incoming ratings, the
distribution of incoming ratings, the distribution of
evaluation data, etc.) and report the impact they have
on recommendation stability.",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Fu:2012:SSL,
author = "Tianjun Fu and Ahmed Abbasi and Daniel Zeng and
Hsinchun Chen",
title = "Sentimental Spidering: Leveraging Opinion Information
in Focused Crawlers",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "24:1--24:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382443",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Despite the increased prevalence of sentiment-related
information on the Web, there has been limited work on
focused crawlers capable of effectively collecting not
only topic-relevant but also sentiment-relevant
content. In this article, we propose a novel focused
crawler that incorporates topic and sentiment
information as well as a graph-based tunneling
mechanism for enhanced collection of opinion-rich Web
content regarding a particular topic. The graph-based
sentiment (GBS) crawler uses a text classifier that
employs both topic and sentiment categorization modules
to assess the relevance of candidate pages. This
information is also used to label nodes in web graphs
that are employed by the tunneling mechanism to improve
collection recall. Experimental results on two test
beds revealed that GBS was able to provide better
precision and recall than seven comparison crawlers.
Moreover, GBS was able to collect a large proportion of
the relevant content after traversing far fewer pages
than comparison methods. GBS outperformed comparison
methods on various categories of Web pages in the test
beds, including collection of blogs, Web forums, and
social networking Web site content. Further analysis
revealed that both the sentiment classification module
and graph-based tunneling mechanism played an integral
role in the overall effectiveness of the GBS crawler.",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{You:2012:EET,
author = "Gae-Won You and Seung-Won Hwang and Young-In Song and
Long Jiang and Zaiqing Nie",
title = "Efficient Entity Translation Mining: a Parallelized
Graph Alignment Approach",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "25:1--25:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382444",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article studies the problem of mining entity
translation, specifically, mining English and Chinese
name pairs. Existing efforts can be categorized into
(a) transliteration-based approaches that leverage
phonetic similarity and (b) corpus-based approaches
that exploit bilingual cooccurrences. These approaches
suffer from inaccuracy and scarcity, respectively. In
clear contrast, we use under-leveraged resources of
monolingual entity cooccurrences crawled from entity
search engines, which are represented as two
entity-relationship graphs extracted from two language
corpora, respectively. Our problem is then abstracted
as finding correct mappings across two graphs. To
achieve this goal, we propose a holistic approach to
exploiting both transliteration similarity and
monolingual cooccurrences. This approach, which builds
upon monolingual corpora, complements existing
corpus-based work requiring scarce resources of
parallel or comparable corpus while significantly
boosting the accuracy of transliteration-based work. In
addition, by parallelizing the mapping process on
multicore architectures, we speed up the computation by
more than 10 times per unit accuracy. We validated the
effectiveness and efficiency of our proposed approach
using real-life datasets.",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Gerani:2012:AMP,
author = "Shima Gerani and Mark Carman and Fabio Crestani",
title = "Aggregation Methods for Proximity-Based Opinion
Retrieval",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "26:1--26:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382445",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The enormous amount of user-generated data available
on the Web provides a great opportunity to understand,
analyze, and exploit people's opinions on different
topics. Traditional Information Retrieval methods
consider the relevance of documents to a topic but are
unable to differentiate between subjective and
objective documents. Opinion retrieval is a retrieval
task in which not only the relevance of a document to
the topic is important but also the amount of opinion
expressed in the document about the topic. In this
article, we address the blog post opinion retrieval
task and propose methods that rank blog posts according
to their relevance and opinionatedness toward a topic.
We propose estimating the opinion density at each
position in a document using a general opinion lexicon
and kernel density functions. We propose and
investigate different models for aggregating the
opinion density at query terms positions to estimate
the opinion score of every document. We then combine
the opinion score with the relevance score based on a
probabilistic justification. Experimental results on
the BLOG06 dataset show that the proposed method
provides significant improvement over the standard TREC
baselines. The proposed models also achieve much higher
performance compared to all state of the art methods.",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Callan:2012:TRO,
author = "Jamie Callan",
title = "{TOIS} Reviewers: {October 2009} to {September 2012}",
journal = j-TOIS,
volume = "30",
number = "4",
pages = "27:1--27:??",
month = nov,
year = "2012",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2382438.2382446",
ISSN = "1046-8188",
bibdate = "Tue Nov 27 17:48:53 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Kim:2013:EDE,
author = "Jinhan Kim and Sanghoon Lee and Seung-Won Hwang and
Sunghun Kim",
title = "Enriching Documents with Examples: a Corpus Mining
Approach",
journal = j-TOIS,
volume = "31",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2414782.2414783",
ISSN = "1046-8188",
bibdate = "Wed Jan 30 11:36:49 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Software developers increasingly rely on information
from the Web, such as documents or code examples on
application programming interfaces (APIs), to
facilitate their development processes. However, API
documents often do not include enough information for
developers to fully understand how to use the APIs, and
searching for good code examples requires considerable
effort. To address this problem, we propose a novel
code example recommendation system that combines the
strength of browsing documents and searching for code
examples and returns API documents embedded with
high-quality code example summaries mined from the Web.
Our evaluation results show that our approach provides
code examples with high precision and boosts programmer
productivity.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Webber:2013:ARC,
author = "William Webber",
title = "Approximate Recall Confidence Intervals",
journal = j-TOIS,
volume = "31",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2414782.2414784",
ISSN = "1046-8188",
bibdate = "Wed Jan 30 11:36:49 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Recall, the proportion of relevant documents
retrieved, is an important measure of effectiveness in
information retrieval, particularly in the legal,
patent, and medical domains. Where document sets are
too large for exhaustive relevance assessment, recall
can be estimated by assessing a random sample of
documents, but an indication of the reliability of this
estimate is also required. In this article, we examine
several methods for estimating two-tailed recall
confidence intervals. We find that the normal
approximation in current use provides poor coverage in
many circumstances, even when adjusted to correct its
inappropriate symmetry. Analytic and Bayesian methods
based on the ratio of binomials are generally more
accurate but are inaccurate on small populations. The
method we recommend derives beta-binomial posteriors on
retrieved and unretrieved yield, with fixed
hyperparameters, and a Monte Carlo estimate of the
posterior distribution of recall. We demonstrate that
this method gives mean coverage at or near the nominal
level, across several scenarios, while being balanced
and stable. We offer advice on sampling design,
including the allocation of assessments to the
retrieved and unretrieved segments, and compare the
proposed beta-binomial with the officially reported
normal intervals for recent TREC Legal Track
iterations.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Costa:2013:XCA,
author = "Gianni Costa and Riccardo Ortale and Ettore Ritacco",
title = "{X}-Class: Associative Classification of {XML}
Documents by Structure",
journal = j-TOIS,
volume = "31",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2414782.2414785",
ISSN = "1046-8188",
bibdate = "Wed Jan 30 11:36:49 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The supervised classification of XML documents by
structure involves learning predictive models in which
certain structural regularities discriminate the
individual document classes. Hitherto, research has
focused on the adoption of prespecified substructures.
This is detrimental for classification effectiveness,
since the a priori chosen substructures may not accord
with the structural properties of the XML documents.
Therein, an unexplored question is how to choose the
type of structural regularity that best adapts to the
structures of the available XML documents. We tackle
this problem through X-Class, an approach that handles
all types of tree-like substructures and allows for
choosing the most discriminatory one. Algorithms are
designed to learn compact rule-based classifiers in
which the chosen substructures discriminate the classes
of XML documents. X-Class is studied across various
domains and types of substructures. Its classification
performance is compared against several rule-based and
SVM-based competitors. Empirical evidence reveals that
the classifiers induced by X-Class are compact,
scalable, and at least as effective as the established
competitors. In particular, certain substructures allow
the induction of very compact classifiers that
generally outperform the rule-based competitors in
terms of effectiveness over all chosen corpora of XML
data. Furthermore, such classifiers are substantially
as effective as the SVM-based competitor, with the
additional advantage of a high-degree of
interpretability.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yom-Tov:2013:ESP,
author = "Elad Yom-Tov and Fernando Diaz",
title = "The Effect of Social and Physical Detachment on
Information Need",
journal = j-TOIS,
volume = "31",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2414782.2414786",
ISSN = "1046-8188",
bibdate = "Wed Jan 30 11:36:49 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The information need of users and the documents which
answer this need are frequently contingent on the
different characteristics of users. This is especially
evident during natural disasters, such as earthquakes
and violent weather incidents, which create a strong
transient information need. In this article, we
investigate how the information need of users, as
expressed by their queries, is affected by their
physical detachment, as estimated by their physical
location in relation to that of the event, and by their
social detachment, as quantified by the number of their
acquaintances who may be affected by the event. Drawing
on large-scale data from ten major events, we show that
social and physical detachment levels of users are a
major influence on their search engine queries. We
demonstrate how knowing social and physical detachment
levels can assist in improving retrieval for two
applications: identifying search queries related to
events and ranking results in response to event-related
queries. We find that the average precision in
identifying relevant search queries improves by
approximately 18\%, and that the average precision of
ranking that uses detachment information improves by
10\%. Using both types of detachment achieved a larger
gain in performance than each of them separately.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2013:RLS,
author = "Quan Wang and Jun Xu and Hang Li and Nick Craswell",
title = "Regularized Latent Semantic Indexing: a New Approach
to Large-Scale Topic Modeling",
journal = j-TOIS,
volume = "31",
number = "1",
pages = "5:1--5:??",
month = jan,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2414782.2414787",
ISSN = "1046-8188",
bibdate = "Wed Jan 30 11:36:49 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Topic modeling provides a powerful way to analyze the
content of a collection of documents. It has become a
popular tool in many research areas, such as text
mining, information retrieval, natural language
processing, and other related fields. In real-world
applications, however, the usefulness of topic modeling
is limited due to scalability issues. Scaling to larger
document collections via parallelization is an active
area of research, but most solutions require drastic
steps, such as vastly reducing input vocabulary. In
this article we introduce Regularized Latent Semantic
Indexing (RLSI)---including a batch version and an
online version, referred to as batch RLSI and online
RLSI, respectively---to scale up topic modeling. Batch
RLSI and online RLSI are as effective as existing topic
modeling techniques and can scale to larger datasets
without reducing input vocabulary. Moreover, online
RLSI can be applied to stream data and can capture the
dynamic evolution of topics. Both versions of RLSI
formalize topic modeling as a problem of minimizing a
quadratic loss function regularized by l1 and/or l2
norm. This formulation allows the learning process to
be decomposed into multiple suboptimization problems
which can be optimized in parallel, for example, via
MapReduce. We particularly propose adopting l1 norm on
topics and l2 norm on document representations to
create a model with compact and readable topics and
which is useful for retrieval. In learning, batch RLSI
processes all the documents in the collection as a
whole, while online RLSI processes the documents in the
collection one by one. We also prove the convergence of
the learning of online RLSI. Relevance ranking
experiments on three TREC datasets show that batch RLSI
and online RLSI perform better than LSI, PLSI, LDA, and
NMF, and the improvements are sometimes statistically
significant. Experiments on a Web dataset containing
about 1.6 million documents and 7 million terms,
demonstrate a similar boost in performance.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Xue:2013:MRU,
author = "Xiaobing Xue and W. Bruce Croft",
title = "Modeling reformulation using query distributions",
journal = j-TOIS,
volume = "31",
number = "2",
pages = "6:1--6:??",
month = may,
year = "2013",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri May 17 19:16:24 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Query reformulation modifies the original query with
the aim of better matching the vocabulary of the
relevant documents, and consequently improving ranking
effectiveness. Previous models typically generate words
and phrases related to the original query, but do not
consider how these words and phrases would fit together
in actual queries. In this article, a novel framework
is proposed that models reformulation as a distribution
of actual queries, where each query is a variation of
the original query. This approach considers an actual
query as the basic unit and thus captures important
query-level dependencies between words and phrases. An
implementation of this framework that only uses
publicly available resources is proposed, which makes
fair comparisons with other methods using TREC
collections possible. Specifically, this implementation
consists of a query generation step that analyzes the
passages containing query words to generate
reformulated queries and a probability estimation step
that learns a distribution for reformulated queries by
optimizing the retrieval performance. Experiments on
TREC collections show that the proposed model can
significantly outperform previous reformulation
models.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pan:2013:TJE,
author = "Sinno Jialin Pan and Zhiqiang Toh and Jian Su",
title = "Transfer joint embedding for cross-domain named entity
recognition",
journal = j-TOIS,
volume = "31",
number = "2",
pages = "7:1--7:??",
month = may,
year = "2013",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri May 17 19:16:24 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Named Entity Recognition (NER) is a fundamental task
in information extraction from unstructured text. Most
previous machine-learning-based NER systems are
domain-specific, which implies that they may only
perform well on some specific domains (e.g., Newswire )
but tend to adapt poorly to other related but different
domains (e.g., Weblog ). Recently, transfer learning
techniques have been proposed to NER. However, most
transfer learning approaches to NER are developed for
binary classification, while NER is a multiclass
classification problem in nature. Therefore, one has to
first reduce the NER task to multiple binary
classification tasks and solve them independently. In
this article, we propose a new transfer learning
method, named Transfer Joint Embedding (TJE), for
cross-domain multiclass classification, which can fully
exploit the relationships between classes (labels), and
reduce domain difference in data distributions for
transfer learning. More specifically, we aim to embed
both labels (outputs) and high-dimensional features
(inputs) from different domains (e.g., a source domain
and a target domain) into a unified low-dimensional
latent space, where (1) each label is represented by a
prototype and the intrinsic relationships between
labels can be measured by Euclidean distance; (2) the
distance in data distributions between the source and
target domains can be reduced; (3) the source domain
labeled data are closer to their corresponding
label-prototypes than others. After the latent space is
learned, classification on the target domain data can
be done with the simple nearest neighbor rule in the
latent space. Furthermore, in order to scale up TJE, we
propose an efficient algorithm based on stochastic
gradient descent (SGD). Finally, we apply the proposed
TJE method for NER across different domains on the ACE
2005 dataset, which is a benchmark in Natural Language
Processing (NLP). Experimental results demonstrate the
effectiveness of TJE and show that TJE can outperform
state-of-the-art transfer learning approaches to NER.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ke:2013:SCP,
author = "Weimao Ke and Javed Mostafa",
title = "Studying the clustering paradox and scalability of
search in highly distributed environments",
journal = j-TOIS,
volume = "31",
number = "2",
pages = "8:1--8:??",
month = may,
year = "2013",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri May 17 19:16:24 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the ubiquitous production, distribution and
consumption of information, today's digital
environments such as the Web are increasingly large and
decentralized. It is hardly possible to obtain central
control over information collections and systems in
these environments. Searching for information in these
information spaces has brought about problems beyond
traditional boundaries of information retrieval (IR)
research. This article addresses one important aspect
of scalability challenges facing information retrieval
models and investigates a decentralized, organic view
of information systems pertaining to search in
large-scale networks. Drawing on observations from
earlier studies, we conduct a series of experiments on
decentralized searches in large-scale networked
information spaces. Results show that how distributed
systems interconnect is crucial to retrieval
performance and scalability of searching. Particularly,
in various experimental settings and retrieval tasks,
we find a consistent phenomenon, namely, the Clustering
Paradox, in which the level of network clustering
(semantic overlay) imposes a scalability limit.
Scalable searches are well supported by a specific,
balanced level of network clustering emerging from
local system interconnectivity. Departure from that
level, either stronger or weaker clustering, leads to
search performance degradation, which is dramatic in
large-scale networks.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhu:2013:SHF,
author = "Xiaofeng Zhu and Zi Huang and Hong Cheng and Jiangtao
Cui and Heng Tao Shen",
title = "Sparse hashing for fast multimedia search",
journal = j-TOIS,
volume = "31",
number = "2",
pages = "9:1--9:??",
month = may,
year = "2013",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri May 17 19:16:24 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Hash-based methods achieve fast similarity search by
representing high-dimensional data with compact binary
codes. However, both generating binary codes and
encoding unseen data effectively and efficiently remain
very challenging tasks. In this article, we focus on
these tasks to implement approximate similarity search
by proposing a novel hash based method named sparse
hashing (SH for short). To generate interpretable (or
semantically meaningful) binary codes, the proposed SH
first converts original data into low-dimensional data
through a novel nonnegative sparse coding method. SH
then converts the low-dimensional data into Hamming
space (i.e., binary encoding low-dimensional data) by a
new binarization rule. After this, training data are
represented by generated binary codes. To efficiently
and effectively encode unseen data, SH learns hash
functions by taking a-priori knowledge into account,
such as implicit group effect of the features in
training data, and the correlations between original
space and the learned Hamming space. SH is able to
perform fast approximate similarity search by efficient
bit XOR operations in the memory of a modern PC with
short binary code representations. Experimental results
show that the proposed SH significantly outperforms
state-of-the-art techniques.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bast:2013:EFS,
author = "Hannah Bast and Marjan Celikik",
title = "Efficient fuzzy search in large text collections",
journal = j-TOIS,
volume = "31",
number = "2",
pages = "10:1--10:??",
month = may,
year = "2013",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Fri May 17 19:16:24 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We consider the problem of fuzzy full-text search in
large text collections, that is, full-text search which
is robust against errors both on the side of the query
as well as on the side of the documents. Standard
inverted-index techniques work extremely well for
ordinary full-text search but fail to achieve
interactive query times (below 100 milliseconds) for
fuzzy full-text search even on moderately-sized text
collections (above 10 GBs of text). We present new
preprocessing techniques that achieve interactive query
times on large text collections (100 GB of text, served
by a single machine). We consider two similarity
measures, one where the query terms match similar terms
in the collection (e.g., algorithm matches algoritm or
vice versa) and one where the query terms match terms
with a similar prefix in the collection (e.g., alori
matches algorithm). The latter is important when we
want to display results instantly after each keystroke
(search as you type). All algorithms have been fully
integrated into the CompleteSearch engine.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Macdonald:2013:ALM,
author = "Craig Macdonald and Rodrygo L. T. Santos and Iadh
Ounis and Ben He",
title = "About learning models with multiple query-dependent
features",
journal = j-TOIS,
volume = "31",
number = "3",
pages = "11:1--11:??",
month = jul,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2493175.2493176",
ISSN = "1046-8188",
bibdate = "Wed Jul 31 12:16:17 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Several questions remain unanswered by the existing
literature concerning the deployment of query-dependent
features within learning to rank. In this work, we
investigate three research questions in order to
empirically ascertain best practices for
learning-to-rank deployments. (i) Previous work in data
fusion that pre-dates learning to rank showed that
while different retrieval systems could be effectively
combined, the combination of multiple models within the
same system was not as effective. In contrast, the
existing learning-to-rank datasets (e.g., LETOR), often
deploy multiple weighting models as query-dependent
features within a single system, raising the question
as to whether such a combination is needed. (ii) Next,
we investigate whether the training of weighting model
parameters, traditionally required for effective
retrieval, is necessary within a learning-to-rank
context. (iii) Finally, we note that existing
learning-to-rank datasets use weighting model features
calculated on different fields (e.g., title, content,
or anchor text), even though such weighting models have
been criticized in the literature. Experiments
addressing these three questions are conducted on Web
search datasets, using various weighting models as
query-dependent and typical query-independent features,
which are combined using three learning-to-rank
techniques. In particular, we show and explain why
multiple weighting models should be deployed as
features. Moreover, we unexpectedly find that training
the weighting model's parameters degrades learned
model's effectiveness. Finally, we show that computing
a weighting model separately for each field is less
effective than more theoretically-sound field-based
weighting models.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hou:2013:MPH,
author = "Yuexian Hou and Xiaozhao Zhao and Dawei Song and
Wenjie Li",
title = "Mining pure high-order word associations via
information geometry for information retrieval",
journal = j-TOIS,
volume = "31",
number = "3",
pages = "12:1--12:??",
month = jul,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2493175.2493177",
ISSN = "1046-8188",
bibdate = "Wed Jul 31 12:16:17 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The classical bag-of-word models for information
retrieval (IR) fail to capture contextual associations
between words. In this article, we propose to
investigate pure high-order dependence among a number
of words forming an unseparable semantic entity, that
is, the high-order dependence that cannot be reduced to
the random coincidence of lower-order dependencies. We
believe that identifying these pure high-order
dependence patterns would lead to a better
representation of documents and novel retrieval models.
Specifically, two formal definitions of pure
dependence-unconditional pure dependence (UPD) and
conditional pure dependence (CPD)-are defined. The
exact decision on UPD and CPD, however, is NP-hard in
general. We hence derive and prove the sufficient
criteria that entail UPD and CPD, within the
well-principled information geometry (IG) framework,
leading to a more feasible UPD/CPD identification
procedure. We further develop novel methods for
extracting word patterns with pure high-order
dependence. Our methods are applied to and extensively
evaluated on three typical IR tasks: text
classification and text retrieval without and with
query expansion.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Asadi:2013:FCG,
author = "Nima Asadi and Jimmy Lin",
title = "Fast candidate generation for real-time tweet search
with {Bloom} filter chains",
journal = j-TOIS,
volume = "31",
number = "3",
pages = "13:1--13:??",
month = jul,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2493175.2493178",
ISSN = "1046-8188",
bibdate = "Wed Jul 31 12:16:17 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The rise of social media and other forms of
user-generated content have created the demand for
real-time search: against a high-velocity stream of
incoming documents, users desire a list of relevant
results at the time the query is issued. In the context
of real-time search on tweets, this work explores
candidate generation in a two-stage retrieval
architecture where an initial list of results is
processed by a second-stage rescorer to produce the
final output. We introduce Bloom filter chains, a novel
extension of Bloom filters that can dynamically expand
to efficiently represent an arbitrarily long and
growing list of monotonically-increasing integers with
a constant false positive rate. Using a collection of
Bloom filter chains, a novel approximate candidate
generation algorithm called BWand is able to perform
both conjunctive and disjunctive retrieval. Experiments
show that our algorithm is many times faster than
competitive baselines and that this increased
performance does not require sacrificing end-to-end
effectiveness. Our results empirically characterize the
trade-off space defined by output quality, query
evaluation speed, and memory footprint for this
particular search architecture.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lucchese:2013:DTS,
author = "Claudio Lucchese and Salvatore Orlando and Raffaele
Perego and Fabrizio Silvestri and Gabriele Tolomei",
title = "Discovering tasks from search engine query logs",
journal = j-TOIS,
volume = "31",
number = "3",
pages = "14:1--14:??",
month = jul,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2493175.2493179",
ISSN = "1046-8188",
bibdate = "Wed Jul 31 12:16:17 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Although Web search engines still answer user queries
with lists of ten blue links to webpages, people are
increasingly issuing queries to accomplish their daily
tasks (e.g., finding a recipe, booking a flight,
reading online news, etc.). In this work, we propose a
two-step methodology for discovering tasks that users
try to perform through search engines. First, we
identify user tasks from individual user sessions
stored in search engine query logs. In our vision, a
user task is a set of possibly noncontiguous queries
(within a user search session), which refer to the same
need. Second, we discover collective tasks by
aggregating similar user tasks, possibly performed by
distinct users. To discover user tasks, we propose
query similarity functions based on unsupervised and
supervised learning approaches. We present a set of
query clustering methods that exploit these functions
in order to detect user tasks. All the proposed
solutions were evaluated on a manually-built ground
truth, and two of them performed better than
state-of-the-art approaches. To detect collective
tasks, we propose four methods that cluster previously
discovered user tasks, which in turn are represented by
the bag-of-words extracted from their composing
queries. These solutions were also evaluated on another
manually-built ground truth.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Nong:2013:PLT,
author = "Ge Nong",
title = "Practical linear-time {$ O(1) $}-workspace suffix
sorting for constant alphabets",
journal = j-TOIS,
volume = "31",
number = "3",
pages = "15:1--15:??",
month = jul,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2493175.2493180",
ISSN = "1046-8188",
bibdate = "Wed Jul 31 12:16:17 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article presents an {$ O(n) $}-time algorithm
called SACA-K for sorting the suffixes of an input
string {$ T[0, n - 1] $} over an alphabet {$ A[0, K -
1] $}. The problem of sorting the suffixes of {$T$} is
also known as constructing the suffix array (SA) for
{$T$}. The theoretical memory usage of SACA-{$K$} is {$
n \log K + n \log n + K \log n $} bits. Moreover, we
also have a practical implementation for SACA-{$K$}
that uses $n$ bytes + $ (n + 256) $ words and is
suitable for strings over any alphabet up to full
ASCII, where a word is $ \log n $ bits. In our
experiment, SACA-{$K$} outperforms SA-IS that was
previously the most time- and space-efficient
linear-time SA construction algorithm (SACA).
SACA-{$K$} is around 33\% faster and uses a smaller
deterministic workspace of {$K$} words, where the
workspace is the space needed beyond the input string
and the output SA. Given {$ K = O(1) $}, SACA-{$K$}
runs in linear time and {$ O(1) $} workspace. To the
best of our knowledge, such a result is the first
reported in the literature with a practical source code
publicly available.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Radinsky:2013:BDW,
author = "Kira Radinsky and Krysta M. Svore and Susan T. Dumais
and Milad Shokouhi and Jaime Teevan and Alex Bocharov
and Eric Horvitz",
title = "Behavioral dynamics on the {Web}: Learning, modeling,
and prediction",
journal = j-TOIS,
volume = "31",
number = "3",
pages = "16:1--16:??",
month = jul,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2493175.2493181",
ISSN = "1046-8188",
bibdate = "Wed Jul 31 12:16:17 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The queries people issue to a search engine and the
results clicked following a query change over time. For
example, after the earthquake in Japan in March 2011,
the query {\em Japan\/} spiked in popularity and people
issuing the query were more likely to click
government-related results than they would prior to the
earthquake. We explore the modeling and prediction of
such temporal patterns in Web search behavior. We
develop a temporal modeling framework adapted from
physics and signal processing and harness it to predict
temporal patterns in search behavior using smoothing,
trends, periodicities, and surprises. Using current and
past behavioral data, we develop a learning procedure
that can be used to construct models of users' Web
search activities. We also develop a novel methodology
that learns to select the best prediction model from a
family of predictive models for a given query or a
class of queries. Experimental results indicate that
the predictive models significantly outperform baseline
models that weight historical evidence the same for all
queries. We present two applications where new methods
introduced for the temporal modeling of user behavior
significantly improve upon the state of the art.
Finally, we discuss opportunities for using models of
temporal dynamics to enhance other areas of Web search
and information retrieval.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hofmann:2013:FSE,
author = "Katja Hofmann and Shimon Whiteson and Maarten {De
Rijke}",
title = "Fidelity, Soundness, and Efficiency of Interleaved
Comparison Methods",
journal = j-TOIS,
volume = "31",
number = "4",
pages = "17:1--17:??",
month = nov,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2536736.2536737",
ISSN = "1046-8188",
bibdate = "Tue Dec 3 18:39:19 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Ranker evaluation is central to the research into
search engines, be it to compare rankers or to provide
feedback for learning to rank. Traditional evaluation
approaches do not scale well because they require
explicit relevance judgments of document-query pairs,
which are expensive to obtain. A promising alternative
is the use of interleaved comparison methods, which
compare rankers using click data obtained when
interleaving their rankings. In this article, we
propose a framework for analyzing interleaved
comparison methods. An interleaved comparison method
has fidelity if the expected outcome of ranker
comparisons properly corresponds to the true relevance
of the ranked documents. It is sound if its estimates
of that expected outcome are unbiased and consistent.
It is efficient if those estimates are accurate with
only little data. We analyze existing interleaved
comparison methods and find that, while sound, none
meet our criteria for fidelity. We propose a
probabilistic interleave method, which is sound and has
fidelity. We show empirically that, by marginalizing
out variables that are known, it is more efficient than
existing interleaved comparison methods. Using
importance sampling we derive a sound extension that is
able to reuse historical data collected in previous
comparisons of other ranker pairs.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Paik:2013:ERQ,
author = "Jiaul H. Paik and Swapan K. Parui and Dipasree Pal and
Stephen E. Robertson",
title = "Effective and Robust Query-Based Stemming",
journal = j-TOIS,
volume = "31",
number = "4",
pages = "18:1--18:??",
month = nov,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2536736.2536738",
ISSN = "1046-8188",
bibdate = "Tue Dec 3 18:39:19 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Stemming is a widely used technique in information
retrieval systems to address the vocabulary mismatch
problem arising out of morphological phenomena. The
major shortcoming of the commonly used stemmers is that
they accept the morphological variants of the query
words without considering their thematic coherence with
the given query, which leads to poor performance.
Moreover, for many queries, such approaches also
produce retrieval performance that is poorer than no
stemming, thereby degrading the robustness. The main
goal of this article is to present corpus-based fully
automatic stemming algorithms which address these
issues. A set of experiments on six TREC collections
and three other non-English collections containing news
and web documents shows that the proposed query-based
stemming algorithms consistently and significantly
outperform four state of the art strong stemmers of
completely varying principles. Our experiments also
confirm that the robustness of the proposed query-based
stemming algorithms are remarkably better than the
existing strong baselines.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Esuli:2013:ITC,
author = "Andrea Esuli and Fabrizio Sebastiani",
title = "Improving Text Classification Accuracy by Training
Label Cleaning",
journal = j-TOIS,
volume = "31",
number = "4",
pages = "19:1--19:??",
month = nov,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2516889",
ISSN = "1046-8188",
bibdate = "Tue Dec 3 18:39:19 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In text classification (TC) and other tasks involving
supervised learning, labelled data may be scarce or
expensive to obtain. Semisupervised learning and active
learning are two strategies whose aim is maximizing the
effectiveness of the resulting classifiers for a given
amount of training effort. Both strategies have been
actively investigated for TC in recent years. Much less
research has been devoted to a third such strategy,
training label cleaning (TLC), which consists in
devising ranking functions that sort the original
training examples in terms of how likely it is that the
human annotator has mislabelled them. This provides a
convenient means for the human annotator to revise the
training set so as to improve its quality. Working in
the context of boosting-based learning methods for
multilabel classification we present three different
techniques for performing TLC and, on three widely used
TC benchmarks, evaluate them by their capability of
spotting training documents that, for experimental
reasons only, we have purposefully mislabelled. We also
evaluate the degradation in classification
effectiveness that these mislabelled texts bring about,
and to what extent training label cleaning can prevent
this degradation.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chelmis:2013:SLP,
author = "Charalampos Chelmis and Viktor K. Prasanna",
title = "Social Link Prediction in Online Social Tagging
Systems",
journal = j-TOIS,
volume = "31",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2516891",
ISSN = "1046-8188",
bibdate = "Tue Dec 3 18:39:19 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Social networks have become a popular medium for
people to communicate and distribute ideas, content,
news, and advertisements. Social content annotation has
naturally emerged as a method of categorization and
filtering of online information. The unrestricted
vocabulary users choose from to annotate content has
often lead to an explosion of the size of space in
which search is performed. In this article, we propose
latent topic models as a principled way of reducing the
dimensionality of such data and capturing the dynamics
of collaborative annotation process. We propose three
generative processes to model latent user tastes with
respect to resources they annotate with metadata. We
show that latent user interests combined with social
clues from the immediate neighborhood of users can
significantly improve social link prediction in the
online music social media site Last.fm. Most link
prediction methods suffer from the high class imbalance
problem, resulting in low precision and/or recall. In
contrast, our proposed classification schemes for
social link recommendation achieve high precision and
recall with respect to not only the dominant class
(nonexistence of a link), but also with respect to
sparse positive instances, which are the most vital in
social tie prediction.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Jia:2013:ISD,
author = "Lifeng Jia and Clement Yu and Weiyi Meng",
title = "The Impacts of Structural Difference and Temporality
of Tweets on Retrieval Effectiveness",
journal = j-TOIS,
volume = "31",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2500751",
ISSN = "1046-8188",
bibdate = "Tue Dec 3 18:39:19 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "To explore the information seeking behaviors in
microblogosphere, the microblog track at TREC 2011
introduced a real-time ad-hoc retrieval task that aims
at ranking relevant tweets in reverse-chronological
order. We study this problem via a two-phase approach:
(1) retrieving tweets in an ad-hoc way; (2) utilizing the
temporal information of tweets to enhance the retrieval
effectiveness of tweets. Tweets can be categorized into
two types. One type consists of short messages not
containing any URL of a Web page. The other type has at
least one URL of a Web page in addition to a short
message. These two types of tweets have different
structures. In the first phase, to address the
structural difference of tweets, we propose a method to
rank tweets using the divide-and-conquer strategy.
Specifically, we first rank the two types of tweets
separately. This produces two rankings, one for each
type. Then we merge these two rankings of tweets into
one ranking. In the second phase, we first categorize
queries into several types by exploring the temporal
distributions of their top-retrieved tweets from the
first phase; then we calculate the time-related
relevance scores of tweets according to the classified
types of queries; finally we combine the time scores
with the IR scores from the first phase to produce a
ranking of tweets. Experimental results achieved by
using the TREC 2011 and TREC 2012 queries over the TREC
Tweets2011 collection show that: (i) our way of ranking
the two types of tweets separately and then merging
them together yields better retrieval effectiveness
than ranking them simultaneously; (ii) our way of
incorporating temporal information into the retrieval
process yields further improvements, and (iii) our
method compares favorably with state-of-the-art methods
in retrieval effectiveness.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chiu:2013:EVS,
author = "Chih-Yi Chiu and Tsung-Han Tsai and Guei-Wun Han and
Cheng-Yu Hsieh and Sheng-Yang Li",
title = "Efficient Video Stream Monitoring for Near-Duplicate
Detection and Localization in a Large-Scale
Repository",
journal = j-TOIS,
volume = "31",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2013",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2516890",
ISSN = "1046-8188",
bibdate = "Tue Dec 3 18:39:19 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In this article, we study the efficiency problem of
video stream near-duplicate monitoring in a large-scale
repository. Existing stream monitoring methods are
mainly designed for a short video to scan over a query
stream; they have difficulty being scalable for a large
number of long videos. We present a simple but
effective algorithm called incremental similarity
update to address the problem. That is, a similarity
upper bound between two videos can be calculated
incrementally by leveraging the prior knowledge of the
previous calculation. The similarity upper bound takes
a lightweight computation to filter out unnecessary
time-consuming computation for the actual similarity
between two videos, making the search process more
efficient. We integrate the algorithm with inverted
indexing to obtain a candidate list from the repository
for the given query stream. Meanwhile, the algorithm is
applied to scan each candidate for locating exact
near-duplicate subsequences. We implement several
state-of-the-art methods for comparison in terms of
accuracy, execution time, and memory consumption.
Experimental results demonstrate the proposed algorithm
yields comparable accuracy, compact memory size, and
more efficient execution time.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Nong:2014:SAC,
author = "Ge Nong and Wai Hong Chan and Sen Zhang and Xiao Feng
Guan",
title = "Suffix Array Construction in External Memory Using
{D}-Critical Substrings",
journal = j-TOIS,
volume = "32",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2518175",
ISSN = "1046-8188",
bibdate = "Tue Jan 28 17:40:54 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We present a new suffix array construction algorithm
that aims to build, in external memory, the suffix
array for an input string of length n measured in the
magnitude of tens of Giga characters over a constant or
integer alphabet. The core of this algorithm is adapted
from the framework of the original internal memory
SA-DS algorithm that samples fixed-size $d$-critical
substrings. This new external-memory algorithm, called
EM-SA-DS, uses novel cache data structures to construct
a suffix array in a sequential scanning manner with
good data spatial locality: data is read from or
written to disk sequentially. On the assumed
external-memory model with RAM capacity $ \Omega ((n
B)^{0.5}) $, disk capacity $ O(n) $, and size of each
I/O block B, all measured in $ \log n $-bit words, the
I/O complexity of EM-SA-DS is $ O(n / B) $. This work
provides a general cache-based solution that could be
further exploited to develop external-memory solutions
for other suffix-array-related problems, for example,
computing the longest-common-prefix array, using a
modern personal computer with a typical memory
configuration of 4GB RAM and a single disk.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cummins:2014:DSD,
author = "Ronan Cummins",
title = "Document Score Distribution Models for Query
Performance Inference and Prediction",
journal = j-TOIS,
volume = "32",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2559170",
ISSN = "1046-8188",
bibdate = "Tue Jan 28 17:40:54 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Modelling the distribution of document scores returned
from an information retrieval (IR) system in response
to a query is of both theoretical and practical
importance. One of the goals of modelling document
scores in this manner is the inference of document
relevance. There has been renewed interest of late in
modelling document scores using parameterised
distributions. Consequently, a number of hypotheses
have been proposed to constrain the mixture
distribution from which document scores could be drawn.
In this article, we show how a standard performance
measure (i.e., average precision) can be inferred from
a document score distribution using labelled data. We
use the accuracy of the inference of average precision
as a measure for determining the usefulness of a
particular model of document scores. We provide a
comprehensive study which shows that certain mixtures
of distributions are able to infer average precision
more accurately than others. Furthermore, we analyse a
number of mixture distributions with regard to the
recall-fallout convexity hypothesis and show that the
convexity hypothesis is practically useful.
Consequently, based on one of the best-performing
score-distribution models, we develop some techniques
for query-performance prediction (QPP) by automatically
estimating the parameters of the document
score-distribution model when relevance information is
unknown. We present experimental results that outline
the benefits of this approach to query-performance
prediction.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Huston:2014:IWS,
author = "Samuel Huston and J. Shane Culpepper and W. Bruce
Croft",
title = "Indexing Word Sequences for Ranked Retrieval",
journal = j-TOIS,
volume = "32",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2559168",
ISSN = "1046-8188",
bibdate = "Tue Jan 28 17:40:54 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Formulating and processing phrases and other term
dependencies to improve query effectiveness is an
important problem in information retrieval. However,
accessing word-sequence statistics using inverted
indexes requires unreasonable processing time or
substantial space overhead. Establishing a balance
between these competing space and time trade-offs can
dramatically improve system performance. In this
article, we present and analyze a new index structure
designed to improve query efficiency in dependency
retrieval models. By adapting a class of $ (\epsilon,
\delta) $-approximation algorithms originally proposed
for sketch summarization in networking applications, we
show how to accurately estimate statistics important in
term-dependency models with low, probabilistically
bounded error rates. The space requirements for the
vocabulary of the index is only logarithmically linked
to the size of the vocabulary. Empirically, we show
that the sketch index can reduce the space requirements
of the vocabulary component of an index of n -grams
consisting of between 1 and 4 words extracted from the
GOV2 collection to less than 0.01\% of the space
requirements of the vocabulary of a full index. We also
show that larger $n$-gram queries can be processed
considerably more efficiently than in current
alternatives, such as positional and next-word
indexes.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ge:2014:CAC,
author = "Yong Ge and Hui Xiong and Alexander Tuzhilin and Qi
Liu",
title = "Cost-Aware Collaborative Filtering for Travel Tour
Recommendations",
journal = j-TOIS,
volume = "32",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2559169",
ISSN = "1046-8188",
bibdate = "Tue Jan 28 17:40:54 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Advances in tourism economics have enabled us to
collect massive amounts of travel tour data. If
properly analyzed, this data could be a source of rich
intelligence for providing real-time decision making
and for the provision of travel tour recommendations.
However, tour recommendation is quite different from
traditional recommendations, because the tourist's
choice is affected directly by the travel costs, which
includes both financial and time costs. To that end, in
this article, we provide a focused study of cost-aware
tour recommendation. Along this line, we first propose
two ways to represent user cost preference. One way is
to represent user cost preference by a two-dimensional
vector. Another way is to consider the uncertainty
about the cost that a user can afford and introduce a
Gaussian prior to model user cost preference. With
these two ways of representing user cost preference, we
develop different cost-aware latent factor models by
incorporating the cost information into the
probabilistic matrix factorization (PMF) model, the
logistic probabilistic matrix factorization (LPMF)
model, and the maximum margin matrix factorization
(MMMF) model, respectively. When applied to real-world
travel tour data, all the cost-aware recommendation
models consistently outperform existing latent factor
models with a significant margin.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Nie:2014:LRD,
author = "Liqiang Nie and Yi-Liang Zhao and Xiangyu Wang and
Jialie Shen and Tat-Seng Chua",
title = "Learning to Recommend Descriptive Tags for Questions
in Social Forums",
journal = j-TOIS,
volume = "32",
number = "1",
pages = "5:1--5:??",
month = jan,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2559157",
ISSN = "1046-8188",
bibdate = "Tue Jan 28 17:40:54 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Around 40\% of the questions in the emerging
social-oriented question answering forums have at most
one manually labeled tag, which is caused by
incomprehensive question understanding or informal
tagging behaviors. The incompleteness of question tags
severely hinders all the tag-based manipulations, such
as feeds for topic-followers, ontological knowledge
organization, and other basic statistics. This article
presents a novel scheme that is able to comprehensively
learn descriptive tags for each question. Extensive
evaluations on a representative real-world dataset
demonstrate that our scheme yields significant gains
for question annotation, and more importantly, the
whole process of our approach is unsupervised and can
be extended to handle large-scale data.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bast:2014:EIB,
author = "Hannah Bast and Marjan Celikik",
title = "Efficient Index-Based Snippet Generation",
journal = j-TOIS,
volume = "32",
number = "2",
pages = "6:1--6:??",
month = apr,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2590972",
ISSN = "1046-8188",
bibdate = "Tue Apr 22 17:59:17 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Ranked result lists with query-dependent snippets have
become state of the art in text search. They are
typically implemented by searching, at query time, for
occurrences of the query words in the top-ranked
documents. This document-based approach has three
inherent problems: (i) when a document is indexed by
terms which it does not contain literally (e.g.,
related words or spelling variants), localization of
the corresponding snippets becomes problematic; (ii)
each query operator (e.g., phrase or proximity search)
has to be implemented twice, on the index side in order
to compute the correct result set, and on the
snippet-generation side to generate the appropriate
snippets; and (iii) in a worst case, the whole document
needs to be scanned for occurrences of the query words,
which could be problematic for very long documents. We
present a new index-based method that localizes
snippets by information solely computed from the index
and that overcomes all three problems. Unlike previous
index-based methods, we show how to achieve this at
essentially no extra cost in query processing time, by
a technique we call operator inversion. We also show
how our index-based method allows the caching of
individual segments instead of complete documents,
which enables a significantly larger cache hit-ratio as
compared to the document-based approach. We have fully
integrated our implementation with the CompleteSearch
engine.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhao:2014:MTA,
author = "Jiashu Zhao and Jimmy Xiangji Huang and Zheng Ye",
title = "Modeling Term Associations for Probabilistic
Information Retrieval",
journal = j-TOIS,
volume = "32",
number = "2",
pages = "7:1--7:??",
month = apr,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2590988",
ISSN = "1046-8188",
bibdate = "Tue Apr 22 17:59:17 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Traditionally, in many probabilistic retrieval models,
query terms are assumed to be independent. Although
such models can achieve reasonably good performance,
associations can exist among terms from a human being's
point of view. There are some recent studies that
investigate how to model term associations/dependencies
by proximity measures. However, the modeling of term
associations theoretically under the probabilistic
retrieval framework is still largely unexplored. In
this article, we introduce a new concept cross term, to
model term proximity, with the aim of boosting
retrieval performance. With cross terms, the
association of multiple query terms can be modeled in
the same way as a simple unigram term. In particular,
an occurrence of a query term is assumed to have an
impact on its neighboring text. The degree of the
query-term impact gradually weakens with increasing
distance from the place of occurrence. We use shape
functions to characterize such impacts. Based on this
assumption, we first propose a bigram CRoss TErm
Retrieval ( CRTER$_2$ ) model as the basis model, and
then recursively propose a generalized n-gram CRoss
TErm Retrieval ( CRTER$_n$ ) model for n query terms,
where n {$>$} 2. Specifically, a bigram cross term
occurs when the corresponding query terms appear close
to each other, and its impact can be modeled by the
intersection of the respective shape functions of the
query terms. For an n-gram cross term, we develop
several distance metrics with different properties and
employ them in the proposed models for ranking. We also
show how to extend the language model using the newly
proposed cross terms. Extensive experiments on a number
of TREC collections demonstrate the effectiveness of
our proposed models.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cui:2014:SSI,
author = "Peng Cui and Shao-Wei Liu and Wen-Wu Zhu and Huan-Bo
Luan and Tat-Seng Chua and Shi-Qiang Yang",
title = "Social-Sensed Image Search",
journal = j-TOIS,
volume = "32",
number = "2",
pages = "8:1--8:??",
month = apr,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2590974",
ISSN = "1046-8188",
bibdate = "Tue Apr 22 17:59:17 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Although Web search techniques have greatly facilitate
users' information seeking, there are still quite a lot
of search sessions that cannot provide satisfactory
results, which are more serious in Web image search
scenarios. How to understand user intent from observed
data is a fundamental issue and of paramount
significance in improving image search performance.
Previous research efforts mostly focus on discovering
user intent either from clickthrough behavior in user
search logs (e.g., Google), or from social data to
facilitate vertical image search in a few limited
social media platforms (e.g., Flickr). This article
aims to combine the virtues of these two information
sources to complement each other, that is, sensing and
understanding users' interests from social media
platforms and transferring this knowledge to rerank the
image search results in general image search engines.
Toward this goal, we first propose a novel
social-sensed image search framework, where both social
media and search engine are jointly considered. To
effectively and efficiently leverage these two kinds of
platforms, we propose an example-based user interest
representation and modeling method, where we construct
a hybrid graph from social media and propose a hybrid
random-walk algorithm to derive the user-image interest
graph. Moreover, we propose a social-sensed image
reranking method to integrate the user-image interest
graph from social media and search results from general
image search engines to rerank the images by fusing
their social relevance and visual relevance. We
conducted extensive experiments on real-world data from
Flickr and Google image search, and the results
demonstrated that the proposed methods can
significantly improve the social relevance of image
search results while maintaining visual relevance
well.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Markov:2014:TQQ,
author = "Ilya Markov and Fabio Crestani",
title = "Theoretical, Qualitative, and Quantitative Analyses of
Small-Document Approaches to Resource Selection",
journal = j-TOIS,
volume = "32",
number = "2",
pages = "9:1--9:??",
month = apr,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2590975",
ISSN = "1046-8188",
bibdate = "Tue Apr 22 17:59:17 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In a distributed retrieval setup, resource selection
is the problem of identifying and ranking relevant
sources of information for a given user's query. For
better usage of existing resource-selection techniques,
it is desirable to know what the fundamental
differences between them are and in what settings one
is superior to others. However, little is understood
still about the actual behavior of resource-selection
methods. In this work, we focus on small-document
approaches to resource selection that rank and select
sources based on the ranking of their documents. We
pose a number of research questions and approach them
by three types of analyses. First, we present existing
small-document techniques in a unified framework and
analyze them theoretically. Second, we propose using a
qualitative analysis to study the behavior of different
small-document approaches. Third, we present a novel
experimental methodology to evaluate small-document
techniques and to validate the results of the
qualitative analysis. This way, we answer the posed
research questions and provide insights about
small-document methods in general and about each
technique in particular.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Skaggs:2014:TMW,
author = "Bradley Skaggs and Lise Getoor",
title = "Topic Modeling for {Wikipedia} Link Disambiguation",
journal = j-TOIS,
volume = "32",
number = "3",
pages = "10:1--10:??",
month = jun,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2633044",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:20:38 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Many articles in the online encyclopedia Wikipedia
have hyperlinks to ambiguous article titles; these
ambiguous links should be replaced with links to
unambiguous articles, a process known as
disambiguation. We propose a novel statistical topic
model based on link text, which we refer to as the Link
Text Topic Model (LTTM), that we use to suggest new
link targets for ambiguous links. To evaluate our
model, we describe a method for extracting ground truth
for this link disambiguation task from edits made to
Wikipedia in a specific time period. We use this ground
truth to demonstrate the superiority of LTTM over other
existing link- and content-based approaches to
disambiguating links in Wikipedia. Finally, we build a
web service that uses LTTM to make suggestions to human
editors wanting to fix ambiguous links in Wikipedia.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yin:2014:LSI,
author = "Hongzhi Yin and Bin Cui and Yizhou Sun and Zhiting Hu
and Ling Chen",
title = "{LCARS}: a Spatial Item Recommender System",
journal = j-TOIS,
volume = "32",
number = "3",
pages = "11:1--11:??",
month = jun,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2629461",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:20:38 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Newly emerging location-based and event-based social
network services provide us with a new platform to
understand users' preferences based on their activity
history. A user can only visit a limited number of
venues/events and most of them are within a limited
distance range, so the user-item matrix is very sparse,
which creates a big challenge to the traditional
collaborative filtering-based recommender systems. The
problem becomes even more challenging when people
travel to a new city where they have no activity
information. In this article, we propose LCARS, a
location-content-aware recommender system that offers a
particular user a set of venues (e.g., restaurants and
shopping malls) or events (e.g., concerts and
exhibitions) by giving consideration to both personal
interest and local preference. This recommender system
can facilitate people's travel not only near the area
in which they live, but also in a city that is new to
them. Specifically, LCARS consists of two components:
offline modeling and online recommendation. The offline
modeling part, called LCA-LDA, is designed to learn the
interest of each individual user and the local
preference of each individual city by capturing item
cooccurrence patterns and exploiting item contents. The
online recommendation part takes a querying user along
with a querying city as input, and automatically
combines the learned interest of the querying user and
the local preference of the querying city to produce
the top- k recommendations. To speed up the online
process, a scalable query processing technique is
developed by extending both the Threshold Algorithm
(TA) and TA-approximation algorithm. We evaluate the
performance of our recommender system on two real
datasets, that is, DoubanEvent and Foursquare, and one
large-scale synthetic dataset. The results show the
superiority of LCARS in recommending spatial items for
users, especially when traveling to new cities, in
terms of both effectiveness and efficiency. Besides,
the experimental analysis results also demonstrate the
excellent interpretability of LCARS.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Laere:2014:GWD,
author = "Olivier {Van Laere} and Steven Schockaert and Vlad
Tanasescu and Bart Dhoedt and Christopher B. Jones",
title = "Georeferencing {Wikipedia} Documents Using Data from
Social Media Sources",
journal = j-TOIS,
volume = "32",
number = "3",
pages = "12:1--12:??",
month = jun,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2629685",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:20:38 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Social media sources such as Flickr and Twitter
continuously generate large amounts of textual
information (tags on Flickr and short messages on
Twitter). This textual information is increasingly
linked to geographical coordinates, which makes it
possible to learn how people refer to places by
identifying correlations between the occurrence of
terms and the locations of the corresponding social
media objects. Recent work has focused on how this
potentially rich source of geographic information can
be used to estimate geographic coordinates for
previously unseen Flickr photos or Twitter messages. In
this article, we extend this work by analysing to what
extent probabilistic language models trained on Flickr
and Twitter can be used to assign coordinates to
Wikipedia articles. Our results show that exploiting
these language models substantially outperforms both
(i) classical gazetteer-based methods (in particular,
using Yahoo! Placemaker and Geonames) and (ii) language
modelling approaches trained on Wikipedia alone. This
supports the hypothesis that social media are important
sources of geographic information, which are valuable
beyond the scope of individual applications.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Brisaboa:2014:XEX,
author = "Nieves R. Brisaboa and Ana Cerdeira-Pena and Gonzalo
Navarro",
title = "{XXS}: Efficient {XPath} Evaluation on Compressed
{XML} Documents",
journal = j-TOIS,
volume = "32",
number = "3",
pages = "13:1--13:??",
month = jun,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2629554",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:20:38 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The eXtensible Markup Language (XML) is acknowledged
as the de facto standard for semistructured data
representation and data exchange on the Web and many
other scenarios. A well-known shortcoming of XML is its
verbosity, which increases manipulation, transmission,
and processing costs. Various structure-blind and
structure-conscious compression techniques can be
applied to XML, and some are even access-friendly,
meaning that the documents can be efficiently accessed
in compressed form. Direct access is necessary to
implement the query languages XPath and XQuery, which
are the standard ones to exploit the expressiveness of
XML. While a good deal of theoretical and practical
proposals exist to solve XPath/XQuery operations on
XML, only a few ones are well integrated with a
compression format that supports the required access
operations on the XML data. In this work we go one step
further and design a compression format for XML
collections that boosts the performance of XPath
queries on the data. This is done by designing
compressed representations of the XML data that support
some complex operations apart from just accessing the
data, and those are exploited to solve key components
of the XPath queries. Our system, called XXS, is aimed
at XML collections containing natural language text,
which are compressed to within 35\%--50\% of their
original size while supporting a large subset of XPath
operations in time competitive with, and many times
outperforming, the best state-of-the-art systems that
work on uncompressed representations.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Awad:2014:CBV,
author = "George Awad and Paul Over and Wessel Kraaij",
title = "Content-Based Video Copy Detection Benchmarking at
{TRECVID}",
journal = j-TOIS,
volume = "32",
number = "3",
pages = "14:1--14:??",
month = jun,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2629531",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:20:38 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article presents an overview of the video copy
detection benchmark which was run over a period of 4
years (2008--2011) as part of the TREC Video Retrieval
(TRECVID) workshop series. The main contributions of
the article include (i) an examination of the evolving
design of the evaluation framework and its components
(system tasks, data, measures); (ii) a high-level
overview of results and best-performing approaches; and
(iii) a discussion of lessons learned over the four
years. The content-based copy detection (CCD) benchmark
worked with a large collection of synthetic queries,
which is atypical for TRECVID, as was the use of a
normalized detection cost framework. These particular
evaluation design choices are motivated and
appraised.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2014:TPB,
author = "Richong Zhang and Yongyi Mao",
title = "Trust Prediction via Belief Propagation",
journal = j-TOIS,
volume = "32",
number = "3",
pages = "15:1--15:??",
month = jun,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2629530",
ISSN = "1046-8188",
bibdate = "Wed Jul 16 17:20:38 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The prediction of trust relationships in social
networks plays an important role in the analytics of
the networks. Although various link prediction
algorithms for general networks may be adapted for this
purpose, the recent notion of ``trust propagation'' has
been shown to effectively capture the trust-formation
mechanisms and resulted in an effective prediction
algorithm. This article builds on the concept of trust
propagation and presents a probabilistic trust
propagation model. Our model exploits the modern
framework of probabilistic graphical models, more
specifically, factor graphs. Under this model, the
trust prediction problem can be formulated as a
statistical inference problem and we derive the belief
propagation algorithm as a solver for trust prediction.
The model and algorithm are tested using datasets from
Epinions and Ciao, by which performance advantages over
the previous algorithms are demonstrated.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Mahdabi:2014:PQF,
author = "Parvaz Mahdabi and Fabio Crestani",
title = "Patent Query Formulation by Synthesizing Multiple
Sources of Relevance Evidence",
journal = j-TOIS,
volume = "32",
number = "4",
pages = "16:1--16:??",
month = oct,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2651363",
ISSN = "1046-8188",
bibdate = "Tue Oct 28 16:57:21 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Patent prior art search is a task in patent retrieval
with the goal of finding documents which describe prior
art work related to a query patent. A query patent is a
full patent application composed of hundreds of terms
which does not represent a single focused information
need. Fortunately, other relevance evidence sources
(i.e., classification tags and bibliographical data)
provide additional details about the underlying
information need. In this article, we propose a unified
framework that integrates multiple relevance evidence
components for query formulation. We first build a
query model from the textual fields of a query patent.
To overcome the term mismatch, we expand this initial
query model with the term distribution of documents in
the citation graph, modeling old and recent domain
terminology. We build an IPC lexicon and perform query
expansion using this lexicon incorporating proximity
information. We performed an empirical evaluation on
two patent datasets. Our results show that employing
the temporal features of documents has a precision
enhancing effect, while query expansion using IPC
lexicon improves the recall of the final rank list.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Forsati:2014:MFE,
author = "Rana Forsati and Mehrdad Mahdavi and Mehrnoush
Shamsfard and Mohamed Sarwat",
title = "Matrix Factorization with Explicit Trust and Distrust
Side Information for Improved Social Recommendation",
journal = j-TOIS,
volume = "32",
number = "4",
pages = "17:1--17:??",
month = oct,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2641564",
ISSN = "1046-8188",
bibdate = "Tue Oct 28 16:57:21 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the advent of online social networks, recommender
systems have became crucial for the success of many
online applications/services due to their significance
role in tailoring these applications to user-specific
needs or preferences. Despite their increasing
popularity, in general, recommender systems suffer from
data sparsity and cold-start problems. To alleviate
these issues, in recent years, there has been an
upsurge of interest in exploiting social information
such as trust relations among users along with the
rating data to improve the performance of recommender
systems. The main motivation for exploiting trust
information in the recommendation process stems from
the observation that the ideas we are exposed to and
the choices we make are significantly influenced by our
social context. However, in large user communities, in
addition to trust relations, distrust relations also
exist between users. For instance, in Epinions, the
concepts of personal ``web of trust'' and personal
``block list'' allow users to categorize their friends
based on the quality of reviews into trusted and
distrusted friends, respectively. Hence, it will be
interesting to incorporate this new source of
information in recommendation as well. In contrast to
the incorporation of trust information in
recommendation which is thriving, the potential of
explicitly incorporating distrust relations is almost
unexplored. In this article, we propose a matrix
factorization-based model for recommendation in social
rating networks that properly incorporates both trust
and distrust relationships aiming to improve the
quality of recommendations and mitigate the data
sparsity and cold-start users issues. Through
experiments on the Epinions dataset, we show that our
new algorithm outperforms its standard trust-enhanced
or distrust-enhanced counterparts with respect to
accuracy, thereby demonstrating the positive effect
that incorporation of explicit distrust information can
have on recommender systems.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lu:2014:BSI,
author = "Shiyang Lu and Tao Mei and Jingdong Wang and Jian
Zhang and Zhiyong Wang and Shipeng Li",
title = "Browse-to-Search: Interactive Exploratory Search with
Visual Entities",
journal = j-TOIS,
volume = "32",
number = "4",
pages = "18:1--18:??",
month = oct,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2630420",
ISSN = "1046-8188",
bibdate = "Tue Oct 28 16:57:21 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the development of image search technology, users
are no longer satisfied with searching for images using
just metadata and textual descriptions. Instead, more
search demands are focused on retrieving images based
on similarities in their contents (textures, colors,
shapes etc.). Nevertheless, one image may deliver rich
or complex content and multiple interests. Sometimes
users do not sufficiently define or describe their
seeking demands for images even when general search
interests appear, owing to a lack of specific knowledge
to express their intents. A new form of information
seeking activity, referred to as exploratory search, is
emerging in the research community, which generally
combines browsing and searching content together to
help users gain additional knowledge and form accurate
queries, thereby assisting the users with their seeking
and investigation activities. However, there have been
few attempts at addressing integrated exploratory
search solutions when image browsing is incorporated
into the exploring loop. In this work, we investigate
the challenges of understanding users' search interests
from the images being browsed and infer their actual
search intentions. We develop a novel system to explore
an effective and efficient way for allowing users to
seamlessly switch between browse and search processes,
and naturally complete visual-based exploratory search
tasks. The system, called Browse-to-Search enables
users to specify their visual search interests by
circling any visual objects in the webpages being
browsed, and then the system automatically forms the
visual entities to represent users' underlying intent.
One visual entity is not limited by the original image
content, but also encapsulated by the textual-based
browsing context and the associated heterogeneous
attributes. We use large-scale image search technology
to find the associated textual attributes from the
repository. Users can then utilize the encapsulated
visual entities to complete search tasks. The
Browse-to-Search system is one of the first attempts to
integrate browse and search activities for a
visual-based exploratory search, which is characterized
by four unique properties: (1) in session-searching is
performed during browsing session and search results
naturally accompany with browsing content; (2) in
context-the pages being browsed provide text-based
contextual cues for searching; (3) in focus-users can
focus on the visual content of interest without
worrying about the difficulties of query formulation,
and visual entities will be automatically formed; and
(4) intuitiveness-a touch and visual search-based user
interface provides a natural user experience. We deploy
the Browse-to-Search system on tablet devices and
evaluate the system performance using millions of
images. We demonstrate that it is effective and
efficient in facilitating the user's exploratory search
compared to the conventional image search methods and,
more importantly, provides users with more robust
results to satisfy their exploring experience.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ture:2014:ERS,
author = "Ferhan Ture and Jimmy Lin",
title = "Exploiting Representations from Statistical Machine
Translation for Cross-Language Information Retrieval",
journal = j-TOIS,
volume = "32",
number = "4",
pages = "19:1--19:??",
month = oct,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2644807",
ISSN = "1046-8188",
bibdate = "Tue Oct 28 16:57:21 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This work explores how internal representations of
modern statistical machine translation systems can be
exploited for cross-language information retrieval. We
tackle two core issues that are central to query
translation: how to exploit context to generate more
accurate translations and how to preserve ambiguity
that may be present in the original query, thereby
retaining a diverse set of translation alternatives.
These two considerations are often in tension since
ambiguity in natural language is typically resolved by
exploiting context, but effective retrieval requires
striking the right balance. We propose two novel query
translation approaches: the grammar-based approach
extracts translation probabilities from translation
grammars, while the decoder-based approach takes
advantage of n -best translation hypotheses. Both are
context-sensitive, in contrast to a baseline
context-insensitive approach that uses bilingual
dictionaries for word-by-word translation. Experimental
results show that by ``opening up'' modern statistical
machine translation systems, we can access intermediate
representations that yield high retrieval
effectiveness. By combining evidence from multiple
sources, we demonstrate significant improvements over
competitive baselines on standard cross-language
information retrieval test collections. In addition to
effectiveness, the efficiency of our techniques are
explored as well.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Raman:2014:UID,
author = "Karthik Raman and Paul N. Bennett and Kevyn
Collins-Thompson",
title = "Understanding Intrinsic Diversity in {Web} Search:
Improving Whole-Session Relevance",
journal = j-TOIS,
volume = "32",
number = "4",
pages = "20:1--20:??",
month = oct,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2629553",
ISSN = "1046-8188",
bibdate = "Tue Oct 28 16:57:21 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Current research on Web search has focused on
optimizing and evaluating single queries. However, a
significant fraction of user queries are part of more
complex tasks [Jones and Klinkner 2008] which span
multiple queries across one or more search sessions
[Liu and Belkin 2010; Kotov et al. 2011]. An ideal
search engine would not only retrieve relevant results
for a user's particular query but also be able to
identify when the user is engaged in a more complex
task and aid the user in completing that task [Morris
et al. 2008; Agichtein et al. 2012]. Toward optimizing
whole-session or task relevance, we characterize and
address the problem of intrinsic diversity (ID) in
retrieval [Radlinski et al. 2009], a type of complex
task that requires multiple interactions with current
search engines. Unlike existing work on extrinsic
diversity [Carbonell and Goldstein 1998; Zhai et al.
2003; Chen and Karger 2006] that deals with ambiguity
in intent across multiple users, ID queries often have
little ambiguity in intent but seek content covering a
variety of aspects on a shared theme. In such
scenarios, the underlying needs are typically
exploratory, comparative, or breadth-oriented in
nature. We identify and address three key problems for
ID retrieval: identifying authentic examples of ID
tasks from post-hoc analysis of behavioral signals in
search logs; learning to identify initiator queries
that mark the start of an ID search task; and given an
initiator query, predicting which content to prefetch
and rank.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2014:CDS,
author = "Jianguo Wang and Eric Lo and Man Lung Yiu and Jiancong
Tong and Gang Wang and Xiaoguang Liu",
title = "Cache Design of {SSD}-Based Search Engine
Architectures: an Experimental Study",
journal = j-TOIS,
volume = "32",
number = "4",
pages = "21:1--21:??",
month = oct,
year = "2014",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2661629",
ISSN = "1046-8188",
bibdate = "Tue Oct 28 16:57:21 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Caching is an important optimization in search engine
architectures. Existing caching techniques for search
engine optimization are mostly biased towards the
reduction of random accesses to disks, because random
accesses are known to be much more expensive than
sequential accesses in traditional magnetic hard disk
drive (HDD). Recently, solid-state drive (SSD) has
emerged as a new kind of secondary storage medium, and
some search engines like Baidu have already used SSD to
completely replace HDD in their infrastructure. One
notable property of SSD is that its random access
latency is comparable to its sequential access latency.
Therefore, the use of SSDs to replace HDDs in a search
engine infrastructure may void the cache management of
existing search engines. In this article, we carry out
a series of empirical experiments to study the impact
of SSD on search engine cache management. Based on the
results, we give insights to practitioners and
researchers on how to adapt the infrastructure and
caching policies for SSD-based search engines.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bennett:2015:OSI,
author = "Paul N. Bennett and Diane Kelly and Ryen W. White and
Yi Zhang",
title = "Overview of the Special Issue on Contextual Search and
Recommendation",
journal = j-TOIS,
volume = "33",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2691351",
ISSN = "1046-8188",
bibdate = "Tue Mar 17 18:01:38 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "1e",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cole:2015:UAP,
author = "Michael J. Cole and Chathra Hendahewa and Nicholas J.
Belkin and Chirag Shah",
title = "User Activity Patterns During Information Search",
journal = j-TOIS,
volume = "33",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699656",
ISSN = "1046-8188",
bibdate = "Tue Mar 17 18:01:38 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Personalization of support for information seeking
depends crucially on the information retrieval system's
knowledge of the task that led the person to engage in
information seeking. Users work during information
search sessions to satisfy their task goals, and their
activity is not random. To what degree are there
patterns in the user activity during information search
sessions? Do activity patterns reflect the user's
situation as the user moves through the search task
under the influence of his or her task goal? Do these
patterns reflect aspects of different types of
information-seeking tasks? Could such activity patterns
identify contexts within which information seeking
takes place? To investigate these questions, we model
sequences of user behaviors in two independent user
studies of information search sessions (N = 32 users,
128 sessions, and N = 40 users, 160 sessions). Two
representations of user activity patterns are used. One
is based on the sequences of page use; the other is
based on a cognitive representation of information
acquisition derived from eye movement patterns in
service of the reading process. One of the user studies
considered journalism work tasks; the other concerned
background research in genomics using search tasks
taken from the TREC Genomics Track. The search tasks
differed in basic dimensions of complexity,
specificity, and the type of information product
(intellectual or factual) needed to achieve the overall
task goal. The results show that similar patterns of
user activity are observed at both the cognitive and
page use levels. The activity patterns at both
representation layers are able to distinguish between
task types in similar ways and, to some degree, between
tasks of different levels of difficulty. We explore
relationships between the results and task difficulty
and discuss the use of activity patterns to explore
events within a search session. User activity patterns
can be at least partially observed in server-side
search logs. A focus on patterns of user activity
sequences may contribute to the development of
information systems that better personalize the user's
search experience.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yuan:2015:WWW,
author = "Quan Yuan and Gao Cong and Kaiqi Zhao and Zongyang Ma
and Aixin Sun",
title = "Who, Where, When, and What: a Nonparametric {Bayesian}
Approach to Context-aware Recommendation and Search for
{Twitter} Users",
journal = j-TOIS,
volume = "33",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699667",
ISSN = "1046-8188",
bibdate = "Tue Mar 17 18:01:38 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Micro-blogging services and location-based social
networks, such as Twitter, Weibo, and Foursquare,
enable users to post short messages with timestamps and
geographical annotations. The rich
spatial-temporal-semantic information of individuals
embedded in these geo-annotated short messages provides
exciting opportunity to develop many context-aware
applications in ubiquitous computing environments.
Example applications include contextual recommendation
and contextual search. To obtain accurate
recommendations and most relevant search results, it is
important to capture users' contextual information
(e.g., time and location) and to understand users'
topical interests and intentions. While time and
location can be readily captured by smartphones,
understanding user's interests and intentions calls for
effective methods in modeling user mobility behavior.
Here, user mobility refers to who visits which place at
what time for what activity. That is, user mobility
behavior modeling must consider user (Who), spatial
(Where), temporal (When), and activity (What) aspects.
Unfortunately, no previous studies on user mobility
behavior modeling have considered all of the four
aspects jointly, which have complex interdependencies.
In our preliminary study, we propose the first solution
named W$^4$ (short for Who, Where, When, and What) to
discover user mobility behavior from the four aspects.
In this article, we further enhance W$^4$ and propose a
nonparametric Bayesian model named EW$^4$ (short for
Enhanced W$^4$ ). EW$^4$ requires no parameter tuning
and achieves better results over W$^4$ in our
experiments. Given some of the four aspects of a user
(e.g., time), our model is able to infer information of
the other aspects (e.g., location and topical words).
Thus, our model has a variety of context-aware
applications, particularly in contextual search and
recommendation. Experimental results on two real-world
datasets show that the proposed model is effective in
discovering users' spatial-temporal topics. The model
also significantly outperforms state-of-the-art
baselines for various tasks including location
prediction for tweets and requirement-aware location
recommendation.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Jarvelin:2015:TBI,
author = "Kalervo J{\"a}rvelin and Pertti Vakkari and Paavo
Arvola and Feza Baskaya and Anni J{\"a}rvelin and Jaana
Kek{\"a}l{\"a}inen and Heikki Keskustalo and Sanna
Kumpulainen and Miamaria Saastamoinen and Reijo
Savolainen and Eero Sormunen",
title = "Task-Based Information Interaction Evaluation: The
Viewpoint of Program Theory",
journal = j-TOIS,
volume = "33",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699660",
ISSN = "1046-8188",
bibdate = "Tue Mar 17 18:01:38 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Evaluation is central in research and development of
information retrieval (IR). In addition to designing
and implementing new retrieval mechanisms, one must
also show through rigorous evaluation that they are
effective. A major focus in IR is IR mechanisms'
capability of ranking relevant documents optimally for
the users, given a query. Searching for information in
practice involves searchers, however, and is highly
interactive. When human searchers have been
incorporated in evaluation studies, the results have
often suggested that better ranking does not
necessarily lead to better search task, or work task,
performance. Therefore, it is not clear which system or
interface features should be developed to improve the
effectiveness of human task performance. In the present
article, we focus on the evaluation of task-based
information interaction (TBII). We give special
emphasis to learning tasks to discuss TBII in more
concrete terms. Information interaction is here
understood as behavioral and cognitive activities
related to task planning, searching information items,
selecting between them, working with them, and
synthesizing and reporting. These five generic
activities contribute to task performance and outcome
and can be supported by information systems. In an
attempt toward task-based evaluation, we introduce
program theory as the evaluation framework. Such
evaluation can investigate whether a program consisting
of TBII activities and tools works and how it works
and, further, provides a causal description of program
(in)effectiveness. Our goal in the present article is
to structure TBII on the basis of the five generic
activities and consider the evaluation of each activity
using the program theory framework. Finally, we combine
these activity-based program theories in an overall
evaluation framework for TBII. Such an evaluation is
complex due to the large number of factors affecting
information interaction. Instead of presenting tested
program theories, we illustrate how the evaluation of
TBII should be accomplished using the program theory
framework in the evaluation of systems and behaviors,
and their interactions, comprehensively in context.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Alhindi:2015:PBS,
author = "Azhar Alhindi and Udo Kruschwitz and Chris Fox and
M-Dyaa Albakour",
title = "Profile-Based Summarisation for {Web} Site
Navigation",
journal = j-TOIS,
volume = "33",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699661",
ISSN = "1046-8188",
bibdate = "Tue Mar 17 18:01:38 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Information systems that utilise contextual
information have the potential of helping a user
identify relevant information more quickly and more
accurately than systems that work the same for all
users and contexts. Contextual information comes in a
variety of types, often derived from records of past
interactions between a user and the information system.
It can be individual or group based. We are focusing on
the latter, harnessing the search behaviour of cohorts
of users, turning it into a domain model that can then
be used to assist other users of the same cohort. More
specifically, we aim to explore how such a domain model
is best utilised for profile-biased summarisation of
documents in a navigation scenario in which such
summaries can be displayed as hover text as a user
moves the mouse over a link. The main motivation is to
help a user find relevant documents more quickly. Given
the fact that the Web in general has been studied
extensively already, we focus our attention on Web
sites and similar document collections. Such
collections can be notoriously difficult to search or
explore. The process of acquiring the domain model is
not a research interest here; we simply adopt a
biologically inspired method that resembles the idea of
ant colony optimisation. This has been shown to work
well in a variety of application areas. The model can
be built in a continuous learning cycle that exploits
search patterns as recorded in typical query log files.
Our research explores different summarisation
techniques, some of which use the domain model and some
that do not. We perform task-based evaluations of these
different techniques-thus of the impact of the domain
model and profile-biased summarisation-in the context
of Web site navigation.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chuklin:2015:CAI,
author = "Aleksandr Chuklin and Anne Schuth and Ke Zhou and
Maarten {De Rijke}",
title = "A Comparative Analysis of Interleaving Methods for
Aggregated Search",
journal = j-TOIS,
volume = "33",
number = "2",
pages = "5:1--5:??",
month = feb,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2668120",
ISSN = "1046-8188",
bibdate = "Fri Mar 6 09:56:29 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "A result page of a modern search engine often goes
beyond a simple list of ``10 blue links.'' Many
specific user needs (e.g., News, Image, Video) are
addressed by so-called aggregated or vertical search
solutions: specially presented documents, often
retrieved from specific sources, that stand out from
the regular organic Web search results. When it comes
to evaluating ranking systems, such complex result
layouts raise their own challenges. This is especially
true for so-called interleaving methods that have
arisen as an important type of online evaluation: by
mixing results from two different result pages,
interleaving can easily break the desired Web layout in
which vertical documents are grouped together, and
hence hurt the user experience. We conduct an analysis
of different interleaving methods as applied to
aggregated search engine result pages. Apart from
conventional interleaving methods, we propose two
vertical-aware methods: one derived from the widely
used Team-Draft Interleaving method by adjusting it in
such a way that it respects vertical document
groupings, and another based on the recently introduced
Optimized Interleaving framework. We show that our
proposed methods are better at preserving the user
experience than existing interleaving methods while
still performing well as a tool for comparing ranking
systems. For evaluating our proposed vertical-aware
interleaving methods, we use real-world click data as
well as simulated clicks and simulated ranking
systems.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bing:2015:WQR,
author = "Lidong Bing and Wai Lam and Tak-Lam Wong and Shoaib
Jameel",
title = "{Web} Query Reformulation via Joint Modeling of Latent
Topic Dependency and Term Context",
journal = j-TOIS,
volume = "33",
number = "2",
pages = "6:1--6:??",
month = feb,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699666",
ISSN = "1046-8188",
bibdate = "Fri Mar 6 09:56:29 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "An important way to improve users' satisfaction in Web
search is to assist them by issuing more effective
queries. One such approach is query reformulation,
which generates new queries according to the current
query issued by users. A common procedure for
conducting reformulation is to generate some candidate
queries first, then a scoring method is employed to
assess these candidates. Currently, most of the
existing methods are context based. They rely heavily
on the context relation of terms in the history queries
and cannot detect and maintain the semantic consistency
of queries. In this article, we propose a graphical
model to score queries. The proposed model exploits a
latent topic space, which is automatically derived from
the query log, to detect semantic dependency of terms
in a query and dependency among topics. Meanwhile, the
graphical model also captures the term context in the
history query by skip-bigram and n-gram language
models. In addition, our model can be easily extended
to consider users' history search interests when we
conduct query reformulation for different users. In the
task of candidate query generation, we investigate a
social tagging data resource-Delicious bookmark-to
generate addition and substitution patterns that are
employed as supplements to the patterns generated from
query log data.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tian:2015:TTA,
author = "Yonghong Tian and Mengren Qian and Tiejun Huang",
title = "{TASC}: a Transformation-Aware Soft Cascading Approach
for Multimodal Video Copy Detection",
journal = j-TOIS,
volume = "33",
number = "2",
pages = "7:1--7:??",
month = feb,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699662",
ISSN = "1046-8188",
bibdate = "Fri Mar 6 09:56:29 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "How to precisely and efficiently detect near-duplicate
copies with complicated audiovisual transformations
from a large-scale video database is a challenging
task. To cope with this challenge, this article
proposes a transformation-aware soft cascading (TASC)
approach for multimodal video copy detection.
Basically, our approach divides query videos into some
categories and then for each category designs a
transformation-aware chain to organize several
detectors in a cascade structure. In each chain,
efficient but simple detectors are placed in the
forepart, whereas effective but complex detectors are
located in the rear. To judge whether two videos are
near-duplicates, a Detection-on-Copy-Units mechanism is
introduced in the TASC, which makes the decision of
copy detection depending on the similarity between
their most similar fractions, called copy units (CUs),
rather than the video-level similarity. Following this,
we propose a CU search algorithm to find a pair of CUs
from two videos and a CU-based localization algorithm
to find the precise locations of their copy segments
that are with the asserted CUs as the center. Moreover,
to address the problem that the copies and noncopies
are possibly linearly inseparable in the feature space,
the TASC also introduces a flexible strategy, called
soft decision boundary, to replace the single threshold
strategy for each detector. Its basic idea is to
automatically learn two thresholds for each detector to
examine the easy-to-judge copies and noncopies,
respectively, and meanwhile to train a nonlinear
classifier to further check those hard-to-judge ones.
Extensive experiments on three benchmark datasets
showed that the TASC can achieve excellent copy
detection accuracy and localization precision with a
very high processing efficiency.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Na:2015:TSD,
author = "Seung-Hoon Na",
title = "Two-Stage Document Length Normalization for
Information Retrieval",
journal = j-TOIS,
volume = "33",
number = "2",
pages = "8:1--8:??",
month = feb,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699669",
ISSN = "1046-8188",
bibdate = "Fri Mar 6 09:56:29 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The standard approach for term frequency normalization
is based only on the document length. However, it does
not distinguish the verbosity from the scope, these
being the two main factors determining the document
length. Because the verbosity and scope have largely
different effects on the increase in term frequency,
the standard approach can easily suffer from
insufficient or excessive penalization depending on the
specific type of long document. To overcome these
problems, this article proposes two-stage normalization
by performing verbosity and scope normalization
separately, and by employing different penalization
functions. In verbosity normalization, each document is
prenormalized by dividing the term frequency by the
verbosity of the document. In scope normalization, an
existing retrieval model is applied in a
straightforward manner to the prenormalized document,
finally leading us to formulate our proposed verbosity
normalized (VN) retrieval model. Experimental results
carried out on standard TREC collections demonstrate
that the VN model leads to marginal but statistically
significant improvements over standard retrieval
models.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ah-Pine:2015:UVT,
author = "Julien Ah-Pine and Gabriela Csurka and St{\'e}phane
Clinchant",
title = "Unsupervised Visual and Textual Information Fusion in
{CBMIR} Using Graph-Based Methods",
journal = j-TOIS,
volume = "33",
number = "2",
pages = "9:1--9:??",
month = feb,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699668",
ISSN = "1046-8188",
bibdate = "Fri Mar 6 09:56:29 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Multimedia collections are more than ever growing in
size and diversity. Effective multimedia retrieval
systems are thus critical to access these datasets from
the end-user perspective and in a scalable way. We are
interested in repositories of image/text multimedia
objects and we study multimodal information fusion
techniques in the context of content-based multimedia
information retrieval. We focus on graph-based methods,
which have proven to provide state-of-the-art
performances. We particularly examine two such methods:
cross-media similarities and random-walk-based scores.
From a theoretical viewpoint, we propose a unifying
graph-based framework, which encompasses the two
aforementioned approaches. Our proposal allows us to
highlight the core features one should consider when
using a graph-based technique for the combination of
visual and textual information. We compare cross-media
and random-walk-based results using three different
real-world datasets. From a practical standpoint, our
extended empirical analyses allow us to provide
insights and guidelines about the use of graph-based
methods for multimodal information fusion in
content-based multimedia information retrieval.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Anagnostopoulos:2015:SQC,
author = "Aris Anagnostopoulos and Luca Becchetti and Ilaria
Bordino and Stefano Leonardi and Ida Mele and Piotr
Sankowski",
title = "Stochastic Query Covering for Fast Approximate
Document Retrieval",
journal = j-TOIS,
volume = "33",
number = "3",
pages = "11:1--11:??",
month = feb,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699671",
ISSN = "1046-8188",
bibdate = "Fri Mar 6 09:56:30 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We design algorithms that, given a collection of
documents and a distribution over user queries, return
a small subset of the document collection in such a way
that we can efficiently provide high-quality answers to
user queries using only the selected subset. This
approach has applications when space is a constraint or
when the query-processing time increases significantly
with the size of the collection. We study our
algorithms through the lens of stochastic analysis and
prove that even though they use only a small fraction
of the entire collection, they can provide answers to
most user queries, achieving a performance close to the
optimal. To complement our theoretical findings, we
experimentally show the versatility of our approach by
considering two important cases in the context of Web
search. In the first case, we favor the retrieval of
documents that are relevant to the query, whereas in
the second case we aim for document diversification.
Both the theoretical and the experimental analysis
provide strong evidence of the potential value of query
covering in diverse application scenarios.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Nong:2015:ISS,
author = "Ge Nong and Wai Hong Chan and Sheng Qing Hu and Yi
Wu",
title = "Induced Sorting Suffixes in External Memory",
journal = j-TOIS,
volume = "33",
number = "3",
pages = "12:1--12:??",
month = feb,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2699665",
ISSN = "1046-8188",
bibdate = "Fri Mar 6 09:56:30 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We present in this article an external memory
algorithm, called disk SA-IS (DSA-IS), to exactly
emulate the induced sorting algorithm SA-IS previously
proposed for sorting suffixes in RAM. DSA-IS is a new
disk-friendly method for sequentially retrieving the
preceding character of a sorted suffix to induce the
order of the preceding suffix. For a size $n$ string of
a constant or integer alphabet, given the RAM capacity
$ \Omega ((n W)^{0.5}) $, where $W$ is the size of each
I/O buffer that is large enough to amortize the
overhead of each access to disk, both the CPU time and
peak disk use of DSA-IS are $ O(n)$. Our experimental
study shows that on average, DSA-IS achieves the best
time and space results of all of the existing external
memory algorithms based on the induced sorting
principle.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yang:2015:BHC,
author = "Hui Yang",
title = "Browsing Hierarchy Construction by Minimum Evolution",
journal = j-TOIS,
volume = "33",
number = "3",
pages = "13:1--13:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2714574",
ISSN = "1046-8188",
bibdate = "Mon Mar 23 17:09:13 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Hierarchies serve as browsing tools to access
information in document collections. This article
explores techniques to derive browsing hierarchies that
can be used as an information map for task-based
search. It proposes a novel minimum-evolution hierarchy
construction framework that directly learns semantic
distances from training data and from users to
construct hierarchies. The aim is to produce globally
optimized hierarchical structures by incorporating
user-generated task specifications into the general
learning framework. Both an automatic version of the
framework and an interactive version are presented. A
comparison with state-of-the-art systems and a user
study jointly demonstrate that the proposed framework
is highly effective.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pal:2015:MAR,
author = "Aditya Pal",
title = "Metrics and Algorithms for Routing Questions to User
Communities",
journal = j-TOIS,
volume = "33",
number = "3",
pages = "14:1--14:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2724706",
ISSN = "1046-8188",
bibdate = "Mon Mar 23 17:09:13 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "An online community consists of a group of users who
share a common interest, background, or experience, and
their collective goal is to contribute toward the
welfare of the community members. Several websites
allow their users to create and manage niche
communities, such as Yahoo! Groups, Facebook Groups,
Google+ Circles, and WebMD Forums. These community
services also exist within enterprises, such as IBM
Connections. Question answering within these
communities enables their members to exchange knowledge
and information with other community members. However,
the onus of finding the right community for question
asking lies with an individual user. The overwhelming
number of communities necessitates the need for a good
question routing strategy so that new questions get
routed to an appropriately focused community and thus
get resolved in a reasonable time frame. In this
article, we consider the novel problem of routing a
question to the right community and propose a framework
for selecting and ranking the relevant communities for
a question. We propose several novel features for
modeling the three main entities of the system:
questions, users, and communities. We propose features
such as language attributes, inclination to respond,
user familiarity, and difficulty of a question; based
on these features, we propose similarity metrics
between the routed question and the system entities. We
introduce a Cutoff-Aggregation ( CA ) algorithm that
aggregates the entity similarity within a community to
compute that community's relevance. We introduce two k
-nearest-neighbor ( knn ) algorithms that are a natural
instantiation of the CA algorithm, which are
computationally efficient and evaluate several ranking
algorithms over the aggregate similarity scores
computed by the two knn algorithms. We propose
clustering techniques to speed up our recommendation
framework and show how pipelining can improve the model
performance. We demonstrate the effectiveness of our
framework on two large real-world datasets.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhao:2015:GSB,
author = "Wayne Xin Zhao and Xudong Zhang and Daniel Lemire and
Dongdong Shan and Jian-Yun Nie and Hongfei Yan and
Ji-Rong Wen",
title = "A General {SIMD}-Based Approach to Accelerating
Compression Algorithms",
journal = j-TOIS,
volume = "33",
number = "3",
pages = "15:1--15:??",
month = mar,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2735629",
ISSN = "1046-8188",
bibdate = "Mon Mar 23 17:09:13 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/datacompression.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Compression algorithms are important for data-oriented
tasks, especially in the era of ``Big Data.'' Modern
processors equipped with powerful SIMD instruction sets
provide us with an opportunity for achieving better
compression performance. Previous research has shown
that SIMD-based optimizations can multiply decoding
speeds. Following these pioneering studies, we propose
a general approach to accelerate compression
algorithms. By instantiating the approach, we have
developed several novel integer compression algorithms,
called Group-Simple, Group-Scheme, Group-AFOR, and
Group-PFD, and implemented their corresponding
vectorized versions. We evaluate the proposed
algorithms on two public TREC datasets, a Wikipedia
dataset, and a Twitter dataset. With competitive
compression ratios and encoding speeds, our SIMD-based
algorithms outperform state-of-the-art nonvectorized
algorithms with respect to decoding speeds.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Han:2015:USC,
author = "Shuguang Han and Zhen Yue and Daqing He",
title = "Understanding and Supporting Cross-Device {Web} Search
for Exploratory Tasks with Mobile Touch Interactions",
journal = j-TOIS,
volume = "33",
number = "4",
pages = "16:1--16:??",
month = may,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2738036",
ISSN = "1046-8188",
bibdate = "Fri Aug 7 08:59:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Mobile devices enable people to look for information
at the moment when their information needs are
triggered. While experiencing complex information needs
that require multiple search sessions, users may
utilize desktop computers to fulfill information needs
started on mobile devices. Under the context of
mobile-to-desktop web search, this article analyzes
users' behavioral patterns and compares them to the
patterns in desktop-to-desktop web search. Then, we
examine several approaches of using Mobile Touch
Interactions (MTIs) to infer relevant content so that
such content can be used for supporting subsequent
search queries on desktop computers. The experimental
data used in this article was collected through a user
study involving 24 participants and six properly
designed cross-device web search tasks. Our
experimental results show that (1) users'
mobile-to-desktop search behaviors do significantly
differ from desktop-to-desktop search behaviors in
terms of information exploration, sense-making and
repeated behaviors. (2) MTIs can be employed to predict
the relevance of click-through documents, but applying
document-level relevant content based on the predicted
relevance does not improve search performance. (3) MTIs
can also be used to identify the relevant text chunks
at a fine-grained subdocument level. Such relevant
information can achieve better search performance than
the document-level relevant content. In addition, such
subdocument relevant information can be combined with
document-level relevance to further improve the search
performance. However, the effectiveness of these
methods relies on the sufficiency of click-through
documents. (4) MTIs can also be obtained from the
Search Engine Results Pages (SERPs). The subdocument
feedbacks inferred from this set of MTIs even
outperform the MTI-based subdocument feedback from the
click-through documents.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Kulkarni:2015:SSE,
author = "Anagha Kulkarni and Jamie Callan",
title = "Selective Search: Efficient and Effective Search of
Large Textual Collections",
journal = j-TOIS,
volume = "33",
number = "4",
pages = "17:1--17:??",
month = may,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2738035",
ISSN = "1046-8188",
bibdate = "Fri Aug 7 08:59:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The traditional search solution for large collections
divides the collection into subsets ( shards ), and
processes the query against all shards in parallel (
exhaustive search ). The search cost and the
computational requirements of this approach are often
prohibitively high for organizations with few
computational resources. This article investigates and
extends an alternative: selective search, an approach
that partitions the dataset based on document
similarity to obtain topic-based shards, and searches
only a few shards that are estimated to contain
relevant documents for the query. We propose shard
creation techniques that are scalable, efficient,
self-reliant, and create topic-based shards with low
variance in size, and high density of relevant
documents. The experimental results demonstrate that
the effectiveness of selective search is on par with
that of exhaustive search, and the corresponding search
costs are substantially lower with the former. Also,
the majority of the queries perform as well or better
with selective search. An oracle experiment that uses
optimal shard ranking for a query indicates that
selective search can outperform the effectiveness of
exhaustive search. Comparison with a query optimization
technique shows higher improvements in efficiency with
selective search. The overall best efficiency is
achieved when the two techniques are combined in an
optimized selective search approach.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{White:2015:BDB,
author = "Ryen W. White and Eric Horvitz",
title = "Belief Dynamics and Biases in {Web} Search",
journal = j-TOIS,
volume = "33",
number = "4",
pages = "18:1--18:??",
month = may,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2746229",
ISSN = "1046-8188",
bibdate = "Fri Aug 7 08:59:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We investigate how beliefs about the efficacy of
medical interventions are influenced by searchers'
exposure to information on retrieved Web pages. We
present a methodology for measuring participants'
beliefs and confidence about the efficacy of treatment
before, during, and after search episodes. We consider
interventions studied in the Cochrane collection of
meta-analyses. We extract related queries from search
engine logs and consider the Cochrane assessments as
ground truth. We analyze the dynamics of belief over
time and show the influence of prior beliefs and
confidence at the end of sessions. We present evidence
for confirmation bias and for anchoring-and-adjustment
during search and retrieval. Then, we build predictive
models to estimate postsearch beliefs using sets of
features about behavior and content. The findings
provide insights about the influence of Web content on
the beliefs of people and have implications for the
design of search systems.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Dang:2015:FFI,
author = "Edward Kai FUNG Dang and Robert Wing Pong Luk and
James Allan",
title = "Fast Forward Index Methods for Pseudo-Relevance
Feedback Retrieval",
journal = j-TOIS,
volume = "33",
number = "4",
pages = "19:1--19:??",
month = may,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2744199",
ISSN = "1046-8188",
bibdate = "Fri Aug 7 08:59:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The inverted index is the dominant indexing method in
information retrieval systems. It enables fast return
of the list of all documents containing a given query
term. However, for retrieval schemes involving query
expansion, as in pseudo-relevance feedback (PRF), the
retrieval time based on an inverted index increases
linearly with the number of expansion terms. In this
regard, we have examined the use of a forward index,
which consists of the mapping of each document to its
constituent terms. We propose a novel forward
index-based reranking scheme to shorten the PRF
retrieval time. In our method, a first retrieval of the
original query is performed using an inverted index,
and then a forward index is employed for the PRF part.
We have studied several new forward indexes, including
using a novel spstring data structure and the weighted
variable bit-block compression (wvbc) signature. With
modern hardware such as solid-state drives (SSDs) and
sufficiently large main memory, forward index methods
are particularly promising. We find that with the whole
index stored in main memory, PRF retrieval using a
spstring or wvbc forward index excels in time
efficiency over an inverted index, being able to obtain
the same levels of performance measures at shorter
times.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yang:2015:QCM,
author = "Hui Yang and Dongyi Guan and Sicong Zhang",
title = "The Query Change Model: Modeling Session Search as a
{Markov} Decision Process",
journal = j-TOIS,
volume = "33",
number = "4",
pages = "20:1--20:??",
month = may,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2747874",
ISSN = "1046-8188",
bibdate = "Fri Aug 7 08:59:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Modern information retrieval (IR) systems exhibit user
dynamics through interactivity. These dynamic aspects
of IR, including changes found in data, users, and
systems, are increasingly being utilized in search
engines. Session search is one such IR task-document
retrieval within a session. During a session, a user
constantly modifies queries to find documents that
fulfill an information need. Existing IR techniques for
assisting the user in this task are limited in their
ability to optimize over changes, learn with a minimal
computational footprint, and be responsive. This
article proposes a novel query change retrieval model
(QCM), which uses syntactic editing changes between
consecutive queries, as well as the relationship
between query changes and previously retrieved
documents, to enhance session search. We propose
modeling session search as a Markov decision process
(MDP). We consider two agents in this MDP: the user
agent and the search engine agent. The user agent's
actions are query changes that we observe, and the
search engine agent's actions are term weight
adjustments as proposed in this work. We also
investigate multiple query aggregation schemes and
their effectiveness on session search. Experiments show
that our approach is highly effective and outperforms
top session search systems in TREC 2011 and TREC
2012.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cummins:2015:PUD,
author = "Ronan Cummins and Jiaul H. Paik and Yuanhua Lv",
title = "A {P{\'o}lya} Urn Document Language Model for Improved
Information Retrieval",
journal = j-TOIS,
volume = "33",
number = "4",
pages = "21:1--21:??",
month = may,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2746231",
ISSN = "1046-8188",
bibdate = "Fri Aug 7 08:59:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The multinomial language model has been one of the
most effective models of retrieval for more than a
decade. However, the multinomial distribution does not
model one important linguistic phenomenon relating to
term dependency-that is, the tendency of a term to
repeat itself within a document (i.e., word
burstiness). In this article, we model document
generation as a random process with reinforcement (a
multivariate P{\'o}lya process) and develop a Dirichlet
compound multinomial language model that captures word
burstiness directly. We show that the new reinforced
language model can be computed as efficiently as
current retrieval models, and with experiments on an
extensive set of TREC collections, we show that it
significantly outperforms the state-of-the-art language
model for a number of standard effectiveness metrics.
Experiments also show that the tuning parameter in the
proposed model is more robust than that in the
multinomial language model. Furthermore, we develop a
constraint for the verbosity hypothesis and show that
the proposed model adheres to the constraint. Finally,
we show that the new language model essentially
introduces a measure closely related to idf, which
gives theoretical justification for combining the term
and document event spaces in tf-idf type schemes.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Mayer:2015:IOV,
author = "Julia M. Mayer and Quentin Jones and Starr Roxanne
Hiltz",
title = "Identifying Opportunities for Valuable Encounters:
Toward Context-Aware Social Matching Systems",
journal = j-TOIS,
volume = "34",
number = "1",
pages = "1:1--1:??",
month = oct,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2751557",
ISSN = "1046-8188",
bibdate = "Tue Feb 16 15:32:55 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Mobile social matching systems have the potential to
transform the way we make new social ties, but only if
we are able to overcome the many challenges that exist
as to how systems can utilize contextual data to
recommend interesting and relevant people to users and
facilitate valuable encounters between strangers. This
article outlines how context and mobility influence
people's motivations to meet new people and presents
innovative design concepts for mediating mobile
encounters through context-aware social matching
systems. Findings from two studies are presented. The
first, a survey study (n {\SGMLequals} 117) explored
the concept of contextual rarity of shared user
attributes as a measure to improve desirability in
mobile social matches. The second, an interview study
(n {\SGMLequals} 58) explored people's motivations to
meet others in various contexts. From these studies we
derived a set of novel context-aware social matching
concepts, including contextual sociability and
familiarity as an indicator of opportune social
context; contextual engagement as an indicator of
opportune personal context; and contextual rarity,
oddity, and activity partnering as an indicator of
opportune relational context. The findings of these
studies establish the importance of different
contextual factors and frame the design space of
context-aware social matching systems.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Quan:2015:LDM,
author = "Xiaojun Quan and Qifan Wang and Ying Zhang and Luo Si
and Liu Wenyin",
title = "Latent Discriminative Models for Social Emotion
Detection with Emotional Dependency",
journal = j-TOIS,
volume = "34",
number = "1",
pages = "2:1--2:??",
month = oct,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2749459",
ISSN = "1046-8188",
bibdate = "Tue Feb 16 15:32:55 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Sentiment analysis of such opinionated online texts as
reviews and comments has received increasingly close
attention, yet most of the work is intended to deal
with the detection of authors' emotion. In contrast,
this article presents our study of the social emotion
detection problem, the objective of which is to
identify the evoked emotions of readers by online
documents such as news articles. A novel Latent
Discriminative Model (LDM) is proposed for this task.
LDM works by introducing intermediate hidden variables
to model the latent structure of input text corpora. To
achieve this, it defines a joint distribution over
emotions and latent variables, conditioned on the
observed text documents. Moreover, we assume that
social emotions are not independent but correlated with
one another, and the dependency of them is capable of
providing additional guidance to LDM in the training
process. The inclusion of this emotional dependency
into LDM gives rise to a new Emotional Dependency-based
LDM (eLDM). We evaluate the proposed models through a
series of empirical evaluations on two real-world
corpora of news articles. Experimental results verify
the effectiveness of LDM and eLDM in social emotion
detection.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yan:2015:DDS,
author = "Su Yan and Xiaojun Wan",
title = "Deep Dependency Substructure-Based Learning for
Multidocument Summarization",
journal = j-TOIS,
volume = "34",
number = "1",
pages = "3:1--3:??",
month = oct,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2766447",
ISSN = "1046-8188",
bibdate = "Tue Feb 16 15:32:55 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Most extractive style topic-focused multidocument
summarization systems generate a summary by ranking
textual units in multiple documents and extracting a
proper subset of sentences biased to the given topic.
Usually, the textual units are simply represented as
sentences or n-grams, which do not carry deep syntactic
and semantic information. This article presents a novel
extractive topic-focused multidocument summarization
framework. The framework proposes a new kind of more
meaningful and informative units named frequent Deep
Dependency Sub-Structure (DDSS) and a topic-sensitive
Multi-Task Learning (MTL) model for frequent DDSS
ranking. Given a document set, first, we parse all the
sentences into deep dependency structures with a
Head-driven Phrase Structure Grammar (HPSG) parser and
mine the frequent DDSSs after semantic normalization.
Then we employ a topic-sensitive MTL model to learn the
importance of these frequent DDSSs. Finally, we exploit
an Integer Linear Programming (ILP) formulation and use
the frequent DDSSs as the essentials for summary
extraction. Experimental results on two DUC datasets
demonstrate that our proposed approach can achieve
state-of-the-art performance. Both the DDSS information
and the topic-sensitive MTL model are validated to be
very helpful for topic-focused multidocument
summarization.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cui:2015:KGF,
author = "Qing Cui and Bin Gao and Jiang Bian and Siyu Qiu and
Hanjun Dai and Tie-Yan Liu",
title = "{KNET}: a General Framework for Learning Word
Embedding Using Morphological Knowledge",
journal = j-TOIS,
volume = "34",
number = "1",
pages = "4:1--4:??",
month = oct,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2797137",
ISSN = "1046-8188",
bibdate = "Tue Feb 16 15:32:55 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Neural network techniques are widely applied to obtain
high-quality distributed representations of words
(i.e., word embeddings) to address text mining,
information retrieval, and natural language processing
tasks. Most recent efforts have proposed several
efficient methods to learn word embeddings from context
such that they can encode both semantic and syntactic
relationships between words. However, it is quite
challenging to handle unseen or rare words with
insufficient context. Inspired by the study on the word
recognition process in cognitive psychology, in this
article, we propose to take advantage of seemingly less
obvious but essentially important morphological
knowledge to address these challenges. In particular,
we introduce a novel neural network architecture called
KNET that leverages both words' contextual information
and morphological knowledge to learn word embeddings.
Meanwhile, this new learning architecture is also able
to benefit from noisy knowledge and balance between
contextual information and morphological knowledge.
Experiments on an analogical reasoning task and a word
similarity task both demonstrate that the proposed KNET
framework can greatly enhance the effectiveness of word
embeddings.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Baralis:2015:MSM,
author = "Elena Baralis and Luca Cagliero and Alessandro Fiori
and Paolo Garza",
title = "{MWI-Sum}: a Multilingual Summarizer Based on Frequent
Weighted Itemsets",
journal = j-TOIS,
volume = "34",
number = "1",
pages = "5:1--5:??",
month = oct,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2809786",
ISSN = "1046-8188",
bibdate = "Tue Feb 16 15:32:55 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Multidocument summarization addresses the selection of
a compact subset of highly informative sentences, i.e.,
the summary, from a collection of textual documents. To
perform sentence selection, two parallel strategies
have been proposed: (a) apply general-purpose
techniques relying on data mining or information
retrieval techniques, and/or (b) perform advanced
linguistic analysis relying on semantics-based models
(e.g., ontologies) to capture the actual sentence
meaning. Since there is an increasing need for
processing documents written in different languages,
the attention of the research community has recently
focused on summarizers based on strategy (a). This
article presents a novel multilingual summarizer,
namely MWI-Sum (Multilingual Weighted Itemset-based
Summarizer), that exploits an itemset-based model to
summarize collections of documents ranging over the
same topic. Unlike previous approaches, it extracts
frequent weighted itemsets tailored to the analyzed
collection and uses them to drive the sentence
selection process. Weighted itemsets represent
correlations among multiple highly relevant terms that
are neglected by previous approaches. The proposed
approach makes minimal use of language-dependent
analyses. Thus, it is easily applicable to document
collections written in different languages. Experiments
performed on benchmark and real-life collections,
English-written and not, demonstrate that the proposed
approach performs better than state-of-the-art
multilingual document summarizers.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Costa:2015:DRM,
author = "Alberto Costa and Emanuele {Di Buccio} and Massimo
Melucci",
title = "A Document Retrieval Model Based on Digital Signal
Filtering",
journal = j-TOIS,
volume = "34",
number = "1",
pages = "6:1--6:??",
month = oct,
year = "2015",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2809787",
ISSN = "1046-8188",
bibdate = "Tue Feb 16 15:32:55 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Information retrieval (IR) systems are designed, in
general, to satisfy the information need of a user who
expresses it by means of a query, by providing him with
a subset of documents selected from a collection and
ordered by decreasing relevance to the query. Such
systems are based on IR models, which define how to
represent the documents and the query, as well as how
to determine the relevance of a document for a query.
In this article, we present a new IR model based on
concepts taken from both IR and digital signal
processing (like Fourier analysis of signals and
filtering). This allows the whole IR process to be seen
as a physical phenomenon, where the query corresponds
to a signal, the documents correspond to filters, and
the determination of the relevant documents to the
query is done by filtering that signal. Tests showed
that the quality of the results provided by this IR
model is comparable with the state-of-the-art.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tang:2016:TLI,
author = "Jie Tang and Tiancheng Lou and Jon Kleinberg and Sen
Wu",
title = "Transfer Learning to Infer Social Ties across
Heterogeneous Networks",
journal = j-TOIS,
volume = "34",
number = "2",
pages = "7:1--7:??",
month = apr,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2746230",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:33 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Interpersonal ties are responsible for the structure
of social networks and the transmission of information
through these networks. Different types of social ties
have essentially different influences on people.
Awareness of the types of social ties can benefit many
applications, such as recommendation and community
detection. For example, our close friends tend to move
in the same circles that we do, while our classmates
may be distributed into different communities. Though a
bulk of research has focused on inferring particular
types of relationships in a specific social network,
few publications systematically study the
generalization of the problem of predicting social ties
across multiple heterogeneous networks. In this work,
we develop a framework referred to as TranFG for
classifying the type of social relationships by
learning across heterogeneous networks. The framework
incorporates social theories into a factor graph model,
which effectively improves the accuracy of predicting
the types of social relationships in a target network
by borrowing knowledge from a different source network.
We also present several active learning strategies to
further enhance the inferring performance. To scale up
the model to handle really large networks, we design a
distributed learning algorithm for the proposed model.
We evaluate the proposed framework (TranFG) on six
different networks and compare with several existing
methods. TranFG clearly outperforms the existing
methods on multiple metrics. For example, by leveraging
information from a coauthor network with labeled
advisor-advisee relationships, TranFG is able to obtain
an F1-score of 90\% (8\%--28\% improvements over
alternative methods) for predicting manager-subordinate
relationships in an enterprise email network. The
proposed model is efficient. It takes only a few
minutes to train the proposed transfer model on large
networks containing tens of thousands of nodes.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Petersen:2016:PLD,
author = "Casper Petersen and Jakob Grue Simonsen and Christina
Lioma",
title = "Power Law Distributions in Information Retrieval",
journal = j-TOIS,
volume = "34",
number = "2",
pages = "8:1--8:??",
month = apr,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2816815",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:33 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Several properties of information retrieval (IR) data,
such as query frequency or document length, are widely
considered to be approximately distributed as a power
law. This common assumption aims to focus on specific
characteristics of the empirical probability
distribution of such data (e.g., its scale-free nature
or its long/fat tail). This assumption, however, may
not be always true. Motivated by recent work in the
statistical treatment of power law claims, we
investigate two research questions: (i) To what extent
do power law approximations hold for term frequency,
document length, query frequency, query length,
citation frequency, and syntactic unigram frequency?
And (ii) what is the computational cost of replacing ad
hoc power law approximations with more accurate
distribution fitting? We study 23 TREC and 5 non-TREC
datasets and compare the fit of power laws to 15 other
standard probability distributions. We find that query
frequency and 5 out of 24 term frequency distributions
are best approximated by a power law. All remaining
properties are better approximated by the Inverse
Gaussian, Generalized Extreme Value, Negative Binomial,
or Yule distribution. We also find the overhead of
replacing power law approximations by more informed
distribution fitting to be negligible, with potential
gains to IR tasks like index compression or test
collection generation for IR evaluation.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Gomez-Rodriguez:2016:IEM,
author = "Manuel Gomez-Rodriguez and Le Song and Nan Du and
Hongyuan Zha and Bernhard Sch{\"o}lkopf",
title = "Influence Estimation and Maximization in
Continuous-Time Diffusion Networks",
journal = j-TOIS,
volume = "34",
number = "2",
pages = "9:1--9:??",
month = apr,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2824253",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:33 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "If a piece of information is released from a set of
media sites, can it spread, in 1 month, to a million
web pages? Can we efficiently find a small set of media
sites among millions that can maximize the spread of
the information, in 1 month? The two problems are
called influence estimation and maximization problems
respectively, which are very challenging since both the
time-sensitive nature of the problems and the issue of
scalability need to be addressed simultaneously. In
this article, we propose two algorithms for influence
estimation in continuous-time diffusion networks. The
first one uses continuous-time Markov chains to
estimate influence exactly on networks with
exponential, or, more generally, phase-type
transmission functions, but does not scale to
large-scale networks, and the second one is a highly
efficient randomized algorithm, which estimates the
influence of every node in a network with general
transmission functions, $| \nu |$ nodes and $| \epsilon
|$ edges to an accuracy of $\epsilon$ using $n = O(1 /
\epsilon^2)$ randomizations and up to logarithmic
factors $O( n | \epsilon |+ n | \nu |)$
computations. We then show that finding the set of most
influential source nodes in a continuous time diffusion
network is an NP-hard problem and develop an efficient
greedy algorithm with provable near-optimal
performance. When used as subroutines in the influence
maximization algorithm, the exact influence estimation
algorithm is guaranteed to find a set of $C$ nodes with
an influence of at least $(1 - 1 / e ) {\rm OPT}$ and
the randomized algorithm is guaranteed to find a set
with an influence of at least $(1 - 1 / e ){\rm OPT} -
2 C \epsilon$, where ${\rm OPT}$ is the optimal
value. Experiments on both synthetic and real-world
data show that the proposed algorithms significantly
improve over previous state-of-the-art methods in terms
of the accuracy of the estimated influence and the
quality of the selected nodes to maximize the
influence, and the randomized algorithm can easily
scale up to networks of millions of nodes.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Song:2016:VTP,
author = "Xuemeng Song and Zhao-Yan Ming and Liqiang Nie and
Yi-Liang Zhao and Tat-Seng Chua",
title = "Volunteerism Tendency Prediction via Harvesting
Multiple Social Networks",
journal = j-TOIS,
volume = "34",
number = "2",
pages = "10:1--10:??",
month = apr,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2832907",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:33 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Volunteers have always been extremely crucial and in
urgent need for nonprofit organizations (NPOs) to
sustain their continuing operations. However, it is
expensive and time-consuming to recruit volunteers
using traditional approaches. In the Web 2.0 era,
abundant and ubiquitous social media data opens a door
to the possibility of automatic volunteer
identification. In this article, we aim to fully
explore this possibility by proposing a scheme that is
able to predict users' volunteerism tendency from
user-generated contents collected from multiple social
networks based on a conceptual volunteering decision
model. We conducted comprehensive experiments to
investigate the effectiveness of our proposed scheme
and further discussed its generalizibility and
extendability. This novel interdisciplinary research
will potentially inspire more promising and important
human-centered applications.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Li:2016:TBI,
author = "Qing Li and Yuanzhu Chen and Li Ling Jiang and Ping Li
and Hsinchun Chen",
title = "A Tensor-Based Information Framework for Predicting
the Stock Market",
journal = j-TOIS,
volume = "34",
number = "2",
pages = "11:1--11:??",
month = apr,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2838731",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:33 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "To study the influence of information on the behavior
of stock markets, a common strategy in previous studies
has been to concatenate the features of various
information sources into one compound feature vector, a
procedure that makes it more difficult to distinguish
the effects of different information sources. We
maintain that capturing the intrinsic relations among
multiple information sources is important for
predicting stock trends. The challenge lies in modeling
the complex space of various sources and types of
information and studying the effects of this
information on stock market behavior. For this purpose,
we introduce a tensor-based information framework to
predict stock movements. Specifically, our framework
models the complex investor information environment
with tensors. A global dimensionality-reduction
algorithm is used to capture the links among various
information sources in a tensor, and a sequence of
tensors is used to represent information gathered over
time. Finally, a tensor-based predictive model to
forecast stock movements, which is in essence a
high-order tensor regression learning problem, is
presented. Experiments performed on an entire year of
data for China Securities Index stocks demonstrate that
a trading system based on our framework outperforms the
classic Top- N trading strategy and two
state-of-the-art media-aware trading algorithms.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Piao:2016:SFA,
author = "Minghao Piao and Keun Ho Ryu",
title = "Subspace Frequency Analysis-Based Field Indices
Extraction for Electricity Customer Classification",
journal = j-TOIS,
volume = "34",
number = "2",
pages = "12:1--12:??",
month = apr,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2858657",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:33 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In electricity customer classification, the most
important task is to avoid the curse of dimensionality
problem, as the consumption diagrams have a large
number of dimensions. To avoid the curse of
dimensionality problem, field indices (load shape
factor) are often used instead of consumption diagrams.
Field indices are directly extracted from consumption
diagrams according to a predefined formula. Previous
studies show that the most important thing for defining
such a formula is to find meaningful time intervals
from consumption diagrams. However, the inconvenient
thing is that there are still a lack of details to
explain how to define such time intervals. In our
study, we propose a data mining--based method named
SFATIE to support the extraction of field indices. The
performance of the proposed method is evaluated by
comparing it with other dimensionality reduction
methods during the classification. For the
classification, most often we have used classification
methods like C5.0, SVM, Neural Net, Bayes Net, and
Logistic. The experimental results show that our method
is better or close to other dimensionality reduction
methods. In addition, the experimental results show
that our proposed method can produce the good quality
of field indices and that these indices can improve the
performance of electricity customer classification.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cheng:2016:ELA,
author = "Zhiyong Cheng and Jialie Shen",
title = "On Effective Location-Aware Music Recommendation",
journal = j-TOIS,
volume = "34",
number = "2",
pages = "13:1--13:??",
month = apr,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2846092",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:33 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Rapid advances in mobile devices and cloud-based music
service now allow consumers to enjoy music anytime and
anywhere. Consequently, there has been an increasing
demand in studying intelligent techniques to facilitate
context-aware music recommendation. However, one
important context that is generally overlooked is
user's venue, which often includes surrounding
atmosphere, correlates with activities, and greatly
influences the user's music preferences. In this
article, we present a novel venue-aware music
recommender system called VenueMusic to effectively
identify suitable songs for various types of popular
venues in our daily lives. Toward this goal, a
Location-aware Topic Model (LTM) is proposed to (i)
mine the common features of songs that are suitable for
a venue type in a latent semantic space and (ii)
represent songs and venue types in the shared latent
space, in which songs and venue types can be directly
matched. It is worth mentioning that to discover
meaningful latent topics with the LTM, a Music Concept
Sequence Generation (MCSG) scheme is designed to
extract effective semantic representations for songs.
An extensive experimental study based on two large
music test collections demonstrates the effectiveness
of the proposed topic model and MCSG scheme. The
comparisons with state-of-the-art music recommender
systems demonstrate the superior performance of
VenueMusic system on recommendation accuracy by
associating venue and music contents using a latent
semantic space. This work is a pioneering study on the
development of a venue-aware music recommender system.
The results show the importance of considering the
influence of venue types in the development of
context-aware music recommender systems.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Papadopoulos:2016:OSI,
author = "Symeon Papadopoulos and Kalina Bontcheva and Eva Jaho
and Mihai Lupu and Carlos Castillo",
title = "Overview of the Special Issue on Trust and Veracity of
Information in Social Media",
journal = j-TOIS,
volume = "34",
number = "3",
pages = "14:1--14:??",
month = may,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2870630",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:34 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Webb:2016:DWP,
author = "Helena Webb and Pete Burnap and Rob Procter and Omer
Rana and Bernd Carsten Stahl and Matthew Williams and
William Housley and Adam Edwards and Marina Jirotka",
title = "Digital Wildfires: Propagation, Verification,
Regulation, and Responsible Innovation",
journal = j-TOIS,
volume = "34",
number = "3",
pages = "15:1--15:??",
month = may,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2893478",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:34 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Social media platforms provide an increasingly popular
means for individuals to share content online. Whilst
this produces undoubted societal benefits, the ability
for content to be spontaneously posted and reposted
creates an ideal environment for rumour and
false/malicious information to spread rapidly. When
this occurs it can cause significant harm and can be
characterised as a ``digital wildfire.'' In this
article, we demonstrate that the propagation and
regulation of digital wildfires form important topics
for research and conduct an overview of existing work
in this area. We outline the relevance of a range of
work from the computational and social sciences,
including a series of insights into the propagation of
rumour and false/malicious information. We argue that
significant research gaps remain-for instance, there is
an absence of systematic studies on the effects of
digital wildfires and there is a need to combine
empirical research with a consideration of how the
responsible governance of social media can be
determined. We propose an agenda for research that
establishes a methodology to explore in full the
propagation and regulation of unverified content on
social media. This agenda promotes high-quality
interdisciplinary research that will also inform policy
debates.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Middleton:2016:GGS,
author = "Stuart E. Middleton and Vadims Krivcovs",
title = "Geoparsing and Geosemantics for Social Media:
Spatiotemporal Grounding of Content Propagating Rumors
to Support Trust and Veracity Analysis during Breaking
News",
journal = j-TOIS,
volume = "34",
number = "3",
pages = "16:1--16:??",
month = may,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2842604",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:34 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In recent years, there has been a growing trend to use
publicly available social media sources within the
field of journalism. Breaking news has tight reporting
deadlines, measured in minutes not days, but content
must still be checked and rumors verified. As such,
journalists are looking at automated content analysis
to prefilter large volumes of social media content
prior to manual verification. This article describes a
real-time social media analytics framework for
journalists. We extend our previously published
geoparsing approach to improve its scalability and
efficiency. We develop and evaluate a novel approach to
geosemantic feature extraction, classifying evidence in
terms of situatedness, timeliness, confirmation, and
validity. Our approach works for new unseen news
topics. We report results from four experiments using
five Twitter datasets crawled during different
English-language news events. One of our datasets is
the standard TREC 2012 microblog corpus. Our
classification results are promising, with F1 scores
varying by class from 0.64 to 0.92 for unseen event
types. We lastly report results from two case studies
during real-world news stories, showcasing different
ways our system can assist journalists filter and
cross-check content as they examine the trust and
veracity of content and sources.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hamdi:2016:TTI,
author = "Sana Hamdi and Alda Lopes Gancarski and Amel
Bouzeghoub and Sadok Ben Yahia",
title = "{TISoN}: Trust Inference in Trust-Oriented Social
Networks",
journal = j-TOIS,
volume = "34",
number = "3",
pages = "17:1--17:??",
month = may,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2858791",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:34 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Trust systems represent a significant trend in
decision support for social networks' service
provision. The basic idea is to allow users to rate
each other even without being direct neighbours. In
this case, the purpose is to derive a trust score for a
given user, which could be of help to decide whether to
trust other users or not. In this article, we
investigate the properties of trust propagation within
social networks, based on the notion of transitivity,
and we introduce the TISoN model to generate and
evaluate Trust Inference within online Social
Networks. To do so, ( i ) we develop a novel TPS
algorithm for Trust Path Searching where we define
neighbours' priority based on their direct trust
degrees, and then select trusted paths while
controlling the path length; and, ( ii ) we develop
different TIM algorithms for Trust Inference Measuring
and build a trust network. In addition, we analyse
existing algorithms and we demonstrate that our
proposed model better computes transitive trust values
than do the existing models. We conduct extensive
experiments on a real online social network dataset,
Advogato. Experimental results show that our work is
scalable and generates better results than do the
pioneering approaches of the literature.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2016:MOS,
author = "Huiling Zhang and Md Abdul Alim and Xiang Li and My T.
Thai and Hien T. Nguyen",
title = "Misinformation in Online Social Networks: Detect Them
All with a Limited Budget",
journal = j-TOIS,
volume = "34",
number = "3",
pages = "18:1--18:??",
month = may,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2885494",
ISSN = "1046-8188",
bibdate = "Mon Jun 20 18:55:34 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Online social networks have become an effective and
important social platform for communication, opinions
exchange, and information sharing. However, they also
make it possible for rapid and wide misinformation
diffusion, which may lead to pernicious influences on
individuals or society. Hence, it is extremely
important and necessary to detect the misinformation
propagation by placing monitors. In this article, we
first define a general misinformation-detection problem
for the case where the knowledge about misinformation
sources is lacking, and show its equivalence to the
influence-maximization problem in the reverse
graph. Furthermore, considering node vulnerability, we
aim to detect the misinformation reaching to a specific
user. Therefore, we study a $\tau$-Monitor Placement
problem for cases where partial knowledge of
misinformation sources is available and prove its \#P
complexity. We formulate a corresponding integer
program, tackle exponential constraints, and propose a
Minimum Monitor Set Construction (MMSC) algorithm, in
which the cut-set$^2$ has been exploited in the
estimation of reachability of node pairs. Moreover, we
generalize the problem from a single target to multiple
central nodes and propose another algorithm based on a
Monte Carlo sampling technique. Extensive experiments
on real-world networks show the effectiveness of
proposed algorithms with respect to minimizing the
number of monitors.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Shtok:2016:QPP,
author = "Anna Shtok and Oren Kurland and David Carmel",
title = "Query Performance Prediction Using Reference Lists",
journal = j-TOIS,
volume = "34",
number = "4",
pages = "19:1--19:??",
month = sep,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2926790",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:18 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The task of query performance prediction is to
estimate the effectiveness of search performed in
response to a query when no relevance judgments are
available. We present a novel probabilistic analysis of
the performance prediction task. The analysis gives
rise to a general prediction framework that uses
pseudo-effective or ineffective document lists that are
retrieved in response to the query. These lists serve
as reference to the result list at hand, the
effectiveness of which we want to predict. We show that
many previously proposed prediction methods can be
explained using our framework. More generally, we shed
new light on existing prediction methods and establish
formal common grounds to seemingly different prediction
approaches. In addition, we formally demonstrate the
connection between prediction using reference lists and
fusion of retrieved lists, and provide empirical
support to this connection. Through an extensive
empirical exploration, we study various factors that
affect the quality of prediction using reference
lists.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ibrahim:2016:CPL,
author = "Muhammad Ibrahim and Mark Carman",
title = "Comparing Pointwise and Listwise Objective Functions
for Random-Forest-Based Learning-to-Rank",
journal = j-TOIS,
volume = "34",
number = "4",
pages = "20:1--20:??",
month = sep,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2866571",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:18 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Current random-forest (RF)-based learning-to-rank
(LtR) algorithms use a classification or regression
framework to solve the ranking problem in a pointwise
manner. The success of this simple yet effective
approach coupled with the inherent parallelizability of
the learning algorithm makes it a strong candidate for
widespread adoption. In this article, we aim to better
understand the effectiveness of RF-based rank-learning
algorithms with a focus on the comparison between
pointwise and listwise approaches. We introduce what we
believe to be the first listwise version of an RF-based
LtR algorithm. The algorithm directly optimizes an
information retrieval metric of choice (in our case,
NDCG) in a greedy manner. Direct optimization of the
listwise objective functions is computationally
prohibitive for most learning algorithms, but possible
in RF since each tree maximizes the objective in a
coordinate-wise fashion. Computational complexity of
the listwise approach is higher than the pointwise
counterpart; hence for larger datasets, we design a
hybrid algorithm that combines a listwise objective in
the early stages of tree construction and a pointwise
objective in the latter stages. We also study the
effect of the discount function of NDCG on the listwise
algorithm. Experimental results on several publicly
available LtR datasets reveal that the listwise/hybrid
algorithm outperforms the pointwise approach on the
majority (but not all) of the datasets. We then
investigate several aspects of the two algorithms to
better understand the inevitable performance tradeoffs.
The aspects include examining an RF-based unsupervised
LtR algorithm and comparing individual tree strength.
Finally, we compare the the investigated RF-based
algorithms with several other LtR algorithms.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Do:2016:PMC,
author = "Loc Do and Hady W. Lauw",
title = "Probabilistic Models for Contextual Agreement in
Preferences",
journal = j-TOIS,
volume = "34",
number = "4",
pages = "21:1--21:??",
month = sep,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2854147",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:18 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The long-tail theory for consumer demand implies the
need for more accurate personalization technologies to
target items to the users who most desire them. A key
tenet of personalization is the capacity to model user
preferences. Most of the previous work on
recommendation and personalization has focused
primarily on individual preferences. While some focus
on shared preferences between pairs of users, they
assume that the same similarity value applies to all
items. Here we investigate the notion of ``context,''
hypothesizing that while two users may agree on their
preferences on some items, they may also disagree on
other items. To model this, we design probabilistic
models for the generation of rating differences between
pairs of users across different items. Since this model
also involves the estimation of rating differences on
unseen items for the purpose of prediction, we further
conduct a systematic analysis of matrix factorization
and tensor factorization methods in this estimation,
and propose a factorization model with a novel
objective function of minimizing error in rating
differences. Experiments on several real-life rating
datasets show that our proposed model consistently
yields context-specific similarity values that perform
better on a prediction task than models relying on
shared preferences.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Miao:2016:TPF,
author = "Jun Miao and Jimmy Xiangji Huang and Jiashu Zhao",
title = "{TopPRF}: a Probabilistic Framework for Integrating
Topic Space into Pseudo Relevance Feedback",
journal = j-TOIS,
volume = "34",
number = "4",
pages = "22:1--22:??",
month = sep,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2956234",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:18 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Traditional pseudo relevance feedback (PRF) models
choose top k feedback documents for query expansion and
treat those documents equally. When k is determined,
feedback terms are selected without considering the
reliability of these documents for relevance. Because
the performance of PRF is sensitive to the selection of
feedback terms, noisy terms imported from these
irrelevant documents or partially relevant documents
will harm the final results extensively. Intuitively,
terms in these documents should be considered less
important for feedback term selection. Nonetheless, how
to measure the reliability of feedback documents is a
difficult problem. Recently, topic modeling has become
more and more popular in the information retrieval (IR)
area. In order to identify how reliable a feedback
document is to be relevant, we attempt to adapt the
topical information into PRF. However, topics are hard
to be quantified and therefore the identification of
topic is usually fuzzy. It is very challenging for
integrating the obtained topical information
effectively into IR and other text-processing-related
areas. Current research work mainly focuses on mining
relevant information from particular topics. This is
extremely difficult when the boundaries of different
topics are hard to define. In this article, we
investigate a key factor of this problem, the topic
number for topic modeling and how it makes topics
``fuzzy.'' To effectively and efficiently apply topical
information, we propose a new probabilistic framework,
``TopPRF,'' and three models, TS-COS, TS-EU, and
TS-Entropy, via integrating ``Topic Space'' (TS)
information into pseudo relevance feedback. These
methods discover how reliable a document is to be
relevant through both term and topical information.
When selecting feedback terms, candidate terms in more
reliable feedback documents should obtain extra
weights. Experimental results on various public
collections justify that our proposed methods can
significantly reduce the influence of ``fuzzy topics''
and obtain stable, good results over the strong
baseline models. Our proposed probabilistic framework,
TopPRF, and three topic-space-based models are capable
of searching documents beyond traditional term matching
only and provide a promising avenue for constructing
better topic-space-based IR systems. Moreover, in-depth
discussions and conclusions are made to help other
researchers apply topical information effectively.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Kharazmi:2016:EAW,
author = "Sadegh Kharazmi and Falk Scholer and David Vallet and
Mark Sanderson",
title = "Examining Additivity and Weak Baselines",
journal = j-TOIS,
volume = "34",
number = "4",
pages = "23:1--23:??",
month = sep,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2882782",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:18 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We present a study of which baseline to use when
testing a new retrieval technique. In contrast to past
work, we show that measuring a statistically
significant improvement over a weak baseline is not a
good predictor of whether a similar improvement will be
measured on a strong baseline. Sometimes strong
baselines are made worse when a new technique is
applied. We investigate whether conducting comparisons
against a range of weaker baselines can increase
confidence that an observed effect will also show
improvements on a stronger baseline. Our results
indicate that this is not the case --- at best, testing
against a range of baselines means that an experimenter
can be more confident that the new technique is
unlikely to significantly harm a strong baseline.
Examining recent past work, we present evidence that
the information retrieval (IR) community continues to
test against weak baselines. This is unfortunate as, in
light of our experiments, we conclude that the only way
to be confident that a new technique is a contribution
is to compare it against nothing less than the state of
the art.",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Luo:2016:MSU,
author = "Xiangfeng Luo and Junyu Xuan and Jie Lu and Guangquan
Zhang",
title = "Measuring the Semantic Uncertainty of News Events for
Evolution Potential Estimation",
journal = j-TOIS,
volume = "34",
number = "4",
pages = "24:1--24:??",
month = sep,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2903719",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:18 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The evolution potential estimation of news events can
support the decision making of both corporations and
governments. For example, a corporation could manage
its public relations crisis in a timely manner if a
negative news event about this corporation is known
with large evolution potential in advance. However,
existing state-of-the-art methods are mainly based on
time series historical data, which are not suitable for
the news events with limited historical data and bursty
properties. In this article, we propose a purely
content-based method to estimate the evolution
potential of the news events. The proposed method
considers a news event at a given time point as a
system composed of different keywords, and the
uncertainty of this system is defined and measured as
the Semantic Uncertainty of this news event. At the
same time, an uncertainty space is constructed with two
extreme states: the most uncertain state and the most
certain state. We believe that the Semantic Uncertainty
has correlation with the content evolution of the news
events, so it can be used to estimate the evolution
potential of the news events. In order to verify the
proposed method, we present detailed experimental
setups and results measuring the correlation of the
Semantic Uncertainty with the Content Change of news
events using collected news events data. The results
show that the correlation does exist and is stronger
than the correlation of value from the
time-series-based method with the Content Change.
Therefore, we can use the Semantic Uncertainty to
estimate the evolution potential of news events.",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cai:2016:DQA,
author = "Fei Cai and Ridho Reinanda and Maarten {De Rijke}",
title = "Diversifying Query Auto-Completion",
journal = j-TOIS,
volume = "34",
number = "4",
pages = "25:1--25:??",
month = sep,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2910579",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:18 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Query auto-completion assists web search users in
formulating queries with a few keystrokes, helping them
to avoid spelling mistakes and to produce clear query
expressions, and so on. Previous work on query
auto-completion mainly centers around returning a list
of completions to users, aiming to push queries that
are most likely intended by the user to the top
positions but ignoring the redundancy among the query
candidates in the list. Thus, semantically related
queries matching the input prefix are often returned
together. This may push valuable suggestions out of the
list, given that only a limited number of candidates
can be shown to the user, which may result in a less
than optimal search experience. In this article, we
consider the task of diversifying query
auto-completion, which aims to return the correct query
completions early in a ranked list of candidate
completions and at the same time reduce the redundancy
among query auto-completion candidates. We develop a
greedy query selection approach that predicts query
completions based on the current search popularity of
candidate completions and on the aspects of previous
queries in the same search session. The popularity of
completion candidates at query time can be directly
aggregated from query logs. However, query aspects are
implicitly expressed by previous clicked documents in
the search context. To determine the query aspect, we
categorize clicked documents of a query using a
hierarchy based on the open directory project. Bayesian
probabilistic matrix factorization is applied to derive
the distribution of queries over all aspects. We
quantify the improvement of our greedy query selection
model against a state-of-the-art baseline using two
large-scale, real-world query logs and show that it
beats the baseline in terms of well-known metrics used
in query auto-completion and diversification. In
addition, we conduct a side-by-side experiment to
verify the effectiveness of our proposal.",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Morsy:2016:ALC,
author = "Sara Morsy and George Karypis",
title = "Accounting for Language Changes Over Time in Document
Similarity Search",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "1:1--1:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2934671",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Given a query document, ranking the documents in a
collection based on how similar they are to the query
is an essential task with extensive applications. For
collections that contain documents whose creation dates
span several decades, this task is further complicated
by the fact that the language changes over time. For
example, many terms add or lose one or more senses to
meet people's evolving needs. To address this problem,
we present methods that take advantage of two types of
information to account for the language change. The
first is the citation network that often exists within
the collection, which can be used to link related
documents with significantly different creation dates
(and hence different language use). The second is the
changes in the usage frequency of terms that occur over
time, which can indicate changes in their senses and
uses. These methods utilize the preceding information
while estimating the representation of both documents
and terms within the context of nonprobabilistic static
and dynamic topic models. Our experiments on two
real-world datasets that span more than 40 years show
that our proposed methods improve the retrieval
performance of existing models and that these
improvements are statistically significant.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Arguello:2016:EAS,
author = "Jaime Arguello and Rob Capra",
title = "The Effects of Aggregated Search Coherence on Search
Behavior",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "2:1--2:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2935747",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Aggregated search is the task of combining results
from multiple independent search systems in a single
Search Engine Results Page (SERP). Aggregated search
coherence refers to the extent to which different
sources on the SERP focus on similar senses of an
ambiguous or underspecified query. In previous studies,
we found that the query senses in a set of vertical
results can influence user engagement with the web
results (the so-called ``spillover'' effect). In this
work, we investigate five research questions (RQ1--RQ5)
that extend our prior work. First, we investigate the
extent to which results from different sources focus on
different senses of an ambiguous query (RQ1). Second,
we investigate how the vertical-to-web spillover effect
varies across different verticals (RQ2). Then, we
examine whether the level of spillover depends on the
vertical position (RQ3) and on whether the vertical
results are displayed with a border and
different-colored background to distinguish them from
the web results (RQ4). Finally, we propose a new method
for displaying results from a particular vertical that
are more consistent with the query senses in the web
results (RQ5). We evaluate this new method based on how
it influences users to make more correct decisions with
respect to the web results-to engage with the web
results when at least one of them is relevant and to
avoid engaging with the web results otherwise. Our
results show the following trends. In terms of RQ1, our
analysis suggests that the top results from the web
search engine are more diversified than the top results
from our four different verticals considered (images,
news, shopping, and video). In terms of RQ2, we found a
stronger spillover effect for the images vertical than
the news, shopping, and video verticals. In terms of
RQ3, we found a stronger level of spillover when the
vertical was positioned at the top of the SERP versus
to the right side of the web results. In terms of RQ4,
we found an interesting additive effect between the
vertical's position and displaying the vertical results
enclosed in a border and with a different-colored
background-the image vertical had no spillover when
presented to the right side of the web results and with
a border and background. Finally, in terms of RQ5, we
found that our proposed vertical results selection
approach can influence users to make more correct
predictions about their level of engagement with the
web results.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2016:CRD,
author = "Yating Zhang and Adam Jatowt and Katsumi Tanaka",
title = "Causal Relationship Detection in Archival Collections
of Product Reviews for Understanding Technology
Evolution",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "3:1--3:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2937752",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Technology progress is one of the key reasons behind
today's rapid changes in lifestyles. Knowing how
products and objects evolve can not only help with
understanding the evolutionary patterns in our society
but can also provide clues on effective product design
and can offer support for predicting the future. We
propose a general framework for analyzing technology's
impact on our lives through detecting cause--effect
relationships, where causes represent changes in
technology while effects are changes in social life,
such as new activities or new ways of using products.
We address the challenge of viewing technology
evolution through the ``social impact lens'' by mining
causal relationships from the long-term collections of
product reviews. In particular, we first propose
dividing vocabulary into two groups: terms describing
product features (called physical terms ) and terms
representing product usage (called conceptual terms ).
We then search for two kinds of changes related to the
appearance of terms: frequency-based and context-based
changes. The former indicate periods when a word was
significantly more frequently used, whereas the latter
indicate periods of high change in the word's context.
Based on the detected changes, we then search for
causal term pairs such that the change in the physical
term triggers the change in the conceptual term. We
next extend our approach to finding causal
relationships between word groups such as a group of
words representing the same technology and causing a
given conceptual change or group of words representing
two different technologies that simultaneously
``co-cause'' a conceptual change. We conduct
experiments on different product types using the Amazon
Product Review Dataset, which spans 1995 to 2013, and
we demonstrate that our approaches outperform
state-of-the-art baselines.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Molino:2016:SQA,
author = "Piero Molino and Luca Maria Aiello and Pasquale Lops",
title = "Social Question Answering: Textual, User, and Network
Features for Best Answer Prediction",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "4:1--4:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2948063",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Community question answering (CQA) sites use a
collaborative paradigm to satisfy complex information
needs. Although the task of matching questions to their
best answers has been tackled for more than a decade,
the social question-answering practice is a complex
process. The factors influencing the accuracy of
question-answer matching are many and hard to
disentangle. We approach the task from an
application-oriented perspective, probing the space of
several dimensions relevant to this problem: features,
algorithms, and topics. We gather under a learning to
rank framework the most extensive feature set used in
literature to date, including 225 features from five
different families. We test the power of such features
in predicting the best answer to a question on the
largest dataset from Yahoo Answers used for this task
so far (40M answers) and provide a faceted analysis of
the results along different topical areas and question
types. We propose a novel family of distributional
semantics measures that most of the time can seamlessly
replace widely used linguistic similarity features,
being more than one order of magnitude faster to
compute and providing greater predictive power. The
best feature set reaches an improvement between 11\%
and 26\% in P@1 compared to recent well-established
state-of-the-art methods.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2016:TRM,
author = "Chenyi Zhang and Hongwei Liang and Ke Wang",
title = "Trip Recommendation Meets Real-World Constraints:
{POI} Availability, Diversity, and Traveling Time
Uncertainty",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "5:1--5:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2948065",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "As location-based social network (LBSN) services
become increasingly popular, trip recommendation that
recommends a sequence of points of interest (POIs) to
visit for a user emerges as one of many important
applications of LBSNs. Personalized trip recommendation
tailors to users' specific tastes by learning from past
check-in behaviors of users and their peers. Finding
the optimal trip that maximizes user's experiences for
a given time budget constraint is an NP-hard problem
and previous solutions do not consider three practical
and important constraints. One constraint is POI
availability, where a POI may be only available during
a certain time window. Another constraint is uncertain
traveling time, where the traveling time between two
POIs is uncertain. In addition, the diversity of the
POIs included in the trip plays an important role in
user's final adoptions. This work presents efficient
solutions to personalized trip recommendation by
incorporating these constraints and leveraging them to
prune the search space. We evaluated the efficiency and
effectiveness of our solutions on real-life LBSN
datasets.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Azmi:2016:AAW,
author = "Aqil M. Azmi and Nouf A. Alshenaifi",
title = "Answering {Arabic} Why-Questions: Baseline vs.
{RST}-Based Approach",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "6:1--6:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2950049",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "A Question Answering (QA) system is concerned with
building a system that automatically answer questions
posed by humans in a natural language. Compared to
other languages, little effort was directed towards QA
systems for Arabic. Due to the difficulty of handling
why -questions, most Arabic QA systems tend to ignore
it. In this article, we specifically address the why
-question for Arabic using two different approaches and
compare their performance and the quality of their
answer. The first is the baseline approach, a generic
method that is used to answer all types of questions,
including factoid; and for the second approach, we use
Rhetorical Structure Theory (RST). We evaluate both
schemes using a corpus of 700 textual documents in
different genres collected from Open Source Arabic
Corpora (OSAC), and a set of 100 question-answer pairs.
Overall, the performance measures of recall, precision,
and c@1 was 68\% (all three measures) for the baseline
approach, and 71\%, 78\%, and 77.4\%, respectively, for
the RST-based approach. The recently introduced
extension of the accuracy, the c@1 measure, rewards
unanswered questions over those wrongly answered.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Baly:2016:MFM,
author = "Ramy Baly and Roula Hobeica and Hazem Hajj and Wassim
El-Hajj and Khaled Bashir Shaban and Ahmad Al-Sallab",
title = "A Meta-Framework for Modeling the Human Reading
Process in Sentiment Analysis",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "7:1--7:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2950050",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article introduces a sentiment analysis approach
that adopts the way humans read, interpret, and extract
sentiment from text. Our motivation builds on the
assumption that human interpretation should lead to the
most accurate assessment of sentiment in text. We call
this automated process Human Reading for Sentiment
(HRS). Previous research in sentiment analysis has
produced many frameworks that can fit one or more of
the HRS aspects; however, none of these methods has
addressed them all in one approach. HRS provides a
meta-framework for developing new sentiment analysis
methods or improving existing ones. The proposed
framework provides a theoretical lens for zooming in
and evaluating aspects of any sentiment analysis method
to identify gaps for improvements towards matching the
human reading process. Key steps in HRS include the
automation of humans low-level and high-level cognitive
text processing. This methodology paves the way towards
the integration of psychology with computational
linguistics and machine learning to employ models of
pragmatics and discourse analysis for sentiment
analysis. HRS is tested with two state-of-the-art
methods; one is based on feature engineering, and the
other is based on deep learning. HRS highlighted the
gaps in both methods and showed improvements for
both.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhao:2016:PLB,
author = "Wayne Xin Zhao and Ningnan Zhou and Wenhui Zhang and
Ji-Rong Wen and Shan Wang and Edward Y. Chang",
title = "A Probabilistic Lifestyle-Based Trajectory Model for
Social Strength Inference from Human Trajectory Data",
journal = j-TOIS,
volume = "35",
number = "1",
pages = "8:1--8:??",
month = oct,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2948064",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the pervasiveness of location-based social
networks, it becomes increasingly important to consider
the social characteristics of locations shared among
persons. Several studies have been proposed to infer
social strength by using trajectory similarity.
However, these studies have two major shortcomings.
First, they rely on the explicit co-occurrence of
check-in locations. In this situation, a user pair of
two friends who seldom share common locations or a user
pair of two strangers who heavily share common visited
locations will receive an unreliable estimation of the
real social strength between them. Second, these
studies do not consider how the overall trajectory
patterns of users change with the varying of living
styles. In this article, we propose a probabilistic
generative model to mine latent lifestyle-related
patterns from human trajectory data for inferring
social strength. It can automatically learn
functionality topics consisting of locations with
similar service functions and transition probabilities
over the set of functionality topics. Furthermore, a
lifestyle is modeled as a unique transition probability
matrix over the set of functionality topics. A user has
a preference distribution over the set of lifestyles,
and he or she is able to select over multiple
lifestyles to adapt to different living contexts. The
learned lifestyle-related patterns are subsequently
used as features in a supervised learner for both
strength estimation and link prediction. We conduct
extensive experiments to evaluate the performance of
the proposed method on two real-world datasets. The
experimental results demonstrate the effectiveness of
our proposed method.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Jiang:2016:CLT,
author = "Di Jiang and Yongxin Tong and Yuanfeng Song",
title = "Cross-Lingual Topic Discovery From Multilingual Search
Engine Query Log",
journal = j-TOIS,
volume = "35",
number = "2",
pages = "9:1--9:??",
month = dec,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2956235",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Today, major commercial search engines are operating
in a multinational fashion to provide web search
services for millions of users who compose search
queries by different languages. Hence, the search
engine query log, which serves as the backbone of many
search engine applications, records millions of users'
search history in a wide spectrum of human languages
and demonstrates a strong multilingual phenomenon.
However, with its salience, the multilingual nature of
a search engine query log is usually ignored by
existing works, which usually consider query log
entries of different languages as being orthogonal and
independent. This kind of oversimplified assumption
heavily distorts the underlying structure of web search
data. In this article, we pioneer in recognition of the
multilingual nature of a query log and make the first
attempt to cross the language barrier in query logs. We
propose a novel model named Cross-Lingual Query Log
Topic Model (CL-QLTM) to analyze query logs from a
cross-lingual perspective and derive the latent topics
of web search data. The CL-QLTM comprehensively
integrates web search data in different languages by
collectively utilizing cross-lingual dictionaries, as
well as the co-occurrence relations in the query log.
In order to relieve the efficiency bottleneck of
applying the CL-QLTM on voluminous query logs, we
propose an efficient parameter inference algorithm
based on the MapReduce computing paradigm. Both
qualitative and quantitative experimental results show
that the CL-QLTM is able to effectively derive
cross-lingual topics from multilingual query logs and
spawn a wide spectrum of new search engine
applications.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2016:ROC,
author = "Shuaiqiang Wang and Shanshan Huang and Tie-Yan Liu and
Jun Ma and Zhumin Chen and Jari Veijalainen",
title = "Ranking-Oriented Collaborative Filtering: a Listwise
Approach",
journal = j-TOIS,
volume = "35",
number = "2",
pages = "10:1--10:??",
month = dec,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2960408",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Collaborative filtering (CF) is one of the most
effective techniques in recommender systems, which can
be either rating oriented or ranking oriented.
Ranking-oriented CF algorithms demonstrated significant
performance gains in terms of ranking accuracy, being
able to estimate a precise preference ranking of items
for each user rather than the absolute ratings (as
rating-oriented CF algorithms do). Conventional
memory-based ranking-oriented CF can be referred to as
pairwise algorithms. They represent each user as a set
of preferences on each pair of items for similarity
calculations and predictions. In this study, we propose
ListCF, a novel listwise CF paradigm that seeks
improvement in both accuracy and efficiency in
comparison with pairwise CF. In ListCF, each user is
represented as a probability distribution of the
permutations over rated items based on the
Plackett-Luce model, and the similarity between users
is measured based on the Kullback--Leibler divergence
between their probability distributions over the set of
commonly rated items. Given a target user and the most
similar users, ListCF directly predicts a total order
of items for each user based on similar users'
probability distributions over permutations of the
items. Besides, we also reveal insightful connections
among pointwise, pairwise, and listwise CF algorithms
from the perspective of the matrix representations. In
addition, to make our algorithm more scalable and
adaptive, we present an incremental algorithm for
ListCF, which allows incrementally updating the
similarities between users when certain user submits a
new rating or updates an existing rating. Extensive
experiments on benchmark datasets in comparison with
the state-of-the-art approaches demonstrate the promise
of our approach.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yin:2016:JMU,
author = "Hongzhi Yin and Bin Cui and Xiaofang Zhou and Weiqing
Wang and Zi Huang and Shazia Sadiq",
title = "Joint Modeling of User Check-in Behaviors for
Real-time Point-of-Interest Recommendation",
journal = j-TOIS,
volume = "35",
number = "2",
pages = "11:1--11:??",
month = dec,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2873055",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Point-of-Interest (POI) recommendation has become an
important means to help people discover attractive and
interesting places, especially when users travel out of
town. However, the extreme sparsity of a user-POI
matrix creates a severe challenge. To cope with this
challenge, we propose a unified probabilistic
generative model, the Topic-Region Model (TRM), to
simultaneously discover the semantic, temporal, and
spatial patterns of users' check-in activities, and to
model their joint effect on users' decision making for
selection of POIs to visit. To demonstrate the
applicability and flexibility of TRM, we investigate
how it supports two recommendation scenarios in a
unified way, that is, hometown recommendation and
out-of-town recommendation. TRM effectively overcomes
data sparsity by the complementarity and mutual
enhancement of the diverse information associated with
users' check-in activities (e.g., check-in content,
time, and location) in the processes of discovering
heterogeneous patterns and producing recommendations.
To support real-time POI recommendations, we further
extend the TRM model to an online learning model,
TRM-Online, to track changing user interests and speed
up the model training. In addition, based on the
learned model, we propose a clustering-based branch and
bound algorithm (CBB) to prune the POI search space and
facilitate fast retrieval of the top- k
recommendations. We conduct extensive experiments to
evaluate the performance of our proposals on two
real-world datasets, including recommendation
effectiveness, overcoming the cold-start problem,
recommendation efficiency, and model-training
efficiency. The experimental results demonstrate the
superiority of our TRM models, especially TRM-Online,
compared with state-of-the-art competitive methods, by
making more effective and efficient mobile
recommendations. In addition, we study the importance
of each type of pattern in the two recommendation
scenarios, respectively, and find that exploiting
temporal patterns is most important for the hometown
recommendation scenario, while the semantic patterns
play a dominant role in improving the recommendation
effectiveness for out-of-town users.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chen:2016:BRU,
author = "Jia Chen and Qin Jin and Shiwan Zhao and Shenghua Bao
and Li Zhang and Zhong Su and Yong Yu",
title = "Boosting Recommendation in Unexplored Categories by
User Price Preference",
journal = j-TOIS,
volume = "35",
number = "2",
pages = "12:1--12:??",
month = dec,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2978579",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "State-of-the-art methods for product recommendation
encounter a significant performance drop in categories
where a user has no purchase history. This problem
needs to be addressed since current online retailers
are moving beyond single category and attempting to be
diversified. In this article, we investigate the
challenging problem of product recommendation in
unexplored categories and discover that the price, a
factor comparable across categories, can improve the
recommendation performance significantly. We introduce
the price utility concept to characterize users' sense
of price and propose three different utility functions.
We show that user price preference in a category is a
distribution and we mine typical user price preference
patterns based on three different types of distance
between distributions. We fuse user price preference
through regularization and joint factorization to boost
recommendation performance in both browsing and buying
shopping orientations. Experimental results show that
fusing user price preference improves performance in a
series of recommendation tasks: unexplored category
recommendation, product recommendation under a given
unexplored category, and product recommendation under
generic unexplored categories.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hu:2016:LIP,
author = "Liang Hu and Longbing Cao and Jian Cao and Zhiping Gu
and Guandong Xu and Dingyu Yang",
title = "Learning Informative Priors from Heterogeneous Domains
to Improve Recommendation in Cold-Start User Domains",
journal = j-TOIS,
volume = "35",
number = "2",
pages = "13:1--13:??",
month = dec,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2976737",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In the real-world environment, users have sufficient
experience in their focused domains but lack experience
in other domains. Recommender systems are very helpful
for recommending potentially desirable items to users
in unfamiliar domains, and cross-domain collaborative
filtering is therefore an important emerging research
topic. However, it is inevitable that the cold-start
issue will be encountered in unfamiliar domains due to
the lack of feedback data. The Bayesian approach shows
that priors play an important role when there are
insufficient data, which implies that recommendation
performance can be significantly improved in cold-start
domains if informative priors can be provided. Based on
this idea, we propose a Weighted Irregular Tensor
Factorization (WITF) model to leverage multi-domain
feedback data across all users to learn the
cross-domain priors w.r.t. both users and items. The
features learned from WITF serve as the informative
priors on the latent factors of users and items in
terms of weighted matrix factorization models.
Moreover, WITF is a unified framework for dealing with
both explicit feedback and implicit feedback. To prove
the effectiveness of our approach, we studied three
typical real-world cases in which a collection of
empirical evaluations were conducted on real-world
datasets to compare the performance of our model and
other state-of-the-art approaches. The results show the
superiority of our model over comparison models.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Thomason:2016:CTA,
author = "Alasdair Thomason and Nathan Griffiths and Victor
Sanchez",
title = "Context Trees: Augmenting Geospatial Trajectories with
Context",
journal = j-TOIS,
volume = "35",
number = "2",
pages = "14:1--14:??",
month = dec,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2978578",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Exposing latent knowledge in geospatial trajectories
has the potential to provide a better understanding of
the movements of individuals and groups. Motivated by
such a desire, this work presents the context tree, a
new hierarchical data structure that summarises the
context behind user actions in a single model. We
propose a method for context tree construction that
augments geospatial trajectories with land usage data
to identify such contexts. Through evaluation of the
construction method and analysis of the properties of
generated context trees, we demonstrate the foundation
for understanding and modelling behaviour afforded.
Summarising user contexts into a single data structure
gives easy access to information that would otherwise
remain latent, providing the basis for better
understanding and predicting the actions and behaviours
of individuals and groups. Finally, we also present a
method for pruning context trees for use in
applications where it is desirable to reduce the size
of the tree while retaining useful information.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Dato:2016:FRA,
author = "Domenico Dato and Claudio Lucchese and Franco Maria
Nardini and Salvatore Orlando and Raffaele Perego and
Nicola Tonellotto and Rossano Venturini",
title = "Fast Ranking with Additive Ensembles of Oblivious and
Non-Oblivious Regression Trees",
journal = j-TOIS,
volume = "35",
number = "2",
pages = "15:1--15:??",
month = dec,
year = "2016",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2987380",
ISSN = "1046-8188",
bibdate = "Mon Apr 3 11:29:19 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Learning-to-Rank models based on additive ensembles of
regression trees have been proven to be very effective
for scoring query results returned by large-scale Web
search engines. Unfortunately, the computational cost
of scoring thousands of candidate documents by
traversing large ensembles of trees is high. Thus,
several works have investigated solutions aimed at
improving the efficiency of document scoring by
exploiting advanced features of modern CPUs and memory
hierarchies. In this article, we present QuickScorer, a
new algorithm that adopts a novel cache-efficient
representation of a given tree ensemble, performs an
interleaved traversal by means of fast bitwise
operations, and supports ensembles of oblivious trees.
An extensive and detailed test assessment is conducted
on two standard Learning-to-Rank datasets and on a
novel very large dataset we made publicly available for
conducting significant efficiency tests. The
experiments show unprecedented speedups over the best
state-of-the-art baselines ranging from $ 1.9 \times $
to $ 6.6 \times $. The analysis of low-level profiling
traces shows that QuickScorer efficiency is due to its
cache-aware approach in terms of both data layout and
access patterns and to a control flow that entails very
low branch mis-prediction rates.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2017:TAC,
author = "Yiqun Liu and Xiaohui Xie and Chao Wang and Jian-Yun
Nie and Min Zhang and Shaoping Ma",
title = "Time-Aware Click Model",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "16:1--16:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2988230",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Click-through information is considered as a valuable
source of users' implicit relevance feedback for
commercial search engines. As existing studies have
shown that the search result position in a search
engine result page (SERP) has a very strong influence
on users' examination behavior, most existing click
models are position based, assuming that users examine
results from top to bottom in a linear fashion.
Although these click models have been successful, most
do not take temporal information into account. As many
existing studies have shown, click dwell time and click
sequence information are strongly correlated with
users' perceived relevance and search satisfaction.
Incorporating temporal information may be important to
improve performance of user click models for Web
searches. In this article, we investigate the problem
of properly incorporating temporal information into
click models. We first carry out a laboratory
eye-tracking study to analyze users' examination
behavior in different click sequences and find that the
user common examination path among adjacent clicks is
linear. Next, we analyze the user dwell time
distribution in different search logs and find that we
cannot simply use a click dwell time threshold (e.g.,
30 seconds) to distinguish relevant/irrelevant results.
Finally, we propose a novel time-aware click model
(TACM), which captures the temporal information of user
behavior. We compare the TACM to several existing click
models using two real-world search engine logs.
Experimental results show that the TACM outperforms
other click models in terms of both predicting click
behavior (perplexity) and estimating result relevance
(NDCG).",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Connor:2017:HEI,
author = "Richard Connor and Franco Alberto Cardillo and Lucia
Vadicamo and Fausto Rabitti",
title = "{Hilbert} Exclusion: Improved Metric Search through
Finite Isometric Embeddings",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "17:1--17:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3001583",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Most research into similarity search in metric spaces
relies on the triangle inequality property. This
property allows the space to be arranged according to
relative distances to avoid searching some subspaces.
We show that many common metric spaces, notably
including those using Euclidean and Jensen-Shannon
distances, also have a stronger property, sometimes
called the four-point property: In essence, these
spaces allow an isometric embedding of any four points
in three-dimensional Euclidean space, as well as any
three points in two-dimensional Euclidean space. In
fact, we show that any space that is isometrically
embeddable in Hilbert space has the stronger property.
This property gives stronger geometric guarantees, and
one in particular, which we name the Hilbert Exclusion
property, allows any indexing mechanism which uses
hyperplane partitioning to perform better. One outcome
of this observation is that a number of
state-of-the-art indexing mechanisms over
high-dimensional spaces can be easily refined to give a
significant increase in performance; furthermore, the
improvement given is greater in higher dimensions. This
therefore leads to a significant improvement in the
cost of metric search in these spaces.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Miao:2017:CEO,
author = "Zhongchen Miao and Kai Chen and Yi Fang and Jianhua He
and Yi Zhou and Wenjun Zhang and Hongyuan Zha",
title = "Cost-Effective Online Trending Topic Detection and
Popularity Prediction in Microblogging",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "18:1--18:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3001833",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Identifying topic trends on microblogging services
such as Twitter and estimating those topics' future
popularity have great academic and business value,
especially when the operations can be done in real
time. For any third party, however, capturing and
processing such huge volumes of real-time data in
microblogs are almost infeasible tasks, as there always
exist API (Application Program Interface) request
limits, monitoring and computing budgets, as well as
timeliness requirements. To deal with these challenges,
we propose a cost-effective system framework with
algorithms that can automatically select a subset of
representative users in microblogging networks in
offline, under given cost constraints. Then the
proposed system can online monitor and utilize only
these selected users' real-time microposts to detect
the overall trending topics and predict their future
popularity among the whole microblogging network.
Therefore, our proposed system framework is practical
for real-time usage as it avoids the high cost in
capturing and processing full real-time data, while not
compromising detection and prediction performance under
given cost constraints. Experiments with real
microblogs dataset show that by tracking only 500 users
out of 0.6 million users and processing no more than
30,000 microposts daily, about 92\% trending topics
could be detected and predicted by the proposed system
and, on average, more than 10 hours earlier than they
appear in official trends lists.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Maddalena:2017:CRM,
author = "Eddy Maddalena and Stefano Mizzaro and Falk Scholer
and Andrew Turpin",
title = "On Crowdsourcing Relevance Magnitudes for Information
Retrieval Evaluation",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "19:1--19:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3002172",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Magnitude estimation is a psychophysical scaling
technique for the measurement of sensation, where
observers assign numbers to stimuli in response to
their perceived intensity. We investigate the use of
magnitude estimation for judging the relevance of
documents for information retrieval evaluation,
carrying out a large-scale user study across 18 TREC
topics and collecting over 50,000 magnitude estimation
judgments using crowdsourcing. Our analysis shows that
magnitude estimation judgments can be reliably
collected using crowdsourcing, are competitive in terms
of assessor cost, and are, on average, rank-aligned
with ordinal judgments made by expert relevance
assessors. We explore the application of magnitude
estimation for IR evaluation, calibrating two
gain-based effectiveness metrics, nDCG and ERR,
directly from user-reported perceptions of relevance. A
comparison of TREC system effectiveness rankings based
on binary, ordinal, and magnitude estimation relevance
shows substantial variation; in particular, the top
systems ranked using magnitude estimation and ordinal
judgments differ substantially. Analysis of the
magnitude estimation scores shows that this effect is
due in part to varying perceptions of relevance:
different users have different perceptions of the
impact of relative differences in document relevance.
These results have direct implications for IR
evaluation, suggesting that current assumptions about a
single view of relevance being sufficient to represent
a population of users are unlikely to hold.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2017:TAP,
author = "Dongxiang Zhang and Long Guo and Liqiang Nie and Jie
Shao and Sai Wu and Heng Tao Shen",
title = "Targeted Advertising in Public Transportation Systems
with Quantitative Evaluation",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "20:1--20:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3003725",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In spite of vast business potential, targeted
advertising in public transportation systems is a
grossly unexplored research area. For instance, SBS
Transit in Singapore can reach 1 billion passengers per
year but the annual advertising revenue contributes
less than \$35 million. To bridge the gap, we propose a
probabilistic data model that captures the motion
patterns and user interests so as to quantitatively
evaluate the impact of an advertisement among the
passengers. In particular, we leverage hundreds of
millions of bus/train boarding transaction records to
quantitatively estimate the probability as well as the
extent of a user being influenced by an ad. Based on
the influence model, we study a top-$k$ retrieval
problem for bus/train ad recommendation, which acts as
a primitive operator to support various advanced
applications. We solve the retrieval problem
efficiently to support real-time decision making. In
the experimental study, we use the dataset from SBS
Transit as a case study to verify the effectiveness and
efficiency of our proposed methodologies.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Sadeghi:2017:RFB,
author = "Seyedeh Sargol Sadeghi and Roi Blanco and Peter Mika
and Mark Sanderson and Falk Scholer and David Vallet",
title = "Re-Finding Behaviour in Vertical Domains",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "21:1--21:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/2975590",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Re-finding is the process of searching for information
that a user has previously encountered and is a common
activity carried out with information retrieval
systems. In this work, we investigate re-finding in the
context of vertical search, differentiating and
modeling user re-finding behavior within different
media and topic domains, including images, news,
reference material, and movies. We distinguish the
re-finding behavior in vertical domains from re-finding
in a general search context and engineer features that
are effective in differentiating re-finding across the
domains. The features are then used to build
machine-learned models, achieving an accuracy of
re-finding detection in verticals of 85.7\% on average.
Our results demonstrate that detecting re-finding in
specific verticals is more difficult than examining
re-finding for general search tasks. We then
investigate the effectiveness of differentiating
re-finding behavior in two restricted contexts: We
consider the case where the history of a searcher's
interactions with the search system is not available.
In this scenario, our features and models achieve an
average accuracy of 77.5\% across the domains. We then
examine the detection of re-finding during the early
part of a search session. Both of these restrictions
represent potential real-world search scenarios, where
a system is attempting to learn about a user but may
have limited information available. Finally, we
investigate in which types of domains re-finding is
most difficult. Here, it would appear that re-finding
images is particularly challenging for users. This
research has implications for search engine design, in
terms of adapting search results by predicting the type
of user tasks and potentially enabling the presentation
of vertical-specific results when re-finding is
identified. To the best of our knowledge, this is the
first work to investigate the issue of vertical
re-finding.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Konow:2017:IT,
author = "Roberto Konow and Gonzalo Navarro and Charles L. A.
Clarke and Alejandro L{\'o}pez-Ort{\'\i}z",
title = "Inverted Treaps",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "22:1--22:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3007186",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We introduce a new representation of the inverted
index that performs faster ranked unions and
intersections while using similar space. Our index is
based on the treap data structure, which allows us to
intersect/merge the document identifiers while
simultaneously thresholding by frequency, instead of
the costlier two-step classical processing methods. To
achieve compression, we represent the treap topology
using different alternative compact data structures.
Further, the treap invariants allow us to elegantly
encode differentially both document identifiers and
frequencies. We also show how to extend this
representation to support incremental updates over the
index. Results show that, under the tf-idf scoring
scheme, our index uses about the same space as
state-of-the-art compact representations, while
performing up to 2--20 times faster on ranked
single-word, union, or intersection queries. Under the
BM25 scoring scheme, our index may use up to 40\% more
space than the others and outperforms them less
frequently but still reaches improvement factors of
2--20 in the best cases. The index supporting
incremental updates poses an overhead of 50\%--100\%
over the static variants in terms of space,
construction, and query time.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{White:2017:SRP,
author = "Ryen W. White and Fernando Diaz and Qi Guo",
title = "Search Result Prefetching on Desktop and Mobile",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "23:1--23:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3015466",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Search result examination is an important part of
searching. High page load latency for landing pages
(clicked search results) can reduce the efficiency of
the search process. Proactively prefetching landing
pages in advance of clickthrough can save searchers
valuable time. However, prefetching consumes resources
(primarily bandwidth and battery) that are wasted
unless the prefetched results are requested by
searchers. Balancing the costs in prefetching
particular results against the benefits in reduced
latency to searchers represents the search result
prefetching challenge. In this article, we introduce
this challenge and present methods to address it in
both desktop and mobile settings. Our methods leverage
searchers' cursor movements (on desktop) and
viewport-based viewing behavior (on mobile) on search
engine result pages (SERPs) in real time to dynamically
estimate the result that searchers will request next.
We demonstrate through large-scale log analysis that
our approach significantly outperforms three strong
baselines that prefetch results based on (i) the search
engine result ranking (prefetch top-ranked results),
(ii) past SERP clicks from all searchers for the query
(prefetch popular results), or (iii) past SERP clicks
from the current searcher for the query (prefetch
results that the searcher prefers). Our promising
findings have implications for the design of search
support in desktop and mobile settings that makes the
search process more efficient.",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Moffat:2017:IUE,
author = "Alistair Moffat and Peter Bailey and Falk Scholer and
Paul Thomas",
title = "Incorporating User Expectations and Behavior into the
Measurement of Search Effectiveness",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "24:1--24:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052768",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Information retrieval systems aim to help users
satisfy information needs. We argue that the goal of
the person using the system, and the pattern of
behavior that they exhibit as they proceed to attain
that goal, should be incorporated into the methods and
techniques used to evaluate the effectiveness of IR
systems, so that the resulting effectiveness scores
have a useful interpretation that corresponds to the
users' search experience. In particular, we investigate
the role of search task complexity, and show that it
has a direct bearing on the number of relevant answer
documents sought by users in response to an information
need, suggesting that useful effectiveness metrics must
be goal sensitive. We further suggest that user
behavior while scanning results listings is affected by
the rate at which their goal is being realized, and
hence that appropriate effectiveness metrics must be
adaptive to the presence (or not) of relevant documents
in the ranking. In response to these two observations,
we present a new effectiveness metric, INST, that has
both of the desired properties: INST employs a
parameter T, a direct measure of the user's search goal
that adjusts the top-weightedness of the evaluation
score; moreover, as progress towards the target T is
made, the modeled user behavior is adapted, to reflect
the remaining expectations. INST is experimentally
compared to previous effectiveness metrics, including
Average Precision (AP), Normalized Discounted
Cumulative Gain (NDCG), and Rank-Biased Precision
(RBP), demonstrating our claims as to INST's
usefulness. Like RBP, INST is a weighted-precision
metric, meaning that each score can be accompanied by a
residual that quantifies the extent of the score
uncertainty caused by unjudged documents. As part of
our experimentation, we use crowd-sourced data and
score residuals to demonstrate that a wide range of
queries arise for even quite specific information
needs, and that these variant queries introduce
significant levels of residual uncertainty into typical
experimental evaluations. These causes of variability
have wide-reaching implications for experiment design,
and for the construction of test collections.",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hu:2017:IQR,
author = "Liang Hu and Longbing Cao and Jian Cao and Zhiping Gu
and Guandong Xu and Jie Wang",
title = "Improving the Quality of Recommendations for Users and
Items in the Tail of Distribution",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "25:1--25:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052769",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Short-head and long-tail distributed data are widely
observed in the real world. The same is true of
recommender systems (RSs), where a small number of
popular items dominate the choices and feedback data
while the rest only account for a small amount of
feedback. As a result, most RS methods tend to learn
user preferences from popular items since they account
for most data. However, recent research in e-commerce
and marketing has shown that future businesses will
obtain greater profit from long-tail selling. Yet,
although the number of long-tail items and users is
much larger than that of short-head items and users, in
reality, the amount of data associated with long-tail
items and users is much less. As a result, user
preferences tend to be popularity-biased. Furthermore,
insufficient data makes long-tail items and users more
vulnerable to shilling attack. To improve the quality
of recommendations for items and users in the tail of
distribution, we propose a coupled regularization
approach that consists of two latent factor models:
C-HMF, for enhancing credibility, and S-HMF, for
emphasizing specialty on user choices. Specifically,
the estimates learned from C-HMF and S-HMF recurrently
serve as the empirical priors to regularize one
another. Such coupled regularization leads to the
comprehensive effects of final estimates, which produce
more qualitative predictions for both tail users and
tail items. To assess the effectiveness of our model,
we conduct empirical evaluations on large real-world
datasets with various metrics. The results prove that
our approach significantly outperforms the compared
methods.",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Huang:2017:ESK,
author = "Minlie Huang and Qiao Qian and Xiaoyan Zhu",
title = "Encoding Syntactic Knowledge in Neural Networks for
Sentiment Classification",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "26:1--26:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052770",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Phrase/Sentence representation is one of the most
important problems in natural language processing. Many
neural network models such as Convolutional Neural
Network (CNN), Recursive Neural Network (RNN), and Long
Short-Term Memory (LSTM) have been proposed to learn
representations of phrase/sentence, however, rich
syntactic knowledge has not been fully explored when
composing a longer text from its shorter constituent
words. In most traditional models, only word embeddings
are utilized to compose phrase/sentence
representations, while the syntactic information of
words is yet to be explored. In this article, we
discover that encoding syntactic knowledge
(part-of-speech tag) in neural networks can enhance
sentence/phrase representation. Specifically, we
propose to learn tag-specific composition functions and
tag embeddings in recursive neural networks, and
propose to utilize POS tags to control the gates of
tree-structured LSTM networks. We evaluate these models
on two benchmark datasets for sentiment classification,
and demonstrate that improvements can be obtained with
such syntactic knowledge encoded.",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2017:CIJ,
author = "Dongxiang Zhang and Liqiang Nie and Huanbo Luan and
Kian-Lee Tan and Tat-Seng Chua and Heng Tao Shen",
title = "Compact Indexing and Judicious Searching for
Billion-Scale Microblog Retrieval",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "27:1--27:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052771",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In this article, we study the problem of efficient
top- k disjunctive query processing in a huge microblog
dataset. In terms of compact indexing, we categorize
the keywords into rare terms and common terms based on
inverse document frequency (idf) and propose tailored
block-oriented organization to save memory consumption.
In terms of fast searching, we classify the queries
into three types based on term category and judiciously
design an efficient search algorithm for each type. We
conducted extensive experiments on a billion-scale
Twitter dataset and examined the performance with both
simple and more advanced ranking functions. The results
showed that with much smaller index size, our search
algorithm achieves a factor of 2--3 times faster
speedup over state-of-the-art solutions in both ranking
scenarios.",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2017:PLQ,
author = "Dongxiang Zhang and Yuchen Li and Ju Fan and Lianli
Gao and Fumin Shen and Heng Tao Shen",
title = "Processing Long Queries Against Short Text: Top-$k$
Advertisement Matching in News Stream Applications",
journal = j-TOIS,
volume = "35",
number = "3",
pages = "28:1--28:??",
month = jun,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052772",
ISSN = "1046-8188",
ISSN-L = "0734-2047",
bibdate = "Tue Jul 11 17:07:53 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tois/;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Many real applications in real-time news stream
advertising call for efficient processing of long
queries against short text. In such applications,
dynamic news feeds are regarded as queries to match
against an advertisement (ad) database for retrieving
the k most relevant ads. The existing approaches to
keyword retrieval cannot work well in this search
scenario when queries are triggered at a very high
frequency. To address the problem, we introduce new
techniques to significantly improve search performance.
First, we devise a two-level partitioning for tight
upper bound estimation and a lazy evaluation scheme to
delay full evaluation of unpromising candidates, which
can bring three to four times performance boosting in a
database with 7 million ads. Second, we propose a novel
rank-aware block-oriented inverted index to further
improve performance. In this index scheme, each entry
in an inverted list is assigned a rank according to its
importance in the ad. Then, we introduce a
block-at-a-time search strategy based on the index
scheme to support a much tighter upper bound estimation
and a very early termination. We have conducted
experiments with real datasets, and the results show
that the rank-aware method can further improve
performance by an order of magnitude.",
acknowledgement = ack-nhfb,
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2017:SMT,
author = "Hongning Wang and Rui Li and Milad Shokouhi and Hang
Li and Yi Chang",
title = "Search, Mining, and Their Applications on Mobile
Devices: Introduction to the Special Issue",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "29:1--29:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086665",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In recent years, mobile devices have become the most
popular interface for users to retrieve and access
information: recent reports show that users spend
significantly more time and issue more search queries
on mobile devices than on desktops in the United
States. The accelerated growth of mobile usage brings
unique opportunities to the information retrieval and
data mining research communities. Mobile devices
capture rich contextual and personal signals that can
be leveraged to accurately predict users' intent for
serving more relevant content and can even proactively
provide novel zero-query recommendations. Apple Siri,
Google Now, and Microsoft Cortana are recent examples
of such emerging systems. Furthermore, mobile devices
constantly generate a huge amount of sensor footprints
(e.g., GPS, motion sensors) and user activity data
(e.g., used apps) that are often missing from their
desktop counterparts. These new sources of implicit and
explicit user feedback are valuable for discovering
actionable knowledge, and designing better systems that
serve each individual the right content at the right
time and location. In addition, by aggregating mobile
interactions across individuals, one can infer
interesting conclusions beyond search and
recommendation. Generating real-time traffic estimates
is one example of such applications. This special issue
focuses on research problems of search, mining, and
their applications in mobile devices. Topics of
interest in this special issue include but are not
limited to mobile data mining and management, mobile
search, personalization and recommendation, mobile user
interfaces and human-computer interaction, and new
applications in the mobile environment. The aim of this
special issue is to bring together top experts across
multiple disciplines, including information retrieval,
data mining, mobile computing, and cyberphysical
systems, such that academic and industrial researchers
can exchange ideas and share the latest developments on
the state of the art and practice of mobile search and
mobile data mining.",
acknowledgement = ack-nhfb,
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Sun:2017:CIP,
author = "Yu Sun and Nicholas Jing Yuan and Xing Xie and Kieran
McDonald and Rui Zhang",
title = "Collaborative Intent Prediction with Real-Time
Contextual Data",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "30:1--30:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3041659",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Intelligent personal assistants on mobile devices such
as Apple's Siri and Microsoft Cortana are increasingly
important. Instead of passively reacting to queries,
they provide users with brand new proactive experiences
that aim to offer the right information at the right
time. It is, therefore, crucial for personal assistants
to understand users' intent, that is, what information
users need now. Intent is closely related to context.
Various contextual signals, including spatio-temporal
information and users' activities, can signify users'
intent. It is, however, challenging to model the
correlation between intent and context. Intent and
context are highly dynamic and often sequentially
correlated. Contextual signals are usually sparse,
heterogeneous, and not simultaneously available. We
propose an innovative collaborative nowcasting model to
jointly address all these issues. The model effectively
addresses the complex sequential and concurring
correlation between context and intent and recognizes
users' real-time intent with continuously arrived
contextual signals. We extensively evaluate the
proposed model with real-world data sets from a
commercial personal assistant. The results validate the
effectiveness the proposed model, and demonstrate its
capability of handling the real-time flow of contextual
signals. The studied problem and model also provide
inspiring implications for new paradigms of
recommendation on mobile intelligent devices.",
acknowledgement = ack-nhfb,
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Li:2017:TAP,
author = "Xin Li and Mingming Jiang and Huiting Hong and Lejian
Liao",
title = "A Time-Aware Personalized Point-of-Interest
Recommendation via High-Order Tensor Factorization",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "31:1--31:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3057283",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Recently, location-based services (LBSs) have been
increasingly popular for people to experience new
possibilities, for example, personalized
point-of-interest (POI) recommendations that leverage
on the overlapping of user trajectories to recommend
POI collaboratively. POI recommendation is yet
challenging as it suffers from the problems known for
the conventional recommendation tasks such as data
sparsity and cold start, and to a much greater extent.
In the literature, most of the related works apply
collaborate filtering to POI recommendation while
overlooking the personalized time-variant human
behavioral tendency. In this article, we put forward a
fourth-order tensor factorization-based ranking
methodology to recommend users their interested
locations by considering their time-varying behavioral
trends while capturing their long-term preferences and
short-term preferences simultaneously. We also propose
to categorize the locations to alleviate data sparsity
and cold-start issues, and accordingly new POIs that
users have not visited can thus be bubbled up during
the category ranking process. The tensor factorization
is carefully studied to prune the irrelevant factors to
the ranking results to achieve efficient POI
recommendations. The experimental results validate the
efficacy of our proposed mechanism, which outperforms
the state-of-the-art approaches significantly.",
acknowledgement = ack-nhfb,
articleno = "31",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{He:2017:MEB,
author = "Jiangning He and Hongyan Liu",
title = "Mining Exploratory Behavior to Improve Mobile App
Recommendations",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "32:1--32:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3072588",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the widespread usage of smart phones, more and
more mobile apps are developed every day, playing an
increasingly important role in changing our lifestyles
and business models. In this trend, it becomes a hot
research topic for developing effective mobile app
recommender systems in both industry and academia.
Compared with existing studies about mobile app
recommendations, our research aims to improve the
recommendation effectiveness based on analyzing a
psychological trait of human beings, exploratory
behavior, which refers to a type of variety-seeking
behavior in unfamiliar domains. To this end, we propose
a novel probabilistic model named Goal-oriented
Exploratory Model (GEM), integrating exploratory
behavior identification with personalized item
recommendation. An algorithm combining collapsed Gibbs
sampling and Expectation Maximization is developed for
model learning and inference. Through extensive
experiments conducted on a real dataset, the proposed
model demonstrates superior recommendation performances
and good interpretability compared with state-of-art
recommendation methods. Moreover, empirical analyses on
exploratory behavior find that individuals with a
strong exploratory tendency exhibit behavioral patterns
of variety seeking, risk taking, and higher
involvement. Besides, mobile apps that are less popular
or in the long tail possess greater potential of
arousing exploratory behavior in individuals.",
acknowledgement = ack-nhfb,
articleno = "32",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bradesko:2017:CCM,
author = "Luka Bradesko and Michael Witbrock and Janez Starc and
Zala Herga and Marko Grobelnik and Dunja Mladeni{\'c}",
title = "Curious Cat-Mobile, Context-Aware Conversational
Crowdsourcing Knowledge Acquisition",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "33:1--33:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086686",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Scaled acquisition of high-quality structured
knowledge has been a longstanding goal of Artificial
Intelligence research. Recent advances in
crowdsourcing, the sheer number of Internet and mobile
users, and the commercial availability of supporting
platforms offer new tools for knowledge acquisition.
This article applies context-aware knowledge
acquisition that simultaneously satisfies users'
immediate information needs while extending its own
knowledge using crowdsourcing. The focus is on
knowledge acquisition on a mobile device, which makes
the approach practical and scalable; in this context,
we propose and implement a new KA approach that
exploits an existing knowledge base to drive the KA
process, communicate with the right people, and check
for consistency of the user-provided answers. We tested
the viability of the approach in experiments using our
platform with real users around the world, and an
existing large source of common-sense background
knowledge. These experiments show that the approach is
promising: the knowledge is estimated to be true and
useful for users 95\% of the time. Using context to
proactively drive knowledge acquisition increased
engagement and effectiveness (the number of new
assertions/day/user increased for 175\%). Using
pre-existing and newly acquired knowledge also proved
beneficial.",
acknowledgement = ack-nhfb,
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Umemoto:2017:SSU,
author = "Kazutoshi Umemoto and Ruihua Song and Jian-Yun Nie and
Xing Xie and Katsumi Tanaka and Yong Rui",
title = "Search by Screenshots for Universal Article Clipping
in Mobile Apps",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "34:1--34:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3091107",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "To address the difficulty in clipping articles from
various mobile applications (apps), we propose a novel
framework called UniClip, which allows a user to snap a
screen of an article to save the whole article in one
place. The key task of the framework is search by
screenshots, which has three challenges: (1) how to
represent a screenshot; (2) how to formulate queries
for effective article retrieval; and (3) how to
identify the article from search results. We solve
these by (1) segmenting a screenshot into structural
units called blocks, (2) formulating effective search
queries by considering the role of each block, and (3)
aggregating the search result lists of multiple
queries. To improve efficiency, we also extend our
approach with learning-to-rank techniques so that we
can find the desired article with only one query.
Experimental results show that our approach achieves
high retrieval performance ($ F_1 = 0.868$), which
outperforms baselines based on keyword extraction and
chunking methods. Learning-to-rank models improve our
approach without learning by about 6\%. A user study
conducted to investigate the usability of UniClip
reveals that ours is preferred by 21 out of 22
participants for its simplicity and effectiveness.",
acknowledgement = ack-nhfb,
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Dong:2017:UMD,
author = "Yuxiao Dong and Nitesh V. Chawla and Jie Tang and Yang
Yang and Yang Yang",
title = "User Modeling on Demographic Attributes in Big Mobile
Social Networks",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "35:1--35:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3057278",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Users with demographic profiles in social networks
offer the potential to understand the social principles
that underpin our highly connected world, from
individuals, to groups, to societies. In this article,
we harness the power of network and data sciences to
model the interplay between user demographics and
social behavior and further study to what extent users'
demographic profiles can be inferred from their mobile
communication patterns. By modeling over 7 million
users and 1 billion mobile communication records, we
find that during the active dating period (i.e., 18--35
years old), users are active in broadening social
connections with males and females alike, while after
reaching 35 years of age people tend to keep small,
closed, and same-gender social circles. Further, we
formalize the demographic prediction problem of
inferring users' gender and age simultaneously. We
propose a factor graph-based WhoAmI method to address
the problem by leveraging not only the correlations
between network features and users' gender/age, but
also the interrelations between gender and age. In
addition, we identify a new problem-coupled network
demographic prediction across multiple mobile
operators-and present a coupled variant of the WhoAmI
method to address its unique challenges. Our extensive
experiments demonstrate the effectiveness, scalability,
and applicability of the WhoAmI methods. Finally, our
study finds a greater than 80\% potential
predictability for inferring users' gender from phone
call behavior and 73\% for users' age from text
messaging interactions.",
acknowledgement = ack-nhfb,
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yang:2017:NNA,
author = "Cheng Yang and Maosong Sun and Wayne Xin Zhao and
Zhiyuan Liu and Edward Y. Chang",
title = "A Neural Network Approach to Jointly Modeling Social
Networks and Mobile Trajectories",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "36:1--36:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3041658",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Two characteristics of location-based services are
mobile trajectories and the ability to facilitate
social networking. The recording of trajectory data
contributes valuable resources towards understanding
users' geographical movement behaviors. Social
networking is possible when users are able to quickly
connect to anyone nearby. A social network with
location based services is known as location-based
social network (LBSN). As shown in Cho et al. [2013],
locations that are frequently visited by socially
related persons tend to be correlated, which indicates
the close association between social connections and
trajectory behaviors of users in LBSNs. To better
analyze and mine LBSN data, we need to have a
comprehensive view of each of these two aspects, i.e.,
the mobile trajectory data and the social network.
Specifically, we present a novel neural network model
that can jointly model both social networks and mobile
trajectories. Our model consists of two components: the
construction of social networks and the generation of
mobile trajectories. First we adopt a network embedding
method for the construction of social networks: a
networking representation can be derived for a user.
The key to our model lies in generating mobile
trajectories. Second, we consider four factors that
influence the generation process of mobile
trajectories: user visit preference, influence of
friends, short-term sequential contexts, and long-term
sequential contexts. To characterize the last two
contexts, we employ the RNN and GRU models to capture
the sequential relatedness in mobile trajectories at
the short or long term levels. Finally, the two
components are tied by sharing the user network
representations. Experimental results on two important
applications demonstrate the effectiveness of our
model. In particular, the improvement over baselines is
more significant when either network structure or
trajectory data is sparse.",
acknowledgement = ack-nhfb,
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cao:2017:CPA,
author = "Da Cao and Xiangnan He and Liqiang Nie and Xiaochi Wei
and Xia Hu and Shunxiang Wu and Tat-Seng Chua",
title = "Cross-Platform App Recommendation by Jointly Modeling
Ratings and Texts",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "37:1--37:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3017429",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Over the last decade, the renaissance of Web
technologies has transformed the online world into an
application (App) driven society. While the abundant
Apps have provided great convenience, their sheer
number also leads to severe information overload,
making it difficult for users to identify desired Apps.
To alleviate the information overloading issue,
recommender systems have been proposed and deployed for
the App domain. However, existing work on App
recommendation has largely focused on one single
platform (e.g., smartphones), while it ignores the rich
data of other relevant platforms (e.g., tablets and
computers). In this article, we tackle the problem of
cross-platform App recommendation, aiming at leveraging
users' and Apps' data on multiple platforms to enhance
the recommendation accuracy. The key advantage of our
proposal is that by leveraging multiplatform data, the
perpetual issues in personalized recommender
systems-data sparsity and cold-start-can be largely
alleviated. To this end, we propose a hybrid solution,
STAR (short for ``croSs-plaTform App Recommendation'')
that integrates both numerical ratings and textual
content from multiple platforms. In STAR, we
innovatively represent an App as an aggregation of
common features across platforms (e.g., App's
functionalities) and specific features that are
dependent on the resided platform. In light of this,
STAR can discriminate a user's preference on an App by
separating the user's interest into two parts (either
in the App's inherent factors or platform-aware
features). To evaluate our proposal, we construct two
real-world datasets that are crawled from the App
stores of iPhone, iPad, and iMac. Through extensive
experiments, we show that our STAR method consistently
outperforms highly competitive recommendation methods,
justifying the rationality of our cross-platform App
recommendation proposal and the effectiveness of our
solution.",
acknowledgement = ack-nhfb,
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yao:2017:VAR,
author = "Yuan Yao and Wayne Xin Zhao and Yaojing Wang and
Hanghang Tong and Feng Xu and Jian Lu",
title = "Version-Aware Rating Prediction for Mobile App
Recommendation",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "38:1--38:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3015458",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the great popularity of mobile devices, the
amount of mobile apps has grown at a more dramatic rate
than ever expected. A technical challenge is how to
recommend suitable apps to mobile users. In this work,
we identify and focus on a unique characteristic that
exists in mobile app recommendation-that is, an app
usually corresponds to multiple release versions. Based
on this characteristic, we propose a fine-grain
version-aware app recommendation problem. Instead of
directly learning the users' preferences over the apps,
we aim to infer the ratings of users on a specific
version of an app. However, the user-version rating
matrix will be sparser than the corresponding user-app
rating matrix, making existing recommendation methods
less effective. In view of this, our approach has made
two major extensions. First, we leverage the review
text that is associated with each rating record; more
importantly, we consider two types of version-based
correlations. The first type is to capture the temporal
correlations between multiple versions within the same
app, and the second type of correlation is to capture
the aggregation correlations between similar apps.
Experimental results on a large dataset demonstrate the
superiority of our approach over several competitive
methods.",
acknowledgement = ack-nhfb,
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2017:DUP,
author = "Xuanzhe Liu and Wei Ai and Huoran Li and Jian Tang and
Gang Huang and Feng Feng and Qiaozhu Mei",
title = "Deriving User Preferences of Mobile Apps from Their
Management Activities",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "39:1--39:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3015462",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "App marketplaces host millions of mobile apps that are
downloaded billions of times. Investigating how people
manage mobile apps in their everyday lives creates a
unique opportunity to understand the behavior and
preferences of mobile device users, infer the quality
of apps, and improve user experience. Existing
literature provides very limited knowledge about app
management activities, due to the lack of app usage
data at scale. This article takes the initiative to
analyze a very large app management log collected
through a leading Android app marketplace. The dataset
covers 5 months of detailed downloading, updating, and
uninstallation activities, which involve 17 million
anonymized users and 1 million apps. We present a
surprising finding that the metrics commonly used to
rank apps in app stores do not truly reflect the users'
real attitudes. We then identify behavioral patterns
from the app management activities that more accurately
indicate user preferences of an app even when no
explicit rating is available. A systematic statistical
analysis is designed to evaluate machine learning
models that are trained to predict user preferences
using these behavioral patterns, which features an
inverse probability weighting method to correct the
selection biases in the training process.",
acknowledgement = ack-nhfb,
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2017:CUT,
author = "Senzhang Wang and Xiaoming Zhang and Jianping Cao and
Lifang He and Leon Stenneth and Philip S. Yu and
Zhoujun Li and Zhiqiu Huang",
title = "Computing Urban Traffic Congestions by Incorporating
Sparse {GPS} Probe Data and Social Media Data",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "40:1--40:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3057281",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Estimating urban traffic conditions of an arterial
network with GPS probe data is a practically important
while substantially challenging problem, and has
attracted increasing research interests recently.
Although GPS probe data is becoming a ubiquitous data
source for various traffic related applications
currently, they are usually insufficient for fully
estimating traffic conditions of a large arterial
network due to the low sampling frequency. To explore
other data sources for more effectively computing urban
traffic conditions, we propose to collect various
traffic events such as traffic accident and jam from
social media as complementary information. In addition,
to further explore other factors that might affect
traffic conditions, we also extract rich auxiliary
information including social events, road features,
Point of Interest (POI), and weather. With the enriched
traffic data and auxiliary information collected from
different sources, we first study the traffic
co-congestion pattern mining problem with the aim of
discovering which road segments geographically close to
each other are likely to co-occur traffic congestion. A
search tree based approach is proposed to efficiently
discover the co-congestion patterns. These patterns are
then used to help estimate traffic congestions and
detect anomalies in a transportation network. To fuse
the multisourced data, we finally propose a coupled
matrix and tensor factorization model named TCE\_R to
more accurately complete the sparse traffic congestion
matrix by collaboratively factorizing it with other
matrices and tensors formed by other data. We evaluate
the proposed model on the arterial network of downtown
Chicago with 1,257 road segments whose total length is
nearly 700 miles. The results demonstrate the superior
performance of TCE\_R by comprehensive comparison with
existing approaches.",
acknowledgement = ack-nhfb,
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Song:2017:DLD,
author = "Xuan Song and Ryosuke Shibasaki and Nicholos Jing Yuan
and Xing Xie and Tao Li and Ryutaro Adachi",
title = "{DeepMob}: Learning Deep Knowledge of Human Emergency
Behavior and Mobility from Big and Heterogeneous Data",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "41:1--41:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3057280",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The frequency and intensity of natural disasters has
increased significantly in recent decades, and this
trend is expected to continue. Hence, understanding and
predicting human evacuation behavior and mobility will
play a vital role in planning effective humanitarian
relief, disaster management, and long-term societal
reconstruction. However, existing models are shallow
models, and it is difficult to apply them for
understanding the ``deep knowledge'' of human mobility.
Therefore, in this study, we collect big and
heterogeneous data (e.g., GPS records of 1.6 million
users over 3 years, data on earthquakes that have
occurred in Japan over 4 years, news report data, and
transportation network data), and we build an
intelligent system, namely, DeepMob, for understanding
and predicting human evacuation behavior and mobility
following different types of natural disasters. The key
component of DeepMob is based on a deep learning
architecture that aims to understand the basic laws
that govern human behavior and mobility following
natural disasters, from big and heterogeneous data.
Furthermore, based on the deep learning model, DeepMob
can accurately predict or simulate a person's future
evacuation behaviors or evacuation routes under
different disaster conditions. Experimental results and
validations demonstrate the efficiency and superior
performance of our system, and suggest that human
mobility following disasters may be predicted and
simulated more easily than previously thought.",
acknowledgement = ack-nhfb,
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Farseev:2017:TCF,
author = "Aleksandr Farseev and Tat-Seng Chua",
title = "Tweet Can Be Fit: Integrating Data from Wearable
Sensors and Multiple Social Networks for Wellness
Profile Learning",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "42:1--42:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086676",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Wellness is a widely popular concept that is commonly
applied to fitness and self-help products or services.
Inference of personal wellness--related attributes,
such as body mass index (BMI) category or disease
tendency, as well as understanding of global
dependencies between wellness attributes and users'
behavior, is of crucial importance to various
applications in personal and public wellness domains.
At the same time, the emergence of social media
platforms and wearable sensors makes it feasible to
perform wellness profiling for users from multiple
perspectives. However, research efforts on wellness
profiling and integration of social media and sensor
data are relatively sparse. This study represents one
of the first attempts in this direction. Specifically,
we infer personal wellness attributes by utilizing our
proposed multisource multitask wellness profile
learning framework-WellMTL-which can handle data
incompleteness and perform wellness attributes
inference from sensor and social media data
simultaneously. To gain insights into the data at a
global level, we also examine correlations between
first-order data representations and personal wellness
attributes. Our experimental results show that the
integration of sensor data and multiple social media
sources can substantially boost the performance of
individual wellness profiling.",
acknowledgement = ack-nhfb,
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2017:UPP,
author = "Haoyu Wang and Yuanchun Li and Yao Guo and Yuvraj
Agarwal and Jason I. Hong",
title = "Understanding the Purpose of Permission Use in Mobile
Apps",
journal = j-TOIS,
volume = "35",
number = "4",
pages = "43:1--43:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086677",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:46 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Mobile apps frequently request access to sensitive
data, such as location and contacts. Understanding the
purpose of why sensitive data is accessed could help
improve privacy as well as enable new kinds of access
control. In this article, we propose a text mining
based method to infer the purpose of sensitive data
access by Android apps. The key idea we propose is to
extract multiple features from app code and then use
those features to train a machine learning classifier
for purpose inference. We present the design,
implementation, and evaluation of two complementary
approaches to infer the purpose of permission use,
first using purely static analysis, and then using
primarily dynamic analysis. We also discuss the pros
and cons of both approaches and the trade-offs
involved.",
acknowledgement = ack-nhfb,
articleno = "43",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Alkwai:2017:CAR,
author = "Lulwah M. Alkwai and Michael L. Nelson and Michele C.
Weigle",
title = "Comparing the Archival Rate of {Arabic}, {English},
{Danish}, and {Korean} Language {Web} Pages",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "1:1--1:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3041656",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "It has long been suspected that web archives and
search engines favor Western and English language
webpages. In this article, we quantitatively explore
how well indexed and archived Arabic language webpages
are as compared to those from other languages. We began
by sampling 15,092 unique URIs from three different
website directories: DMOZ (multilingual), Raddadi, and
Star28 (the last two primarily Arabic language). Using
language identification tools, we eliminated pages not
in the Arabic language (e.g., English-language versions
of Aljazeera pages) and culled the collection to 7,976
Arabic language webpages. We then used these 7,976
pages and crawled the live web and web archives to
produce a collection of 300,646 Arabic language pages.
We compared the analysis of Arabic language pages with
that of English, Danish, and Korean language pages.
First, for each language, we sampled unique URIs from
DMOZ; then, using language identification tools, we
kept only pages in the desired language. Finally, we
crawled the archived and live web to collect a larger
sample of pages in English, Danish, or Korean. In total
for the four languages, we analyzed over 500,000
webpages. We discovered: (1) English has a higher
archiving rate than Arabic, with 72.04\% archived.
However, Arabic has a higher archiving rate than Danish
and Korean, with 53.36\% of Arabic URIs archived,
followed by Danish and Korean with 35.89\% and 32.81\%
archived, respectively. (2) Most Arabic and English
language pages are located in the United States; only
14.84\% of the Arabic URIs had an Arabic country code
top-level domain (e.g., sa) and only 10.53\% had a
GeoIP in an Arabic country. Most Danish-language pages
were located in Denmark, and most Korean-language pages
were located in South Korea. (3) The presence of a
webpage in a directory positively impacts indexing and
presence in the DMOZ directory, specifically,
positively impacts archiving in all four languages. In
this work, we show that web archives and search engines
favor English pages. However, it is not universally
true for all Western-language webpages because, in this
work, we show that Arabic webpages have a higher
archival rate than Danish language webpages.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pibiri:2017:CEF,
author = "Giulio Ermanno Pibiri and Rossano Venturini",
title = "Clustered {Elias--Fano} Indexes",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "2:1--2:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052773",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "State-of-the-art encoders for inverted indexes
compress each posting list individually. Encoding
clusters of posting lists offers the possibility of
reducing the redundancy of the lists while maintaining
a noticeable query processing speed. In this article,
we propose a new index representation based on
clustering the collection of posting lists and, for
each created cluster, building an ad hoc reference list
with respect to which all lists in the cluster are
encoded with Elias-Fano. We describe a posting lists
clustering algorithm tailored for our encoder and two
methods for building the reference list for a cluster.
Both approaches are heuristic and differ in the way
postings are added to the reference list: according to
their frequency in the cluster or according to the
number of bits necessary for their representation. The
extensive experimental analysis indicates that
significant space reductions are indeed possible,
beating the best state-of-the-art encoders.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Jiang:2017:GGS,
author = "Jiawei Jiang and Yunhai Tong and Hua Lu and Bin Cui
and Kai Lei and Lele Yu",
title = "{GVoS}: a General System for Near-Duplicate
Video-Related Applications on Storm",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "3:1--3:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3041657",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The exponential increase of online videos greatly
enriches the life of users but also brings huge numbers
of near-duplicate videos (NDVs) that seriously
challenge the video websites. The video websites entail
NDV-related applications such as detection of copyright
violation, video monitoring, video re-ranking, and
video recommendation. Since these applications adopt
different features and different processing procedures
due to diverse scenarios, constructing separate and
special-purpose systems for them incurs considerable
costs on design, implementation, and maintenance. In
this article, we propose a general NDV system on Storm
(GVoS)-a popular distributed real-time stream
processing platform-to simultaneously support a wide
variety of video applications. The generality of GVoS
is achieved in two aspects. First, we extract the
reusable components from various applications. Second,
we conduct the communication between components via a
mechanism called Stream Shared Message (SSM) that
contains the video-related data. Furthermore, we
present an algorithm to reduce the size of SSM in order
to avoid the data explosion and decrease the network
latency. The experimental results demonstrate that GVoS
can achieve performance almost the same as the
customized systems. Meanwhile, GVoS accomplishes
remarkably higher systematic versatility and
efficiently facilitates the development of various
NDV-related applications.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2017:UVP,
author = "Xiang Wang and Liqiang Nie and Xuemeng Song and
Dongxiang Zhang and Tat-Seng Chua",
title = "Unifying Virtual and Physical Worlds: Learning Toward
Local and Global Consistency",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "4:1--4:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052774",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Event-based social networking services, such as
Meetup, are capable of linking online virtual
interactions to offline physical activities. Compared
to mono online social networking services (e.g.,
Twitter and Google+), such dual networks provide a
complete picture of users' online and offline behaviors
that more often than not are compatible and
complementary. In the light of this, we argue that
joint learning over dual networks offers us a better
way to comprehensively understand user behaviors and
their underlying organizational principles. Despite its
value, few efforts have been dedicated to jointly
considering the following factors within a unified
model: (1) local user contextualization, (2) global
structure coherence, and (3) effectiveness evaluation.
Toward this end, we propose a novel dual clustering
model for community detection over dual networks to
jointly model local consistency for a specific user and
global consistency of partitioning results across
networks. We theoretically derived its solution. In
addition, we verified our model regarding multiple
metrics from different aspects and applied it to the
application of event attendance prediction.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Shirakawa:2017:IWG,
author = "Masumi Shirakawa and Takahiro Hara and Shojiro
Nishio",
title = "{IDF} for Word {$N$}-grams",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "5:1--5:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3052775",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Inverse Document Frequency (IDF) is widely accepted
term weighting scheme whose robustness is supported by
many theoretical justifications. However, applying IDF
to word N-grams (or simply N-grams) of any length
without relying on heuristics has remained a
challenging issue. This article describes a theoretical
extension of IDF to handle N-grams. First, we elucidate
the theoretical relationship between IDF and
information distance, a universal metric defined by the
Kolmogorov complexity. Based on our understanding of
this relationship, we propose N-gram IDF, a new IDF
family that gives fair weights to words and phrases of
any length. Based only on the magnitude relation of
N-gram IDF weights, dominant N-grams among overlapping
N-grams can be determined. We also propose an efficient
method to compute the N-gram IDF weights of all N-grams
by leveraging the enhanced suffix array and wavelet
tree. Because the exact computation of N-gram IDF
provably requires significant computational cost, we
modify it to a fast approximation method that can
estimate weight errors analytically and maintain
application-level performance. Empirical evaluations
with unsupervised/supervised key term extraction and
web search query segmentation with various experimental
settings demonstrate the robustness and
language-independent nature of the proposed N-gram
IDF.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Vardasbi:2017:SSW,
author = "Ali Vardasbi and Heshaam Faili and Masoud Asadpour",
title = "{SWIM}: Stepped Weighted Shell Decomposition Influence
Maximization for Large-Scale Networks",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "6:1--6:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3072652",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "A considerable amount of research has been devoted to
the proposition of scalable algorithms for influence
maximization. A number of such scalable algorithms
exploit the community structure of the network. Besides
the community structure, real-world social networks
possess a different property, known as the layer
structure. In this article, we propose a method based
on the layer structure to maximize the influence in
huge networks. Conducting experiments on a number of
real-world networks, we will show that our method
outperforms the state-of-the-art algorithms by its time
complexity while having similar or slightly better
final influence spread. Furthermore, unlike its
predecessors, our method is able to show a high
entanglement between structure and dynamics by giving
insight on the reason why different networks have two
contrasting behaviors in their saturation. By
``saturation,'' we mean a state during the seed
selection process after which adjoining new nodes to
the initial set will have a negligible effect on
increasing the influence spread. We will demonstrate
that how our method can predict the saturation dynamics
in the networks. This prediction can be used to
identify the network structures that are more
vulnerable to the fast spread of the rumors.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yang:2017:YMP,
author = "Longqi Yang and Cheng-Kang Hsieh and Hongjian Yang and
John P. Pollak and Nicola Dell and Serge Belongie and
Curtis Cole and Deborah Estrin",
title = "{Yum-Me}: a Personalized Nutrient-Based Meal
Recommender System",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "7:1--7:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3072614",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Nutrient-based meal recommendations have the potential
to help individuals prevent or manage conditions such
as diabetes and obesity. However, learning people's
food preferences and making recommendations that
simultaneously appeal to their palate and satisfy
nutritional expectations are challenging. Existing
approaches either only learn high-level preferences or
require a prolonged learning period. We propose Yum-me,
a personalized nutrient-based meal recommender system
designed to meet individuals' nutritional expectations,
dietary restrictions, and fine-grained food
preferences. Yum-me enables a simple and accurate food
preference profiling procedure via a visual quiz-based
user interface and projects the learned profile into
the domain of nutritionally appropriate food options to
find ones that will appeal to the user. We present the
design and implementation of Yum-me and further
describe and evaluate two innovative contributions. The
first contribution is an open source state-of-the-art
food image analysis model, named FoodDist. We
demonstrate FoodDist's superior performance through
careful benchmarking and discuss its applicability
across a wide array of dietary applications. The second
contribution is a novel online learning framework that
learns food preference from itemwise and pairwise image
comparisons. We evaluate the framework in a field study
of 227 anonymous users and demonstrate that it
outperforms other baselines by a significant margin. We
further conducted an end-to-end validation of the
feasibility and effectiveness of Yum-me through a
60-person user study, in which Yum-me improves the
recommendation acceptance rate by 42.63\%.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liang:2017:SRD,
author = "Shangsong Liang and Emine Yilmaz and Hong Shen and
Maarten {De Rijke} and W. Bruce Croft",
title = "Search Result Diversification in Short Text Streams",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "8:1--8:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3057282",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We consider the problem of search result
diversification for streams of short texts.
Diversifying search results in short text streams is
more challenging than in the case of long documents, as
it is difficult to capture the latent topics of short
documents. To capture the changes of topics and the
probabilities of documents for a given query at a
specific time in a short text stream, we propose a
dynamic Dirichlet multinomial mixture topic model,
called D2M3, as well as a Gibbs sampling algorithm for
the inference. We also propose a streaming
diversification algorithm, SDA, that integrates the
information captured by D2M3 with our proposed modified
version of the PM-2 (Proportionality-based
diversification Method --- second version)
diversification algorithm. We conduct experiments on a
Twitter dataset and find that SDA statistically
significantly outperforms state-of-the-art
non-streaming retrieval methods, plain streaming
retrieval methods, as well as streaming diversification
methods that use other dynamic topic models.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Hou:2017:LAC,
author = "Lei Hou and Juanzi Li and Xiao-Li Li and Jie Tang and
Xiaofei Guo",
title = "Learning to Align Comments to News Topics",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "9:1--9:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3072591",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the rapid proliferation of social media,
increasingly more people express their opinions and
reviews (user-generated content (UGC)) on recent news
articles through various online services, such as news
portals, forums, discussion groups, and microblogs.
Clearly, identifying hot topics that users greatly care
about can improve readers' news browsing experience and
facilitate research into interaction analysis between
news and UGC. Furthermore, it is of great benefit to
public opinion monitoring and management for both
industry and government agencies. However, it is
extremely time consuming, if not impossible, to
manually examine the large amount of available social
content. In this article, we formally define the news
comment alignment problem and propose a novel framework
that: (1) automatically extracts topics from a given
news article and its associated comments, (2)
identifies and extends positive examples with different
degrees of confidence using three methods (i.e.,
hypersphere, density, and cluster chain), and (3)
completes the alignment between news sentences and
comments through a weighted-SVM classifier. Extensive
experiments show that our proposed framework
significantly outperforms state-of-the-art methods.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liang:2017:IDU,
author = "Shangsong Liang and Zhaochun Ren and Yukun Zhao and
Jun Ma and Emine Yilmaz and Maarten {De Rijke}",
title = "Inferring Dynamic User Interests in Streams of Short
Texts for User Clustering",
journal = j-TOIS,
volume = "36",
number = "1",
pages = "10:1--10:??",
month = aug,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3072606",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "User clustering has been studied from different
angles. In order to identify shared interests,
behavior-based methods consider similar browsing or
search patterns of users, whereas content-based methods
use information from the contents of the documents
visited by the users. So far, content-based user
clustering has mostly focused on static sets of
relatively long documents. Given the dynamic nature of
social media, there is a need to dynamically cluster
users in the context of streams of short texts. User
clustering in this setting is more challenging than in
the case of long documents, as it is difficult to
capture the users' dynamic topic distributions in
sparse data settings. To address this problem, we
propose a dynamic user clustering topic model (UCT).
UCT adaptively tracks changes of each user's
time-varying topic distributions based both on the
short texts the user posts during a given time period
and on previously estimated distributions. To infer
changes, we propose a Gibbs sampling algorithm where a
set of word pairs from each user is constructed for
sampling. UCT can be used in two ways: (1) as a
short-term dependency model that infers a user's
current topic distribution based on the user's topic
distributions during the previous time period only, and
(2) as a long-term dependency model that infers a
user's current topic distributions based on the user's
topic distributions during multiple time periods in the
past. The clustering results are explainable and
human-understandable, in contrast to many other
clustering algorithms. For evaluation purposes, we work
with a dataset consisting of users and tweets from each
user. Experimental results demonstrate the
effectiveness of our proposed short-term and long-term
dependency user clustering models compared to
state-of-the-art baselines.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Li:2017:ETM,
author = "Chenliang Li and Yu Duan and Haoran Wang and Zhiqian
Zhang and Aixin Sun and Zongyang Ma",
title = "Enhancing Topic Modeling for Short Texts with
Auxiliary Word Embeddings",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "11:1--11:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3091108",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Many applications require semantic understanding of
short texts, and inferring discriminative and coherent
latent topics is a critical and fundamental task in
these applications. Conventional topic models largely
rely on word co-occurrences to derive topics from a
collection of documents. However, due to the length of
each document, short texts are much more sparse in
terms of word co-occurrences. Recent studies show that
the Dirichlet Multinomial Mixture (DMM) model is
effective for topic inference over short texts by
assuming that each piece of short text is generated by
a single topic. However, DMM has two main limitations.
First, even though it seems reasonable to assume that
each short text has only one topic because of its
shortness, the definition of ``shortness'' is
subjective and the length of the short texts is dataset
dependent. That is, the single-topic assumption may be
too strong for some datasets. To address this
limitation, we propose to model the topic number as a
Poisson distribution, allowing each short text to be
associated with a small number of topics (e.g., one to
three topics). This model is named PDMM. Second, DMM
(and also PDMM) does not have access to background
knowledge (e.g., semantic relations between words) when
modeling short texts. When a human being interprets a
piece of short text, the understanding is not solely
based on its content words, but also their semantic
relations. Recent advances in word embeddings offer
effective learning of word semantic relations from a
large corpus. Such auxiliary word embeddings enable us
to address the second limitation. To this end, we
propose to promote the semantically related words under
the same topic during the sampling process, by using
the generalized P{\'o}lya urn (GPU) model. Through the
GPU model, background knowledge about word semantic
relations learned from millions of external documents
can be easily exploited to improve topic modeling for
short texts. By directly extending the PDMM model with
the GPU model, we propose two more effective topic
models for short texts, named GPU-DMM and GPU-PDMM.
Through extensive experiments on two real-world short
text collections in two languages, we demonstrate that
PDMM achieves better topic representations than
state-of-the-art models, measured by topic coherence.
The learned topic representation leads to better
accuracy in a text classification task, as an indirect
evaluation. Both GPU-DMM and GPU-PDMM further improve
topic coherence and text classification accuracy.
GPU-PDMM outperforms GPU-DMM at the price of higher
computational costs.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Voorhees:2017:URI,
author = "Ellen M. Voorhees and Daniel Samarov and Ian
Soboroff",
title = "Using Replicates in Information Retrieval Evaluation",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "12:1--12:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086701",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article explores a method for more accurately
estimating the main effect of the system in a typical
test-collection-based evaluation of information
retrieval systems, thus increasing the sensitivity of
system comparisons. Randomly partitioning the test
document collection allows for multiple tests of a
given system and topic (replicates). Bootstrap ANOVA
can use these replicates to extract system-topic
interactions-something not possible without
replicates-yielding a more precise value for the system
effect and a narrower confidence interval around that
value. Experiments using multiple TREC collections
demonstrate that removing the topic-system interactions
substantially reduces the confidence intervals around
the system effect as well as increases the number of
significant pairwise differences found. Further, the
method is robust against small changes in the number of
partitions used, against variability in the documents
that constitute the partitions, and the measure of
effectiveness used to quantify system effectiveness.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2017:FFT,
author = "Jing Zhang and Jie Tang and Cong Ma and Hanghang Tong
and Yu Jing and Juanzi Li and Walter Luyten and
Marie-Francine Moens",
title = "Fast and Flexible Top-$k$ Similarity Search on Large
Networks",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "13:1--13:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086695",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Similarity search is a fundamental problem in network
analysis and can be applied in many applications, such
as collaborator recommendation in coauthor networks,
friend recommendation in social networks, and relation
prediction in medical information networks. In this
article, we propose a sampling-based method using
random paths to estimate the similarities based on both
common neighbors and structural contexts efficiently in
very large homogeneous or heterogeneous information
networks. We give a theoretical guarantee that the
sampling size depends on the error-bound $ \epsilon $,
the confidence level $ (1 - \delta) $, and the path
length $T$ of each random walk. We perform an extensive
empirical study on a Tencent microblogging network of
1,000,000,000 edges. We show that our algorithm can
return top-$k$ similar vertices for any vertex in a
network $ 300 \times $ faster than the state-of-the-art
methods. We develop a prototype system of recommending
similar authors to demonstrate the effectiveness of our
method.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Nguyen:2017:SIS,
author = "Hung T. Nguyen and Preetam Ghosh and Michael L. Mayo
and Thang N. Dinh",
title = "Social Influence Spectrum at Scale: Near-Optimal
Solutions for Multiple Budgets at Once",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "14:1--14:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086700",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Given a social network, the Influence Maximization
(InfMax) problem seeks a seed set of $k$ people that
maximizes the expected influence for a viral marketing
campaign. However, a solution for a particular seed
size $k$ is often not enough to make an informed choice
regarding budget and cost-effectiveness. In this
article, we propose the computation of Influence
Spectrum (InfSpec), the maximum influence at each
possible seed set size $k$ within a given range $
[k_{\rm lower}, k_{\rm upper}]$, thus providing optimal
decision making for any availability of budget or
influence requirements. As none of the existing methods
for InfMax are efficient enough for the task in large
networks, we propose LISA (sub-Linear Influence
Spectrum Approximation), an efficient approximation
algorithm for InfSpec (and also InfMax) with the
best-known worst-case guarantees for billion-scale
networks. LISA returns an $ (1 - 1 / e -
\epsilon)$-approximate influence spectrum with high
probability $ (1 - \delta)$, where $ \epsilon $, $
\delta $ are precision parameters provided by users.
Using statistical decision theory, LISA has an
asymptotic optimal running time (in addition to optimal
approximation guarantee). In practice, LISA surpasses
the state-of-the-art InfMax methods, taking less than
15 minutes to process a network of 41.7 million nodes
and 1.5 billions edges.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cai:2017:ALC,
author = "Wenbin Cai and Yexun Zhang and Ya Zhang and Siyuan
Zhou and Wenquan Wang and Zhuoxiang Chen and Chris
Ding",
title = "Active Learning for Classification with Maximum Model
Change",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "15:1--15:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086820",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Most existing active learning studies focus on
designing sample selection algorithms. However, several
fundamental problems deserve investigation to provide
deep insight into active learning. In this article, we
conduct an in-depth investigation on active learning
for classification from the perspective of model
change. We derive a general active learning framework
for classification called maximum model change (MMC),
which aims at querying the influential examples. The
model change is quantified as the difference between
the model parameters before and after training with the
expanded training set. Inspired by the stochastic
gradient update rule, the gradient of the loss with
respect to a given candidate example is adopted to
approximate the model change. This framework is applied
to two popular classifiers: support vector machines and
logistic regression. We analyze the convergence
property of MMC and theoretically justify it. We
explore the connection between MMC and
uncertainty-based sampling to provide a uniform view.
In addition, we discuss its potential usability to
other learning models and show its applicability in a
wide range of applications. We validate the MMC
strategy on two kinds of benchmark datasets, the UCI
repository and ImageNet, and show that it outperforms
many state-of-the-art methods.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2017:DBE,
author = "Ming Liu and Lei Chen and Bingquan Liu and Guidong
Zheng and Xiaoming Zhang",
title = "{DBpedia}-Based Entity Linking via Greedy Search and
Adjusted {Monte Carlo} Random Walk",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "16:1--16:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086703",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Facing a large amount of entities appearing on the
web, entity linking has recently become useful. It
assigns an entity from a resource to one name mention
to help users grasp the meaning of this name mention.
Unfortunately, many possible entities can be assigned
to one name mention. Apparently, the usually
co-occurring name mentions are related and can be
considered together to determine their best
assignments. This approach is called collective entity
linking and is often conducted based on entity graph.
However, traditional collective entity linking methods
either consume much time due to the large scale of
entity graph or obtain low accuracy due to simplifying
graph. To improve both accuracy and efficiency, this
article proposes a novel collective entity linking
algorithm. It first constructs an entity graph by
connecting any two related entities, and then a
probability-based objective function is proposed on
this graph to ensure the high accuracy of the linking
result. Via this function, we convert entity linking to
the process of finding the nodes with the highest
PageRank Values. Greedy search and an adjusted Monte
Carlo random walk are proposed to fulfill this work.
Experimental results demonstrate that our algorithm
performs much better than traditional linking
methods.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Peng:2017:PMT,
author = "Min Peng and Wang Gao and Hua Wang and Yanchun Zhang
and Jiajia Huang and Qianqian Xie and Gang Hu and Gang
Tian",
title = "Parallelization of Massive Textstream Compression
Based on Compressed Sensing",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "17:1--17:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3086702",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/datacompression.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Compressing textstreams generated by social networks
can both reduce storage consumption and improve
efficiency such as fast searching. However, the
compression process is a challenge due to the large
scale of textstreams. In this article, we propose a
textstream compression framework based on compressed
sensing theory and design a series of matching parallel
procedures. The new approach uses a linear projection
technique in the textstream compression process,
achieving fast compression speed and low compression
ratio. Two processes are executed by designing
elaborated parallel procedures for efficient
compressing and decompressing of large-scale
textstreams. The decompression process is implemented
for approximate solutions of underdetermined linear
systems. Experimental results show that the new method
can efficiently achieve the compression and
decompression tasks on a large amount of text generated
by social networks.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhou:2017:MMD,
author = "Guang-You Zhou and Jimmy Xiangji Huang",
title = "Modeling and Mining Domain Shared Knowledge for
Sentiment Analysis",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "18:1--18:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3091995",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Sentiment classification aims to automatically predict
sentiment polarity (e.g., positive or negative) of user
generated sentiment data (e.g., reviews, blogs). In
real applications, these user-generated sentiment data
can span so many different domains that it is difficult
to label the training data for all of them. Therefore,
we study the problem of sentiment classification
adaptation task in this article. That is, a system is
trained to label reviews from one source domain but is
meant to be used on the target domain. One of the
biggest challenges for sentiment classification
adaptation task is how to deal with the problem when
two data distributions between the source domain and
target domain are significantly different from one
another. However, our observation is that there might
exist some domain shared knowledge among certain input
dimensions of different domains. In this article, we
present a novel method for modeling and mining the
domain shared knowledge from different sentiment review
domains via a joint non-negative matrix
factorization-based framework. In this proposed
framework, we attempt to learn the domain shared
knowledge and the domain-specific information from
different sentiment review domains with several various
regularization constraints. The advantage of the
proposed method can promote the correspondence under
the topic space between the source domain and the
target domain, which can significantly reduce the data
distribution gap across two domains. We conduct
extensive experiments on two real-world balanced data
sets from Amazon product reviews for sentence-level and
document-level binary sentiment classification.
Experimental results show that our proposed approach
significantly outperforms several strong baselines and
achieves an accuracy that is competitive with the most
well-known methods for sentiment classification
adaptation.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ferro:2017:WDA,
author = "Nicola Ferro",
title = "What Does Affect the Correlation Among Evaluation
Measures?",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "19:1--19:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3106371",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Information Retrieval (IR) is well-known for the great
number of adopted evaluation measures, with new ones
popping up more and more frequently. In this context,
correlation analysis is the tool used to study the
evaluation measures and to let us understand if two
measures rank systems similarly, if they grasp
different aspects of system performances or actually
reflect different user models, if a new measure is well
motivated or not. To this end, the two most commonly
used correlation coefficients are the Kendall's $ \tau
$ correlation and the AP correlation $ \tau_{\rm AP} $.
The goal of the article is to investigate the
properties of the tool, that is, correlation analysis,
we use to study evaluation measures. In particular, we
investigate three research questions about these two
correlation coefficients: (i) what is the effect of the
number of systems and topics? (ii) what is the effect
of removing low-performing systems? (iii) what is the
effect of the experimental collections? To answer these
research questions, we propose a methodology based on
General Linear Mixed Model (GLMM) and ANalysis Of
VAriance (ANOVA) to isolate the effects of the number
of topics, number of systems, and experimental
collections and to let us observe expected correlation
values, net from these effects, which are stable and
reliable. We learned that the effect of the number of
topics is more prominent than the effect of the number
of systems. Even if it produces different absolute
values, the effect of removing low-performing systems
does not seem to provide information substantially
different from not removing them, especially when
comparing a whole set of evaluation measures. Finally,
we found out that both document corpora and topic sets
affect the correlation among evaluation measures, the
effect of the latter being more prominent. Moreover,
there is a substantial interaction between evaluation
measures, corpora and topic sets, meaning that the
correlation between different evaluation measures can
be substantially increased or decreased depending on
the different corpora and topics at hand.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ferrante:2017:AEE,
author = "Marco Ferrante and Nicola Ferro and Maria Maistro",
title = "{AWARE}: Exploiting Evaluation Measures to Combine
Multiple Assessors",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "20:1--20:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3110217",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We propose the Assessor-driven Weighted Averages for
Retrieval Evaluation (AWARE) probabilistic framework, a
novel methodology for dealing with multiple crowd
assessors that may be contradictory and/or noisy. By
modeling relevance judgements and crowd assessors as
sources of uncertainty, AWARE takes the expectation of
a generic performance measure, like Average Precision,
composed with these random variables. In this way, it
approaches the problem of aggregating different crowd
assessors from a new perspective, that is, directly
combining the performance measures computed on the
ground truth generated by the crowd assessors instead
of adopting some classification technique to merge the
labels produced by them. We propose several
unsupervised estimators that instantiate the AWARE
framework and we compare them with state-of-the-art
approaches, that is,Majoriity Vote and Expectation
Maximization, on TREC collections. We found that AWARE
approaches improve in terms of their capability of
correctly ranking systems and predicting their actual
performance scores.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bai:2017:ULI,
author = "Xiao Bai and Ioannis Arapakis and B. Barla Cambazoglu
and Ana Freire",
title = "Understanding and Leveraging the Impact of Response
Latency on User Behaviour in {Web} Search",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "21:1--21:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3106372",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The interplay between the response latency of web
search systems and users' search experience has only
recently started to attract research attention, despite
the important implications of response latency on
monetisation of such systems. In this work, we carry
out two complementary studies to investigate the impact
of response latency on users' searching behaviour in
web search engines. We first conduct a controlled user
study to investigate the sensitivity of users to
increasing delays in response latency. This study shows
that the users of a fast search system are more
sensitive to delays than the users of a slow search
system. Moreover, the study finds that users are more
likely to notice the response latency delays beyond a
certain latency threshold, their search experience
potentially being affected. We then analyse a large
number of search queries obtained from Yahoo Web Search
to investigate the impact of response latency on users'
click behaviour. This analysis demonstrates the
significant change in click behaviour as the response
latency increases. We also find that certain user,
context, and query attributes play a role in the way
increasing response latency affects the click
behaviour. To demonstrate a possible use case for our
findings, we devise a machine-learning framework that
leverages the latency impact, together with other
features, to predict whether a user will issue any
clicks on web search results. As a further extension of
this use case, we investigate whether this
machine-learning framework can be exploited to help
search engines reduce their energy consumption during
query processing.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Shi:2017:LRB,
author = "Lei Shi and Wayne Xin Zhao and Yi-Dong Shen",
title = "Local Representative-Based Matrix Factorization for
Cold-Start Recommendation",
journal = j-TOIS,
volume = "36",
number = "2",
pages = "22:1--22:??",
month = sep,
year = "2017",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3108148",
ISSN = "1046-8188",
bibdate = "Tue Jan 16 07:16:47 MST 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Cold-start recommendation is one of the most
challenging problems in recommender systems. An
important approach to cold-start recommendation is to
conduct an interview for new users, called the
interview-based approach. Among the interview-based
methods, Representative-Based Matrix Factorization
(RBMF) [24] provides an effective solution with
appealing merits: it represents users over selected
representative items, which makes the recommendations
highly intuitive and interpretable. However, RBMF only
utilizes a global set of representative items to model
all users. Such a representation is somehow too strict
and may not be flexible enough to capture varying
users' interests. To address this problem, we propose a
novel interview-based model to dynamically create
meaningful user groups using decision trees and then
select local representative items for different groups.
A two-round interview is performed for a new user. In
the first round, $ l_1 $ global questions are issued
for group division, while in the second round, $ l_2 $
local-group-specific questions are given to derive
local representation. We collect the feedback on the $
(l_1 + l_2) $ items to learn the user representations.
By putting these steps together, we develop a joint
optimization model, named local representative-based
matrix factorization, for new user recommendations.
Extensive experiments on three public datasets have
demonstrated the effectiveness of the proposed model
compared with several competitive baselines.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Arampatzis:2018:SPI,
author = "Avi Arampatzis and Georgios Kalamatianos",
title = "Suggesting Points-of-Interest via Content-Based,
Collaborative, and Hybrid Fusion Methods in Mobile
Devices",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "23:1--23:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3125620",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Recommending venues or points-of-interest (POIs) is a
hot topic in recent years, especially for tourism
applications and mobile users. We propose and evaluate
several suggestion methods, taking an effectiveness,
feasibility, efficiency, and privacy perspective. The
task is addressed by two content-based methods (a
Weighted kNN classifier and a Rated Rocchio
personalized query), Collaborative Filtering methods,
as well as several (rank-based or rating-based) methods
of merging results of different systems. Effectiveness
is evaluated on two standard benchmark datasets,
provided and used by TREC's Contextual Suggestion
Tracks in 2015 and 2016. First, we enrich these
datasets with more information on venues, collected
from web services like Foursquare and Yelp; we make
this extra data available for future experimentation.
Then, we find that the content-based methods provide
state-of-the-art effectiveness, the collaborative
filtering variants mostly suffer from data sparsity
problems in the current datasets, and the merging
methods further improve results by mainly promoting the
first relevant suggestion. Concerning mobile
feasibility, efficiency, and user privacy, the
content-based methods, especially Rated Rocchio, are
the best. Collaborative filtering has the worst
efficiency and privacy leaks. Our findings can be very
useful for developing effective and efficient
operational systems, respecting user privacy. Last, our
experiments indicate that better benchmark datasets
would be welcome, and the use of additional evaluation
measures-more sensitive in recall-is recommended.",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhao:2018:TEF,
author = "Jingwen Zhao and Yunjun Gao and Gang Chen and Rui
Chen",
title = "Towards Efficient Framework for Time-Aware Spatial
Keyword Queries on Road Networks",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "24:1--24:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3143802",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The spatial keyword query takes as inputs a query
location and a set of query keywords and returns the
answer objects by considering both their spatial
distances to the query location and textual similarity
with the query keywords. However, temporal information
plays an important role in the spatial keyword query
(where there is, to our knowledge, no prior work
considering temporal information of the objects), since
objects are not always valid. For instance, visitors
may plan their trips according to the opening hours of
attractions. Moreover, in real-life applications,
objects are located on a predefined road network, and
the spatial proximity of two objects is measured by the
shortest path distance or travelling time between them.
In this article, we study the problem of time-aware
spatial keyword (TSK) query, which assumes that objects
are located on the road network, and finds the k
objects satisfying users' spatio-temporal description
and textual constraint. We first present the pruning
strategy and algorithm based on an existing index.
Then, we design an efficient index structure called TG
index and propose several algorithms using the TG index
that can prune the search space with both
spatio-temporal and textual information simultaneously.
Further, we show that the TG index technique can also
be applied to improve the performance of time-travel
text search and spatial keyword query. Extensive
experiments using both real and synthetic datasets
demonstrate the effectiveness and efficiency of the
presented index and algorithms.",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{McCreadie:2018:EDE,
author = "Richard McCreadie and Rodrygo L. T. Santos and Craig
Macdonald and Iadh Ounis",
title = "Explicit Diversification of Event Aspects for Temporal
Summarization",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "25:1--25:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3158671",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "During major events, such as emergencies and
disasters, a large volume of information is reported on
newswire and social media platforms. Temporal
summarization (TS) approaches are used to automatically
produce concise overviews of such events by extracting
text snippets from related articles over time. Current
TS approaches rely on a combination of event relevance
and textual novelty for snippet selection. However, for
events that span multiple days, textual novelty is
often a poor criterion for selecting snippets, since
many snippets are textually unique but are semantically
redundant or non-informative. In this article, we
propose a framework for the diversification of snippets
using explicit event aspects, building on recent works
in search result diversification. In particular, we
first propose two techniques to identify explicit
aspects that a user might want to see covered in a
summary for different types of event. We then extend a
state-of-the-art explicit diversification framework to
maximize the coverage of these aspects when selecting
summary snippets for unseen events. Through
experimentation over the TREC TS 2013, 2014, and 2015
datasets, we show that explicit diversification for
temporal summarization significantly outperforms
classical novelty-based diversification, as the use of
explicit event aspects reduces the amount of redundant
and off-topic snippets returned, while also increasing
summary timeliness.",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chong:2018:EUV,
author = "Wen-Haw Chong and Ee-Peng Lim",
title = "Exploiting User and Venue Characteristics for
Fine-Grained Tweet Geolocation",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "26:1--26:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3156667",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Which venue is a tweet posted from? We call this a
fine-grained geolocation problem. Given an observed
tweet, the task is to infer its discrete posting venue,
e.g., a specific restaurant. This recovers the venue
context and differs from prior work, which geolocats
tweets to location coordinates or cities/neighborhoods.
First, we conduct empirical analysis to uncover venue
and user characteristics for improving geolocation. For
venues, we observe spatial homophily, in which venues
near each other have more similar tweet content (i.e.,
text representations) compared to venues further apart.
For users, we observe that they are spatially focused
and more likely to visit venues near their previous
visits. We also find that a substantial proportion of
users post one or more geocoded tweet(s), thus
providing their location history data. We then propose
geolocation models that exploit spatial homophily and
spatial focus characteristics plus posting time
information. Our models rank candidate venues of test
tweets such that the actual posting venue is ranked
high. To better tune model parameters, we introduce a
learning-to-rank framework. Our best model
significantly outperforms state-of-the-art baselines.
Furthermore, we show that tweets without any
location-indicative words can be geolocated
meaningfully as well.",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhao:2018:ALT,
author = "Wayne Xin Zhao and Wenhui Zhang and Yulan He and Xing
Xie and Ji-Rong Wen",
title = "Automatically Learning Topics and Difficulty Levels of
Problems in Online Judge Systems",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "27:1--27:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3158670",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Online Judge (OJ) systems have been widely used in
many areas, including programming, mathematical
problems solving, and job interviews. Unlike other
online learning systems, such as Massive Open Online
Course, most OJ systems are designed for self-directed
learning without the intervention of teachers. Also, in
most OJ systems, problems are simply listed in volumes
and there is no clear organization of them by topics or
difficulty levels. As such, problems in the same volume
are mixed in terms of topics or difficulty levels. By
analyzing large-scale users' learning traces, we
observe that there are two major learning modes (or
patterns). Users either practice problems in a
sequential manner from the same volume regardless of
their topics or they attempt problems about the same
topic, which may spread across multiple volumes. Our
observation is consistent with the findings in classic
educational psychology. Based on our observation, we
propose a novel two-mode Markov topic model to
automatically detect the topics of online problems by
jointly characterizing the two learning modes. For
further predicting the difficulty level of online
problems, we propose a competition-based expertise
model using the learned topic information. Extensive
experiments on three large OJ datasets have
demonstrated the effectiveness of our approach in three
different tasks, including skill topic extraction,
expertise competition prediction and problem
recommendation.",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Levi:2018:SCP,
author = "Or Levi and Ido Guy and Fiana Raiber and Oren
Kurland",
title = "Selective Cluster Presentation on the Search Results
Page",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "28:1--28:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3158672",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Web search engines present, for some queries, a
cluster of results from the same specialized domain
(``vertical'') on the search results page (SERP). We
introduce a comprehensive analysis of the presentation
of such clusters from seven different verticals based
on the logs of a commercial Web search engine. This
analysis reveals several unique characteristics-such as
size, rank, and clicks-of result clusters from
community question-and-answer websites. The study of
properties of this result cluster-specifically as part
of the SERP-has received little attention in previous
work. Our analysis also motivates the pursuit of a
long-standing challenge in ad hoc retrieval, namely,
selective cluster retrieval. In our setting, the
specific challenge is to select for presentation the
documents most highly ranked either by a cluster-based
approach (those in the top-retrieved cluster) or by a
document-based approach. We address this classification
task by representing queries with features based on
those utilized for ranking the clusters,
query-performance predictors, and properties of the
document-clustering structure. Empirical evaluation
performed with TREC data shows that our approach
outperforms a recently proposed state-of-the-art
cluster-based document-retrieval method as well as
state-of-the-art document-retrieval methods that do not
account for inter-document similarities.",
acknowledgement = ack-nhfb,
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liao:2018:JMP,
author = "Yi Liao and Wai Lam and Lidong Bing and Xin Shen",
title = "Joint Modeling of Participant Influence and Latent
Topics for Recommendation in Event-based Social
Networks",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "29:1--29:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3183712",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Event-based social networks (EBSNs) are becoming
popular in recent years. Users can publish a planned
event on an EBSN website, calling for other users to
participate in the event. When a user is making a
decision on whether to participate in an event in
EBSNs, one aspect for consideration is existing
participants defined as users who have agreed to join
this event. Existing participants of the event may
affect the decision of the user, to which we refer as
participant influence. However, participant influence
is not well studied by previous works. In this article,
we propose an event recommendation model that considers
participant influence, and exploits the influence of
existing participants on the decisions of new
participants based on Poisson factorization. The effect
of participant influence is associated with the target
event, the host group of the event, and the location of
the event. Furthermore, our proposed model can extract
latent event topics from event text descriptions, and
characterize events, groups, and locations by
distributions of event topics. Associations between
latent event topics and participant influence are
exploited for improving event recommendation. Besides
making event recommendation, the proposed model is able
to reveal the semantic properties of the participant
influence between two users semantically. We have
conducted extensive experiments on some datasets
extracted from a real-world EBSN. Our proposed model
achieves superior event recommendation performance over
several state-of-the-art models. The results
demonstrate that the consideration of participant
influence can improve event recommendation.",
acknowledgement = ack-nhfb,
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Guy:2018:CVS,
author = "Ido Guy",
title = "The Characteristics of Voice Search: Comparing Spoken
with Typed-in Mobile {Web} Search Queries",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "30:1--30:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3182163",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The growing popularity of mobile search and the
advancement in voice recognition technologies have
opened the door for web search users to speak their
queries rather than type them. While this kind of voice
search is still in its infancy, it is gradually
becoming more widespread. In this article, we report a
comprehensive voice search query log analysis of a
commercial web search engine's mobile application. We
compare voice and text search by various aspects, with
special focus on the semantic and syntactic
characteristics of the queries. Our analysis suggests
that voice queries focus more on audio-visual content
and question answering and less on social networking
and adult domains. In addition, voice queries are more
commonly submitted on the go. We also conduct an
empirical evaluation showing that the language of voice
queries is closer to natural language than the language
of text queries. Our analysis points out further
differences between voice and text search. We discuss
the implications of these differences for the design of
future voice-enabled web search tools.",
acknowledgement = ack-nhfb,
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Guo:2018:CIP,
author = "Long Guo and Dongxiang Zhang and Yuan Wang and Huayu
Wu and Bin Cui and Kian-Lee Tan",
title = "{CO} 2: Inferring Personal Interests From Raw
Footprints by Connecting the Offline World with the
Online World",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "31:1--31:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3182164",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "User-generated trajectories (UGTs), such as travel
records from bus companies, capture rich information of
human mobility in the offline world. However, some
interesting applications of these raw footprints have
not been exploited well due to the lack of textual
information to infer the subject's personal interests.
Although there is rich semantic information contained
in the spatial- and temporal-aware user-generated
contents (STUGC) published in the online world, such as
Twitter, less effort has been made to utilize this
information to facilitate the interest discovery
process. In this article, we design an effective
probabilistic framework named CO$^2$ to connect the
offline world with the online world in order to
discover users' interests directly from their raw
footprints in UGT. CO$^2$ first infers trip intentions
by utilizing the semantic information in STUGC and then
discovers user interests by aggregating the intentions.
To evaluate the effectiveness of CO$^2$, we use two
large-scale real-world datasets as a case study and
further conduct a questionnaire survey to show the
superior performance of CO$^2$.",
acknowledgement = ack-nhfb,
articleno = "31",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Yang:2018:ULP,
author = "Jing Yang and Carsten Eickhoff",
title = "Unsupervised Learning of Parsimonious General-Purpose
Embeddings for User and Location Modeling",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "32:1--32:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3182165",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Many social network applications depend on robust
representations of spatio-temporal data. In this work,
we present an embedding model based on feed-forward
neural networks which transforms social media check-ins
into dense feature vectors encoding geographic,
temporal, and functional aspects for modeling places,
neighborhoods, and users. We employ the embedding model
in a variety of applications including location
recommendation, urban functional zone study, and crime
prediction. For location recommendation, we propose a
Spatio-Temporal Embedding Similarity algorithm (STES)
based on the embedding model. In a range of experiments
on real life data collected from Foursquare, we
demonstrate our model's effectiveness at characterizing
places and people and its applicability in
aforementioned problem domains. Finally, we select
eight major cities around the globe and verify the
robustness and generality of our model by porting
pre-trained models from one city to another, thereby
alleviating the need for costly local training.",
acknowledgement = ack-nhfb,
articleno = "32",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lian:2018:GSL,
author = "Defu Lian and Kai Zheng and Yong Ge and Longbing Cao
and Enhong Chen and Xing Xie",
title = "{GeoMF++}: Scalable Location Recommendation via Joint
Geographical Modeling and Matrix Factorization",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "33:1--33:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3182166",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Location recommendation is an important means to help
people discover attractive locations. However, extreme
sparsity of user-location matrices leads to a severe
challenge, so it is necessary to take implicit feedback
characteristics of user mobility data into account and
leverage the location's spatial information. To this
end, based on previously developed GeoMF, we propose a
scalable and flexible framework, dubbed GeoMF++, for
joint geographical modeling and implicit feedback-based
matrix factorization. We then develop an efficient
optimization algorithm for parameter learning, which
scales linearly with data size and the total number of
neighbor grids of all locations. GeoMF++ can be well
explained from two perspectives. First, it subsumes
two-dimensional kernel density estimation so that it
captures spatial clustering phenomenon in user mobility
data; Second, it is strongly connected with widely used
neighbor additive models, graph Laplacian regularized
models, and collective matrix factorization. Finally,
we extensively evaluate GeoMF++ on two large-scale LBSN
datasets. The experimental results show that GeoMF++
consistently outperforms the state-of-the-art and other
competing baselines on both datasets in terms of NDCG
and Recall. Besides, the efficiency studies show that
GeoMF++ is much more scalable with the increase of data
size and the dimension of latent space.",
acknowledgement = ack-nhfb,
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tan:2018:QTQ,
author = "Jiwei Tan and Xiaojun Wan and Hui Liu and Jianguo
Xiao",
title = "{QuoteRec}: Toward Quote Recommendation for Writing",
journal = j-TOIS,
volume = "36",
number = "3",
pages = "34:1--34:??",
month = apr,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3183370",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Quote is a language phenomenon of transcribing the
statement of someone else, such as a proverb and a
famous saying. An appropriate usage of quote usually
equips the expression with more elegance and
credibility. However, there are times when we are eager
to stress our idea by citing a quote, while nothing
relevant comes to mind. Therefore, it is exciting to
have a recommender system which provides quote
recommendations while we are writing. This article
extends previous study of quote recommendation, the
task that recommends the appropriate quote according to
the context (i.e., the content occurring before and
after the quote). In this article, a quote recommender
system called QuoteRec is presented to tackle the task.
We investigate two models to learn the vector
representations of quotes and contexts, and then rank
the candidate quotes based on the representations. The
first model learns the quote representation according
to the contexts of a quote. The second model is an
extension of the neural network model in previous
study, which learns the representation of a quote by
concerning both its content and contexts. Experimental
results demonstrate the effectiveness of the two models
in learning the semantic representations of quotes, and
the neural network model achieves state-of-the-art
results on the quote recommendation task.",
acknowledgement = ack-nhfb,
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Nelissen:2018:STU,
author = "Klaas Nelissen and Monique Snoeck and Seppe {Vanden
Broucke} and Bart Baesens",
title = "Swipe and Tell: Using Implicit Feedback to Predict
User Engagement on Tablets",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "35:1--35:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3185153",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "When content consumers explicitly judge content
positively, we consider them to be engaged.
Unfortunately, explicit user evaluations are difficult
to collect, as they require user effort. Therefore, we
propose to use device interactions as implicit feedback
to detect engagement. We assess the usefulness of swipe
interactions on tablets for predicting engagement and
make the comparison with using traditional features
based on time spent. We gathered two unique datasets of
more than 250,000 swipes, 100,000 unique article
visits, and over 35,000 explicitly judged news articles
by modifying two commonly used tablet apps of two
newspapers. We tracked all device interactions of 407
experiment participants during one month of habitual
news reading. We employed a behavioral metric as a
proxy for engagement, because our analysis needed to be
scalable to many users, and scanning behavior required
us to allow users to indicate engagement quickly. We
point out the importance of taking into account content
ordering, report the most predictive features, zoom in
on briefly read content and on the most frequently read
articles. Our findings demonstrate that fine-grained
tablet interactions are useful indicators of engagement
for newsreaders on tablets. The best features
successfully combine both time-based aspects and swipe
interactions.",
acknowledgement = ack-nhfb,
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Goldberg:2018:FID,
author = "David Goldberg and Andrew Trotman and Xiao Wang and
Wei Min and Zongru Wan",
title = "Further Insights on Drawing Sound Conclusions from
Noisy Judgments",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "36:1--36:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3186195",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The effectiveness of a search engine is typically
evaluated using hand-labeled datasets, where the labels
indicate the relevance of documents to queries. Often
the number of labels needed is too large to be created
by the best annotators, and so less expensive labels
(e.g., from crowdsourcing) are used. This introduces
errors in the labels, and thus errors in standard
effectiveness metrics (such as P@k and DCG). These
errors must be taken into consideration when using the
metrics. Previous work has approached assessor error by
taking aggregates over multiple inexpensive assessors.
We take a different approach and introduce equations
and algorithms that can adjust the metrics to the
values they would have had if there were no annotation
errors. This is especially important when two search
engines are compared on their metrics. We give examples
where one engine appeared to be statistically
significantly better than the other, but the effect
disappeared after the metrics were corrected for
annotation error. In other words, the evidence
supporting a statistical difference was illusory and
caused by a failure to account for annotation error.",
acknowledgement = ack-nhfb,
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Bekhet:2018:ISB,
author = "Saddam Bekhet and Amr Ahmed",
title = "An Integrated Signature-Based Framework for Efficient
Visual Similarity Detection and Measurement in Video
Shots",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "37:1--37:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3190784",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article presents a framework for speedy video
matching and retrieval through detection and
measurement of visual similarity. The framework's
efficiency stems from its power to encode a given shot
content into a compact fixed-length signature that
helps in robust real-time matching. Separate scene and
motion signatures are developed and fused together to
fully represent and match respective video shots. Scene
information is captured through the Statistical
Dominant Color Profile (SDCP), while motion information
is captured through a graph-based signature called the
Dominant Color Graph Profile (DCGP). The SDCP is a
fixed-length compact signature that statistically
encodes the colors' spatiotemporal patterns across
video frames. The DCGP is a fixed-length signature that
records and tracks the gray levels across subsampled
video frames, where the graph structural properties are
used to extract the signature values. Finally, the
overall video signature is generated by fusing the
individual scene and motion signatures. The
signature-based aspect of the proposed framework is the
key to its high matching speed (> 2000 fps) compared to
current techniques that rely on exhaustive
processing. To maximize the benefit of the framework,
compressed-domain videos are utilized as a case study
following their wide availability. However, the
framework avoids full video decompression and operates
on tiny frames rather than full-size decompressed
frames. Experiments on various standard and challenging
dataset groups show the framework's robust performance
in terms of both retrieval and computational
performance.",
acknowledgement = ack-nhfb,
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{VanGysel:2018:NVS,
author = "Christophe {Van Gysel} and Maarten de Rijke and
Evangelos Kanoulas",
title = "Neural Vector Spaces for Unsupervised Information
Retrieval",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "38:1--38:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3196826",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We propose the Neural Vector Space Model (NVSM), a
method that learns representations of documents in an
unsupervised manner for news article retrieval. In the
NVSM paradigm, we learn low-dimensional representations
of words and documents from scratch using gradient
descent and rank documents according to their
similarity with query representations that are composed
from word representations. We show that NVSM performs
better at document ranking than existing latent
semantic vector space methods. The addition of NVSM to
a mixture of lexical language models and a
state-of-the-art baseline vector space model yields a
statistically significant increase in retrieval
effectiveness. Consequently, NVSM adds a complementary
relevance signal. Next to semantic matching, we find
that NVSM performs well in cases where lexical matching
is needed. NVSM learns a notion of term specificity
directly from the document collection without feature
engineering. We also show that NVSM learns regularities
related to Luhn significance. Finally, we give advice
on how to deploy NVSM in situations where model
selection (e.g., cross-validation) is infeasible. We
find that an unsupervised ensemble of multiple models
trained with different hyperparameter values performs
better than a single cross-validated model. Therefore,
NVSM can safely be used for ranking documents without
supervised relevance judgments.",
acknowledgement = ack-nhfb,
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ren:2018:SRE,
author = "Pengjie Ren and Zhumin Chen and Zhaochun Ren and Furu
Wei and Liqiang Nie and Jun Ma and Maarten de Rijke",
title = "Sentence Relations for Extractive Summarization with
Deep Neural Networks",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "39:1--39:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3200864",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Sentence regression is a type of extractive
summarization that achieves state-of-the-art
performance and is commonly used in practical systems.
The most challenging task within the sentence
regression framework is to identify discriminative
features to represent each sentence. In this article,
we study the use of sentence relations, e.g.,
Contextual Sentence Relations (CSR), Title Sentence
Relations (TSR), and Query Sentence Relations (QSR), so
as to improve the performance of sentence regression.
CSR, TSR, and QSR refer to the relations between a main
body sentence and its local context, its document
title, and a given query, respectively. We propose a
deep neural network model, Sentence Relation-based
Summarization (SRSum), that consists of five
sub-models, PriorSum, CSRSum, TSRSum, QSRSum, and
SFSum. PriorSum encodes the latent semantic meaning of
a sentence using a bi-gram convolutional neural
network. SFSum encodes the surface information of a
sentence, e.g., sentence length, sentence position, and
so on. CSRSum, TSRSum, and QSRSum are three sentence
relation sub-models corresponding to CSR, TSR, and QSR,
respectively. CSRSum evaluates the ability of each
sentence to summarize its local contexts. Specifically,
CSRSum applies a CSR-based word-level and
sentence-level attention mechanism to simulate the
context-aware reading of a human reader, where words
and sentences that have anaphoric relations or local
summarization abilities are easily remembered and paid
attention to. TSRSum evaluates the semantic closeness
of each sentence with respect to its title, which
usually reflects the main ideas of a document. TSRSum
applies a TSR-based attention mechanism to simulate
people's reading ability with the main idea (title) in
mind. QSRSum evaluates the relevance of each sentence
with given queries for the query-focused summarization.
QSRSum applies a QSR-based attention mechanism to
simulate the attentive reading of a human reader with
some queries in mind. The mechanism can recognize which
parts of the given queries are more likely answered by
a sentence under consideration. Finally as a whole,
SRSum automatically learns useful latent features by
jointly learning representations of query sentences,
content sentences, and title sentences as well as their
relations. We conduct extensive experiments on six
benchmark datasets, including generic multi-document
summarization and query-focused multi-document
summarization. On both tasks, SRSum achieves comparable
or superior performance compared with state-of-the-art
approaches in terms of multiple ROUGE metrics.",
acknowledgement = ack-nhfb,
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Middleton:2018:LES,
author = "Stuart E. Middleton and Giorgos Kordopatis-Zilos and
Symeon Papadopoulos and Yiannis Kompatsiaris",
title = "Location Extraction from Social Media: Geoparsing,
Location Disambiguation, and Geotagging",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "40:1--40:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3202662",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Location extraction, also called ``toponym
extraction,'' is a field covering geoparsing,
extracting spatial representations from location
mentions in text, and geotagging, assigning spatial
coordinates to content items. This article evaluates
five ``best-of-class'' location extraction algorithms.
We develop a geoparsing algorithm using an
OpenStreetMap database, and a geotagging algorithm
using a language model constructed from social media
tags and multiple gazetteers. Third-party work
evaluated includes a DBpedia-based entity recognition
and disambiguation approach, a named entity recognition
and Geonames gazetteer approach, and a Google Geocoder
API approach. We perform two quantitative benchmark
evaluations, one geoparsing tweets and one geotagging
Flickr posts, to compare all approaches. We also
perform a qualitative evaluation recalling top N
location mentions from tweets during major news events.
The OpenStreetMap approach was best (F1 0.90+) for
geoparsing English, and the language model approach was
best (F1 0.66) for Turkish. The language model was best
(F1@1km 0.49) for the geotagging evaluation. The map
database was best (R@20 0.60+) in the qualitative
evaluation. We report on strengths, weaknesses, and a
detailed failure analysis for the approaches and
suggest concrete areas for further research.",
acknowledgement = ack-nhfb,
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Arguello:2018:FIU,
author = "Jaime Arguello and Bogeum Choi and Robert Capra",
title = "Factors Influencing Users' Information Requests:
Medium, Target, and Extra-Topical Dimension",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "41:1--41:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3209624",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We report on a crowdsourced study that investigated
how two factors influence the way people formulate
information requests. Our first factor, medium,
considers whether the request is produced using text or
voice. Our second factor, target, considers whether the
request is intended for a search engine or a human
intermediary (i.e., someone who will search on the
user's behalf). In particular, we study how these two
factors influence the way people formulate requests in
situations where the information need has a specific
type of extra-topical dimension (i.e., a type of
constraint that is independent from the information
need's topic). We focus on six extra-topical
dimensions: (1) domain knowledge, (2) viewpoint, (3)
experiential, (4) venue location, (5) source location,
and (6) temporal. The extra-topical dimension was
manipulated by giving participants carefully
constructed search tasks. We analyzed a large number of
information requests produced by study participants,
and address three research questions. We study the
effects of our two factors (medium and target) on (RQ1)
participants' perceptions about their own information
requests, (RQ2) the different characteristics of their
information requests (e.g., natural language structure,
retrieval performance), and (RQ3) participants'
strategies for requesting information when the search
task has a specific type of extra-topical dimension.
Our results found that both factors influenced
participants' perceptions about their own information
requests, the characteristics of participants'
requests, and the strategies adopted by participants to
request information matching the extra-topical
dimension. Our results have implications for future
research on methods that can harness (rather than
ignore) extra-topical query terms to retrieve relevant
information.",
acknowledgement = ack-nhfb,
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Mao:2018:HDD,
author = "Jiaxin Mao and Yiqun Liu and Noriko Kando and Min
Zhang and Shaoping Ma",
title = "How Does Domain Expertise Affect Users' Search
Interaction and Outcome in Exploratory Search?",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "42:1--42:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3223045",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "People often conduct exploratory search to explore
unfamiliar information space and learn new knowledge.
While supporting the highly dynamic and interactive
exploratory search is still challenging for the search
system, we want to investigate which factors can make
the exploratory search successful and satisfying from
the user's perspective. Previous research suggests that
domain experts have different search strategies and are
more successful in finding domain-specific information,
but how the domain expertise level will influence
users' interaction and search outcomes in exploratory
search, especially in different knowledge domains, is
still unclear. In this work, via a carefully designed
user study that involves 30 participants, we
investigate the influence of domain expertise levels on
the interaction and outcome of exploratory search in
three different domains: environment, medicine, and
politics. We record participants' search behaviors,
including their explicit feedback and eye fixation
sequences, in a laboratory setting. With this dataset,
we identify both domain-independent and
domain-dependent effects on user behaviors and search
outcomes. Our results extend existing research on the
effect of domain expertise in search and suggest
different strategies for exploiting domain expertise to
support exploratory search in different knowledge
domains.",
acknowledgement = ack-nhfb,
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2018:LAI,
author = "Yanhao Wang and Yuchen Li and Ju Fan and Kian-Lee
Tan",
title = "Location-aware Influence Maximization over Dynamic
Social Streams",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "43:1--43:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3230871",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Influence maximization (IM), which selects a set of k
seed users (a.k.a., a seed set ) to maximize the
influence spread over a social network, is a
fundamental problem in a wide range of applications.
However, most existing IM algorithms are static and
location-unaware. They fail to provide high-quality
seed sets efficiently when the social network evolves
rapidly and IM queries are location-aware. In this
article, we first define two IM queries, namely Stream
Influence Maximization (SIM) and Location-aware SIM
(LSIM), to track influential users over social streams.
Technically, SIM adopts the sliding window model and
maintains a seed set with the maximum influence value
collectively over the most recent social actions. LSIM
further considers social actions are associated with
geo-tags and identifies a seed set that maximizes the
influence value in a query region over a location-aware
social stream. Then, we propose the Sparse Influential
Checkpoints (SIC) framework for efficient SIM query
processing. SIC maintains a sequence of influential
checkpoints over the sliding window and each checkpoint
maintains a partial solution for SIM in an append-only
substream of social actions. Theoretically, SIC keeps a
logarithmic number of checkpoints w.r.t. the size of
the sliding window and always returns an approximate
solution from one of the checkpoint for the SIM query
at any time. Furthermore, we propose the Location-based
SIC (LSIC) framework and its improved version LSIC$^+$,
both of which process LSIM queries by integrating the
SIC framework with a Quadtree spatial index. LSIC can
provide approximate solutions for both ad hoc and
continuous LSIM queries in real time, while LSIC$^+$
further improves the solution quality of LSIC.
Experimental results on real-world datasets demonstrate
the effectiveness and efficiency of the proposed
frameworks against the state-of-the-art IM
algorithms.",
acknowledgement = ack-nhfb,
articleno = "43",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ruotsalo:2018:IIM,
author = "Tuukka Ruotsalo and Jaakko Peltonen and Manuel J. A.
Eugster and Dorota G{\l}owacka and Patrik Flor{\'e}en
and Petri Myllym{\"a}ki and Giulio Jacucci and Samuel
Kaski",
title = "Interactive Intent Modeling for Exploratory Search",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "44:1--44:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3231593",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Exploratory search requires the system to assist the
user in comprehending the information space and
expressing evolving search intents for iterative
exploration and retrieval of information. We introduce
interactive intent modeling, a technique that models a
user's evolving search intents and visualizes them as
keywords for interaction. The user can provide feedback
on the keywords, from which the system learns and
visualizes an improved intent estimate and retrieves
information. We report experiments comparing variants
of a system implementing interactive intent modeling to
a control system. Data comprising search logs,
interaction logs, essay answers, and questionnaires
indicate significant improvements in task performance,
information retrieval performance over the session,
information comprehension performance, and user
experience. The improvements in retrieval effectiveness
can be attributed to the intent modeling and the effect
on users' task performance, breadth of information
comprehension, and user experience are shown to be
dependent on a richer visualization. Our results
demonstrate the utility of combining interactive
modeling of search intentions with interactive
visualization of the models that can benefit both
directing the exploratory search process and making
sense of the information space. Our findings can help
design personalized systems that support exploratory
information seeking and discovery of novel
information.",
acknowledgement = ack-nhfb,
articleno = "44",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Aliannejadi:2018:PCA,
author = "Mohammad Aliannejadi and Fabio Crestani",
title = "Personalized Context-Aware Point of Interest
Recommendation",
journal = j-TOIS,
volume = "36",
number = "4",
pages = "45:1--45:??",
month = oct,
year = "2018",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3231933",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:51:59 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Personalized recommendation of Points of Interest
(POIs) plays a key role in satisfying users on
Location-Based Social Networks (LBSNs). In this
article, we propose a probabilistic model to find the
mapping between user-annotated tags and locations'
taste keywords. Furthermore, we introduce a dataset on
locations' contextual appropriateness and demonstrate
its usefulness in predicting the contextual relevance
of locations. We investigate four approaches to use our
proposed mapping for addressing the data sparsity
problem: one model to reduce the dimensionality of
location taste keywords and three models to predict
user tags for a new location. Moreover, we present
different scores calculated from multiple LBSNs and
show how we incorporate new information from the
mapping into a POI recommendation approach. Then, the
computed scores are integrated using learning to rank
techniques. The experiments on two TREC datasets show
the effectiveness of our approach, beating
state-of-the-art methods.",
acknowledgement = ack-nhfb,
articleno = "45",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Mic:2019:BSS,
author = "Vladimir Mic and David Novak and Pavel Zezula",
title = "Binary Sketches for Secondary Filtering",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3231936",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "This article addresses the problem of matching the
most similar data objects to a given query object. We
adopt a generic model of similarity that involves the
domain of objects and metric distance functions only.
We examine the case of a large dataset in a complex
data space, which makes this problem inherently
difficult. Many indexing and searching approaches have
been proposed, but they have often failed to
efficiently prune complex search spaces and access
large portions of the dataset when evaluating queries.
We propose an approach to enhancing the existing search
techniques to significantly reduce the number of
accessed data objects while preserving the quality of
the search results. In particular, we extend each data
object with its sketch, a short binary string in
Hamming space. These sketches approximate the
similarity relationships in the original search space,
and we use them to filter out non-relevant objects not
pruned by the original search technique. We provide a
probabilistic model to tune the parameters of the
sketch-based filtering separately for each query
object. Experiments conducted with different similarity
search techniques and real-life datasets demonstrate
that the secondary filtering can speed-up similarity
search several times.",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Safran:2019:ELB,
author = "Mejdl Safran and Dunren Che",
title = "Efficient Learning-Based Recommendation Algorithms for
Top- N Tasks and Top- N Workers in Large-Scale
Crowdsourcing Systems",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3231934",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The task and worker recommendation problems in
crowdsourcing systems have brought up unique
characteristics that are not present in traditional
recommendation scenarios, i.e., the huge flow of tasks
with short lifespans, the importance of workers'
capabilities, and the quality of the completed tasks.
These unique features make traditional recommendation
approaches no longer satisfactory for task and worker
recommendation in crowdsourcing systems. In this
article, we propose a two-tier data representation
scheme (defining a worker--category suitability score
and a worker--task attractiveness score ) to support
personalized task and worker recommendations. We also
extend two optimization methods, namely least mean
square error and Bayesian personalized rank, to better
fit the characteristics of task/worker recommendation
in crowdsourcing systems. We then integrate the
proposed representation scheme and the extended
optimization methods along with the two adapted popular
learning models, i.e., matrix factorization and kNN,
and result in two lines of top- N recommendation
algorithms for crowdsourcing systems: (1) Top- N -Tasks
recommendation algorithms for discovering the top- N
most suitable tasks for a given worker and (2) Top- N
-Workers recommendation algorithms for identifying the
top- N best workers for a task requester. An extensive
experimental study is conducted that validates the
effectiveness and efficiency of a broad spectrum of
algorithms, accompanied by our analysis and the
insights gained.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Deveaud:2019:LAR,
author = "Romain Deveaud and Josiane Mothe and Md Zia Ullah and
Jian-Yun Nie",
title = "Learning to Adaptively Rank Document Retrieval System
Configurations",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3231937",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Modern Information Retrieval (IR) systems have become
more and more complex, involving a large number of
parameters. For example, a system may choose from a set
of possible retrieval models (BM25, language model,
etc.), or various query expansion parameters, whose
values greatly influence the overall retrieval
effectiveness. Traditionally, these parameters are set
at a system level based on training queries, and the
same parameters are then used for different queries. We
observe that it may not be easy to set all these
parameters separately, since they can be dependent. In
addition, a global setting for all queries may not best
fit all individual queries with different
characteristics. The parameters should be set according
to these characteristics. In this article, we propose a
novel approach to tackle this problem by dealing with
the entire system configurations (i.e., a set of
parameters representing an IR system behaviour) instead
of selecting a single parameter at a time. The
selection of the best configuration is cast as a
problem of ranking different possible configurations
given a query. We apply learning-to-rank approaches for
this task. We exploit both the query features and the
system configuration features in the learning-to-rank
method so that the selection of configuration is query
dependent. The experiments we conducted on four TREC ad
hoc collections show that this approach can
significantly outperform the traditional method to tune
system configuration globally (i.e., grid search) and
leads to higher effectiveness than the top performing
systems of the TREC tracks. We also perform an ablation
analysis on the impact of different features on the
model learning capability and show that query expansion
features are among the most important for adaptive
systems.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Alakuijala:2019:BGP,
author = "Jyrki Alakuijala and Andrea Farruggia and Paolo
Ferragina and Eugene Kliuchnikov and Robert Obryk and
Zoltan Szabadka and Lode Vandevenne",
title = "{Brotli}: a General-Purpose Data Compressor",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3231935",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/datacompression.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Brotli is an open source general-purpose data
compressor introduced by Google in late 2013 and now
adopted in most known browsers and Web servers. It is
publicly available on GitHub and its data format was
submitted as RFC 7932 in July 2016. Brotli is based on
the Lempel--Ziv compression scheme and planned as a
generic replacement of Gzip and ZLib. The main goal in
its design was to compress data on the Internet, which
meant optimizing the resources used at decoding time,
while achieving maximal compression density. This
article is intended to provide the first thorough,
systematic description of the Brotli format as well as
a detailed computational and experimental analysis of
the main algorithmic blocks underlying the current
encoder implementation, together with a comparison
against compressors of different families constituting
the state-of-the-art either in practice or in theory.
This treatment will allow us to raise a set of new
algorithmic and software engineering problems that
deserve further attention from the scientific
community.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Qu:2019:PBN,
author = "Yanru Qu and Bohui Fang and Weinan Zhang and Ruiming
Tang and Minzhe Niu and Huifeng Guo and Yong Yu and
Xiuqiang He",
title = "Product-Based Neural Networks for User Response
Prediction over Multi-Field Categorical Data",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "5:1--5:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3233770",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "User response prediction is a crucial component for
personalized information retrieval and filtering
scenarios, such as recommender system and web search.
The data in user response prediction is mostly in a
multi-field categorical format and transformed into
sparse representations via one-hot encoding. Due to the
sparsity problems in representation and optimization,
most research focuses on feature engineering and
shallow modeling. Recently, deep neural networks have
attracted research attention on such a problem for
their high capacity and end-to-end training scheme. In
this article, we study user response prediction in the
scenario of click prediction. We first analyze a
coupled gradient issue in latent vector-based models
and propose kernel product to learn field-aware feature
interactions. Then, we discuss an insensitive gradient
issue in DNN-based models and propose Product-based
Neural Network, which adopts a feature extractor to
explore feature interactions. Generalizing the kernel
product to a net-in-net architecture, we further
propose Product-network in Network (PIN), which can
generalize previous models. Extensive experiments on
four industrial datasets and one contest dataset
demonstrate that our models consistently outperform
eight baselines on both area under curve and log loss.
Besides, PIN makes great click-through rate improvement
(relatively 34.67\%) in online A/B test.",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Huang:2019:QTQ,
author = "Heyan Huang and Xiaochi Wei and Liqiang Nie and
Xianling Mao and Xin-Shun Xu",
title = "From Question to Text: Question-Oriented Feature
Attention for Answer Selection",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "6:1--6:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3233771",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Understanding unstructured texts is an essential skill
for human beings as it enables knowledge acquisition.
Although understanding unstructured texts is easy for
we human beings with good education, it is a great
challenge for machines. Recently, with the rapid
development of artificial intelligence techniques,
researchers put efforts to teach machines to understand
texts and justify the educated machines by letting them
solve the questions upon the given unstructured texts,
inspired by the reading comprehension test as we humans
do. However, feature effectiveness with respect to
different questions significantly hinders the
performance of answer selection, because different
questions may focus on various aspects of the given
text and answer candidates. To solve this problem, we
propose a question-oriented feature attention (QFA)
mechanism, which learns to weight different engineering
features according to the given question, so that
important features with respect to the specific
question is emphasized accordingly. Experiments on
MCTest dataset have well-validated the effectiveness of
the proposed method. Additionally, the proposed QFA is
applicable to various IR tasks, such as question
answering and answer selection. We have verified the
applicability on a crawled community-based
question-answering dataset.",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lu:2019:DBT,
author = "Wei Lu and Fu-Lai Chung and Wenhao Jiang and Martin
Ester and Wei Liu",
title = "A Deep {Bayesian} Tensor-Based System for Video
Recommendation",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "7:1--7:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3233773",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "With the availability of abundant online
multi-relational video information, recommender systems
that can effectively exploit these sorts of data and
suggest creatively interesting items will become
increasingly important. Recent research illustrates
that tensor models offer effective approaches for
complex multi-relational data learning and missing
element completion. So far, most tensor-based user
clustering models have focused on the accuracy of
recommendation. Given the dynamic nature of online
media, recommendation in this setting is more
challenging as it is difficult to capture the users'
dynamic topic distributions in sparse data settings as
well as to identify unseen items as candidates of
recommendation. Targeting at constructing a recommender
system that can encourage more creativity, a deep
Bayesian probabilistic tensor framework for tag and
item recommendation is proposed. During the score
ranking processes, a metric called Bayesian surprise is
incorporated to increase the creativity of the
recommended candidates. The new algorithm, called Deep
Canonical PARAFAC Factorization (DCPF), is evaluated on
both synthetic and large-scale real-world problems. An
empirical study for video recommendation demonstrates
the superiority of the proposed model and indicates
that it can better capture the latent patterns of
interactions and generates interesting recommendations
based on creative tag combinations.",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tymoshenko:2019:SDS,
author = "Kateryna Tymoshenko and Alessandro Moschitti",
title = "Shallow and Deep Syntactic\slash Semantic Structures
for Passage Reranking in Question-Answering Systems",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "8:1--8:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3233772",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "In this article, we extensively study the use of
syntactic and semantic structures obtained with shallow
and full syntactic parsers for answer passage
reranking. We propose several dependency and
constituent-based structures, also enriched with Linked
Open Data (LD) knowledge to represent pairs of
questions and answer passages. We encode such tree
structures in learning-to-rank (L2R) algorithms using
tree kernels, which can project them in tree
substructure spaces, where each dimension represents a
powerful syntactic/semantic feature. Additionally,
since we define links between question and passage
structures, our tree kernel spaces also include
relational structural features. We carried out an
extensive comparative experimentation of our models for
automatic answer selection benchmarks on different TREC
QA corpora as well as the newer Wikipedia-based
dataset, namely WikiQA, which has been widely used to
test sentence rerankers. The results consistently
demonstrate that our structural semantic models achieve
the state of the art in passage reranking. In
particular, we derived the following important
findings: (i) relational syntactic structures are
essential to achieve superior results; (ii) models
trained with dependency trees can outperform those
trained with shallow trees, e.g., in case of sentence
reranking; (iii) external knowledge automatically
generated with focus and question classifiers is very
effective; and (iv) the semantic information derived by
LD and incorporated in syntactic structures can be used
to replace the knowledge provided by the
above-mentioned classifiers. This is a remarkable
advantage as it enables our models to increase coverage
and portability over new domains.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Li:2019:SGT,
author = "Chenliang Li and Shiqian Chen and Jian Xing and Aixin
Sun and Zongyang Ma",
title = "Seed-Guided Topic Model for Document Filtering and
Classification",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "9:1--9:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3238250",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "One important necessity is to filter out the
irrelevant information and organize the relevant
information into meaningful categories. However,
developing text classifiers often requires a large
number of labeled documents as training examples.
Manually labeling documents is costly and
time-consuming. More importantly, it becomes
unrealistic to know all the categories covered by the
documents beforehand. Recently, a few methods have been
proposed to label documents by using a small set of
relevant keywords for each category, known as dataless
text classification. In this article, we propose a
seed-guided topic model for the dataless text filtering
and classification (named DFC). Given a collection of
unlabeled documents, and for each specified category a
small set of seed words that are relevant to the
semantic meaning of the category, DFC filters out the
irrelevant documents and classifies the relevant
documents into the corresponding categories through
topic influence. DFC models two kinds of topics:
category-topics and general-topics. Also, there are two
kinds of category-topics: relevant-topics and
irrelevant-topics. Each relevant-topic is associated
with one specific category, representing its semantic
meaning. The irrelevant-topics represent the semantics
of the unknown categories covered by the document
collection. And the general-topics capture the global
semantic information. DFC assumes that each document is
associated with a single category-topic and a mixture
of general-topics. A novelty of the model is that DFC
learns the topics by exploiting the explicit word
co-occurrence patterns between the seed words and
regular words (i.e., non-seed words) in the document
collection. A document is then filtered, or classified,
based on its posterior category-topic assignment.
Experiments on two widely used datasets show that DFC
consistently outperforms the state-of-the-art dataless
text classifiers for both classification with filtering
and classification without filtering. In many tasks,
DFC can also achieve comparable or even better
classification accuracy than the state-of-the-art
supervised learning solutions. Our experimental results
further show that DFC is insensitive to the tuning
parameters. Moreover, we conduct a thorough study about
the impact of seed words for existing dataless text
classification techniques. The results reveal that it
is not using more seed words but the document coverage
of the seed words for the corresponding category that
affects the dataless classification performance.",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pan:2019:TRH,
author = "Weike Pan and Qiang Yang and Wanling Cai and Yaofeng
Chen and Qing Zhang and Xiaogang Peng and Zhong Ming",
title = "Transfer to Rank for Heterogeneous One-Class
Collaborative Filtering",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "10:1--10:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3243652",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Heterogeneous one-class collaborative filtering is an
emerging and important problem in recommender systems,
where two different types of one-class feedback, i.e.,
purchases and browses, are available as input data. The
associated challenges include ambiguity of browses,
scarcity of purchases, and heterogeneity arising from
different feedback. In this article, we propose to
model purchases and browses from a new perspective,
i.e., users' roles of mixer, browser and purchaser.
Specifically, we design a novel transfer learning
solution termed role-based transfer to rank (RoToR),
which contains two variants, i.e., integrative RoToR
and sequential RoToR. In integrative RoToR, we leverage
browses into the preference learning task of purchases,
in which we take each user as a sophisticated customer
(i.e., mixer ) that is able to take different types of
feedback into consideration. In sequential RoToR, we
aim to simplify the integrative one by decomposing it
into two dependent phases according to a typical
shopping process. Furthermore, we instantiate both
variants using different preference learning paradigms
such as pointwise preference learning and pairwise
preference learning. Finally, we conduct extensive
empirical studies with various baseline methods on
three large public datasets and find that our RoToR can
perform significantly more accurate than the
state-of-the-art methods.",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Oard:2019:JME,
author = "Douglas W. Oard and Fabrizio Sebastiani and Jyothi K.
Vinjumur",
title = "Jointly Minimizing the Expected Costs of Review for
Responsiveness and Privilege in E-Discovery",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "11:1--11:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3268928",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Discovery is an important aspect of the civil
litigation process in the United States of America, in
which all parties to a lawsuit are permitted to request
relevant evidence from other parties. With the rapid
growth of digital content, the emerging need for
``e-discovery'' has created a strong demand for
techniques that can be used to review massive
collections both for ``responsiveness'' (i.e.,
relevance) to the request and for ``privilege'' (i.e.,
presence of legally protected content that the party
performing the review may have a right to withhold). In
this process, the party performing the review may incur
costs of two types, namely, annotation costs (deriving
from the fact that human reviewers need to be paid for
their work) and misclassification costs (deriving from
the fact that failing to correctly determine the
responsiveness or privilege of a document may adversely
affect the interests of the parties in various ways).
Relying exclusively on automatic classification would
minimize annotation costs but could result in
substantial misclassification costs, while relying
exclusively on manual classification could generate the
opposite consequences. This article proposes a risk
minimization framework (called MINECORE, for
``minimizing the expected costs of review'') that seeks
to strike an optimal balance between these two extreme
stands. In MINECORE (a) the documents are first
automatically classified for both responsiveness and
privilege, and then (b) some of the automatically
classified documents are annotated by human reviewers
for responsiveness (typically by junior reviewers)
and/or, in cascade, for privilege (typically by senior
reviewers), with the overall goal of minimizing the
expected cost (i.e., the risk ) of the entire process.
Risk minimization is achieved by optimizing, for both
responsiveness and privilege, the choice of which
documents to manually review. We present a simulation
study in which classes from a standard text
classification test collection (RCV1-v2) are used as
surrogates for responsiveness and privilege. The
results indicate that MINECORE can yield substantially
lower total cost than any of a set of strong
baselines.",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chen:2019:ADE,
author = "Xu Chen and Yongfeng Zhang and Hongteng Xu and Zheng
Qin and Hongyuan Zha",
title = "Adversarial Distillation for Efficient Recommendation
with External Knowledge",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "12:1--12:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3281659",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "Integrating external knowledge into the recommendation
system has attracted increasing attention in both
industry and academic communities. Recent methods
mostly take the power of neural network for effective
knowledge representation to improve the recommendation
performance. However, the heavy deep architectures in
existing models are usually incorporated in an embedded
manner, which may greatly increase the model complexity
and lower the runtime efficiency. To simultaneously
take the power of deep learning for external knowledge
modeling as well as maintaining the model efficiency at
test time, we reformulate the problem of recommendation
with external knowledge into a generalized distillation
framework. The general idea is to free the complex deep
architecture into a separate model, which is only used
in the training phrase, while abandoned at test time.
In particular, in the training phrase, the external
knowledge is processed by a comprehensive teacher model
to produce valuable information to teach a simple and
efficient student model. Once the framework is learned,
the teacher model is abandoned, and only the succinct
yet enhanced student model is used to make fast
predictions at test time. In this article, we specify
the external knowledge as user review, and to leverage
it in an effective manner, we further extend the
traditional generalized distillation framework by
designing a Selective Distillation Network (SDNet) with
adversarial adaption and orthogonality constraint
strategies to make it more robust to noise information.
Extensive experiments verify that our model can not
only improve the performance of rating prediction, but
also can significantly reduce time consumption when
making predictions as compared with several
state-of-the-art methods.",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cornolti:2019:SPA,
author = "Marco Cornolti and Paolo Ferragina and Massimiliano
Ciaramita and Stefan R{\"u}d and Hinrich Sch{\"u}tze",
title = "{SMAPH}: a Piggyback Approach for Entity-Linking in
{Web} Queries",
journal = j-TOIS,
volume = "37",
number = "1",
pages = "13:1--13:??",
month = jan,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3284102",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "We study the problem of linking the terms of a
web-search query to a semantic representation given by
the set of entities (a.k.a. concepts) mentioned in it.
We introduce SMAPH, a system that performs this task
using the information coming from a web search engine,
an approach we call ``piggybacking.'' We employ search
engines to alleviate the noise and irregularities that
characterize the language of queries. Snippets returned
as search results also provide a context for the query
that makes it easier to disambiguate the meaning of the
query. From the search results, SMAPH builds a set of
candidate entities with high coverage. This set is
filtered by linking back the candidate entities to the
terms occurring in the input query, ensuring high
precision. A greedy disambiguation algorithm performs
this filtering; it maximizes the coherence of the
solution by iteratively discovering the pertinent
entities mentioned in the query. We propose three
versions of SMAPH that outperform state-of-the-art
solutions on the known benchmarks and on the GERDAQ
dataset, a novel dataset that we have built
specifically for this problem via crowd-sourcing and
that we make publicly available.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Niu:2019:UFS,
author = "Xi Niu and Xiangyu Fan and Tao Zhang",
title = "Understanding Faceted Search from Data Science and
Human Factor Perspectives",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "14:1--14:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3284101",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3284101",
abstract = "Faceted search has become a common feature on most
search interfaces in e-commerce websites, digital
libraries, government's open information portals, and
so on. Beyond the existing studies on developing
algorithms for faceted search and empirical studies on
facet usage, this study investigated user real-time
interactions with facets over the course of a search
from both data science and human factor perspectives.
It adopted a Random Forest (RF) model to successfully
predict facet use using search dynamic variables. In
addition, the RF model provided a ranking of variables
by their predictive power, which suggests that the
search process follows rhythmic flow of a sequence
within which facet addition is mostly influenced by its
immediately preceding action. In the follow-up user
study, we found that participants used facets at
critical points from the beginning to end of search
sessions. Participants used facets for distinctive
reasons at different stages. They also used facets
implicitly without applying the facets to their search.
Most participants liked the faceted search, although a
few participants were concerned about the choice
overload introduced by facets. The results of this
research can be used to understand information seekers
and propose or refine a set of practical design
guidelines for faceted search.",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Loni:2019:TRM,
author = "Babak Loni and Roberto Pagano and Martha Larson and
Alan Hanjalic",
title = "Top-{$N$} Recommendation with Multi-Channel Positive
Feedback using Factorization Machines",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "15:1--15:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3291756",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3291756",
abstract = "User interactions can be considered to constitute
different feedback channels, for example, view, click,
like or follow, that provide implicit information on
users' preferences. Each implicit feedback channel
typically carries a unary, positive-only signal that
can be exploited by collaborative filtering models to
generate lists of personalized recommendations. This
article investigates how a learning-to-rank recommender
system can best take advantage of implicit feedback
signals from multiple channels. We focus on
Factorization Machines (FMs) with Bayesian Personalized
Ranking (BPR), a pairwise learning-to-rank method, that
allows us to experiment with different forms of
exploitation. We perform extensive experiments on three
datasets with multiple types of feedback to arrive at a
series of insights. We compare conventional, direct
integration of feedback types with our proposed method,
which exploits multiple feedback channels during the
sampling process of training. We refer to our method as
multi-channel sampling. Our results show that
multi-channel sampling outperforms conventional
integration, and that sampling with the relative
``level'' of feedback is always superior to a
level-blind sampling approach. We evaluate our method
experimentally on three datasets in different domains
and observe that with our multi-channel sampler the
accuracy of recommendations can be improved
considerably compared to the state-of-the-art models.
Further experiments reveal that the appropriate
sampling method depends on particular properties of
datasets such as popularity skewness.",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cheng:2019:MER,
author = "Zhiyong Cheng and Xiaojun Chang and Lei Zhu and Rose
C. Kanjirathinkal and Mohan Kankanhalli",
title = "{MMALFM}: Explainable Recommendation by Leveraging
Reviews and Images",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "16:1--16:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3291060",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3291060",
abstract = "Personalized rating prediction is an important
research problem in recommender systems. Although the
latent factor model (e.g., matrix factorization)
achieves good accuracy in rating prediction, it suffers
from many problems including cold-start,
non-transparency, and suboptimal results for individual
user-item pairs. In this article, we exploit textual
reviews and item images together with ratings to tackle
these limitations. Specifically, we first apply a
proposed multi-modal aspect-aware topic model (MATM) on
text reviews and item images to model users'
preferences and items' features from different aspects,
and also estimate the aspect importance of a user
toward an item. Then, the aspect importance is
integrated into a novel aspect-aware latent factor
model (ALFM), which learns user's and item's latent
factors based on ratings. In particular, ALFM
introduces a weight matrix to associate those latent
factors with the same set of aspects in MATM, such that
the latent factors could be used to estimate aspect
ratings. Finally, the overall rating is computed via a
linear combination of the aspect ratings, which are
weighted by the corresponding aspect importance. To
this end, our model could alleviate the data sparsity
problem and gain good interpretability for
recommendation. Besides, every aspect rating is
weighted by its aspect importance, which is dependent
on the targeted user's preferences and the targeted
item's features. Therefore, it is expected that the
proposed method can model a user's preferences on an
item more accurately for each user-item pair.
Comprehensive experimental studies have been conducted
on the Yelp 2017 Challenge dataset and Amazon product
datasets. Results show that (1) our method achieves
significant improvement compared to strong baseline
methods, especially for users with only few ratings;
(2) item visual features can improve the prediction
performance-the effects of item image features on
improving the prediction results depend on the
importance of the visual features for the items; and
(3) our model can explicitly interpret the predicted
results in great detail.",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chong:2019:FGG,
author = "Wen-Haw Chong and Ee-Peng Lim",
title = "Fine-grained Geolocation of Tweets in Temporal
Proximity",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "17:1--17:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3291059",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3291059",
abstract = "In fine-grained tweet geolocation, tweets are linked
to the specific venues (e.g., restaurants, shops) from
which they were posted. This explicitly recovers the
venue context that is essential for applications such
as location-based advertising or user profiling. For
this geolocation task, we focus on geolocating tweets
that are contained in tweet sequences. In a tweet
sequence, tweets are posted from some latent venue(s)
by the same user and within a short time interval. This
scenario arises from two observations: (1) It is quite
common that users post multiple tweets in a short time
and (2) most tweets are not geocoded. To more
accurately geolocate a tweet, we propose a model that
performs query expansion on the tweet (query) using two
novel approaches. The first approach temporal query
expansion considers users' staying behavior around
venues. The second approach visitation query expansion
leverages on user revisiting the same or similar venues
in the past. We combine both query expansion approaches
via a novel fusion framework and overlay them on a
Hidden Markov Model to account for sequential
information. In our comprehensive experiments across
multiple datasets and metrics, we show our proposed
model to be more robust and accurate than other
baselines.",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Qian:2019:SRL,
author = "Tieyun Qian and Bei Liu and Quoc Viet Hung Nguyen and
Hongzhi Yin",
title = "Spatiotemporal Representation Learning for
Translation-Based {POI} Recommendation",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "18:1--18:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3295499",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3295499",
abstract = "The increasing proliferation of location-based social
networks brings about a huge volume of user check-in
data, which facilitates the recommendation of points of
interest (POIs). Time and location are the two most
important contextual factors in the user's
decision-making for choosing a POI to visit. In this
article, we focus on the spatiotemporal context-aware
POI recommendation, which considers the joint effect of
time and location for POI recommendation. Inspired by
the recent advances in knowledge graph embedding, we
propose a spatiotemporal context-aware and
translation-based recommender framework (STA) to model
the third-order relationship among users, POIs, and
spatiotemporal contexts for large-scale POI
recommendation. Specifically, we embed both users and
POIs into a ``transition space'' where spatiotemporal
contexts (i.e., a \< time, location \> pair) are
modeled as translation vectors operating on users and
POIs. We further develop a series of strategies to
exploit various correlation information to address the
data sparsity and cold-start issues for new
spatiotemporal contexts, new users, and new POIs. We
conduct extensive experiments on two real-world
datasets. The experimental results demonstrate that our
STA framework achieves the superior performance in
terms of high recommendation accuracy, robustness to
data sparsity, and effectiveness in handling the
cold-start problem.",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Guo:2019:ALS,
author = "Yangyang Guo and Zhiyong Cheng and Liqiang Nie and
Yinglong Wang and Jun Ma and Mohan Kankanhalli",
title = "Attentive Long Short-Term Preference Modeling for
Personalized Product Search",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "19:1--19:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3295822",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3295822",
abstract = "E-commerce users may expect different products even
for the same query, due to their diverse personal
preferences. It is well known that there are two types
of preferences: long-term ones and short-term ones. The
former refers to users' inherent purchasing bias and
evolves slowly. By contrast, the latter reflects users'
purchasing inclination in a relatively short period.
They both affect users' current purchasing intentions.
However, few research efforts have been dedicated to
jointly model them for the personalized product search.
To this end, we propose a novel Attentive Long
Short-Term Preference model, dubbed as ALSTP, for
personalized product search. Our model adopts the
neural networks approach to learn and integrate the
long- and short-term user preferences with the current
query for the personalized product search. In
particular, two attention networks are designed to
distinguish which factors in the short-term as well as
long-term user preferences are more relevant to the
current query. This unique design enables our model to
capture users' current search intentions more
accurately. Our work is the first to apply attention
mechanisms to integrate both long- and short-term user
preferences with the given query for the personalized
search. Extensive experiments over four Amazon product
datasets show that our model significantly outperforms
several state-of-the-art product search methods in
terms of different evaluation metrics.",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lukasik:2019:GPR,
author = "Michal Lukasik and Kalina Bontcheva and Trevor Cohn
and Arkaitz Zubiaga and Maria Liakata and Rob Procter",
title = "{Gaussian} Processes for Rumour Stance Classification
in Social Media",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "20:1--20:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3295823",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3295823",
abstract = "Social media tend to be rife with rumours while new
reports are released piecemeal during breaking news.
Interestingly, one can mine multiple reactions
expressed by social media users in those situations,
exploring their stance towards rumours, ultimately
enabling the flagging of highly disputed rumours as
being potentially false. In this work, we set out to
develop an automated, supervised classifier that uses
multi-task learning to classify the stance expressed in
each individual tweet in a conversation around a rumour
as either supporting, denying or questioning the
rumour. Using a Gaussian Process classifier, and
exploring its effectiveness on two datasets with very
different characteristics and varying distributions of
stances, we show that our approach consistently
outperforms competitive baseline classifiers. Our
classifier is especially effective in estimating the
distribution of different types of stance associated
with a given rumour, which we set forth as a desired
characteristic for a rumour-tracking system that will
show both ordinary users of Twitter and professional
news practitioners how others orient to the disputed
veracity of a rumour, with the final aim of
establishing its actual truth value.",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Cagliero:2019:EMD,
author = "Luca Cagliero and Paolo Garza and Elena Baralis",
title = "{ELSA}: a Multilingual Document Summarization
Algorithm Based on Frequent Itemsets and Latent
Semantic Analysis",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "21:1--21:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3298987",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3298987",
abstract = "Sentence-based summarization aims at extracting
concise summaries of collections of textual documents.
Summaries consist of a worthwhile subset of document
sentences. The most effective multilingual strategies
rely on Latent Semantic Analysis (LSA) and on frequent
itemset mining, respectively. LSA-based summarizers
pick the document sentences that cover the most
important concepts. Concepts are modeled as
combinations of single-document terms and are derived
from a term-by-sentence matrix by exploiting Singular
Value Decomposition (SVD). Itemset-based summarizers
pick the sentences that contain the largest number of
frequent itemsets, which represent combinations of
frequently co-occurring terms. The main drawbacks of
existing approaches are (i) the inability of LSA to
consider the correlation between combinations of
multiple-document terms and the underlying concepts,
(ii) the inherent redundancy of frequent itemsets
because similar itemsets may be related to the same
concept, and (iii) the inability of itemset-based
summarizers to correlate itemsets with the underlying
document concepts. To overcome the issues of both of
the abovementioned algorithms, we propose a new
summarization approach that exploits frequent itemsets
to describe all of the latent concepts covered by the
documents under analysis and LSA to reduce the
potentially redundant set of itemsets to a compact set
of uncorrelated concepts. The summarizer selects the
sentences that cover the latent concepts with minimal
redundancy. We tested the summarization algorithm on
both multilingual and English-language benchmark
document collections. The proposed approach performed
significantly better than both itemset- and LSA-based
summarizers, and better than most of the other
state-of-the-art approaches.",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wu:2019:CAU,
author = "Libing Wu and Cong Quan and Chenliang Li and Qian Wang
and Bolong Zheng and Xiangyang Luo",
title = "A Context-Aware User-Item Representation Learning for
Item Recommendation",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "22:1--22:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3298988",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3298988",
abstract = "Both reviews and user-item interactions (i.e., rating
scores) have been widely adopted for user rating
prediction. However, these existing techniques mainly
extract the latent representations for users and items
in an independent and static manner. That is, a single
static feature vector is derived to encode user
preference without considering the particular
characteristics of each candidate item. We argue that
this static encoding scheme is incapable of fully
capturing users' preferences, because users usually
exhibit different preferences when interacting with
different items. In this article, we propose a novel
context-aware user-item representation learning model
for rating prediction, named CARL. CARL derives a joint
representation for a given user-item pair based on
their individual latent features and latent feature
interactions. Then, CARL adopts Factorization Machines
to further model higher order feature interactions on
the basis of the user-item pair for rating prediction.
Specifically, two separate learning components are
devised in CARL to exploit review data and interaction
data, respectively: review-based feature learning and
interaction-based feature learning. In the review-based
learning component, with convolution operations and
attention mechanism, the pair-based relevant features
for the given user-item pair are extracted by jointly
considering their corresponding reviews. However, these
features are only review-driven and may not be
comprehensive. Hence, an interaction-based learning
component further extracts complementary features from
interaction data alone, also on the basis of user-item
pairs. The final rating score is then derived with a
dynamic linear fusion mechanism. Experiments on seven
real-world datasets show that CARL achieves
significantly better rating prediction accuracy than
existing state-of-the-art alternatives. Also, with the
attention mechanism, we show that the pair-based
relevant information (i.e., context-aware information)
in reviews can be highlighted to interpret the rating
prediction for different user-item pairs.",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2019:MVB,
author = "Ming Liu and Gu Gong and Bing Qin and Ting Liu",
title = "A Multi-View-Based Collective Entity Linking Method",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "23:1--23:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3300197",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3300197",
abstract = "Facing lots of name mentions appearing on the web,
entity linking is essential for many information
processing applications. To improve linking accuracy,
the relations between entities are usually considered
in the linking process. This kind of method is called
collective entity linking and can obtain high-quality
results. There are two kinds of information helpful to
reveal the relations between entities, i.e., contextual
information and structural information of entities.
Most traditional collective entity linking methods
consider them separately. In fact, these two kinds of
information represent entities from specific and
diverse views and can enhance each other, respectively.
Besides, if we look into each view closely, it can be
separated into sub-views that are more meaningful. For
this reason, this article proposes a multi-view-based
collective entity linking algorithm, which combines
several views of entities into an objective function
for entity linking. The importance of each view can be
valued and the linking results can be obtained along
with resolving this objective function. Experimental
results demonstrate that our linking algorithm can
acquire higher accuracy than many state-of-the-art
entity linking methods. Besides, since we simplify the
entity's structure and change the entity linking to a
sub-matrix searching problem, our algorithm also
obtains high efficiency.",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Sousa:2019:RSL,
author = "Daniel Xavier Sousa and S{\'e}rgio Canuto and Marcos
Andr{\'e} Gon{\c{c}}alves and Thierson Couto Rosa and
Wellington Santos Martins",
title = "Risk-Sensitive Learning to Rank with Evolutionary
Multi-Objective Feature Selection",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "24:1--24:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3300196",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3300196",
abstract = "Learning to Rank (L2R) is one of the main research
lines in Information Retrieval. Risk-sensitive L2R is a
sub-area of L2R that tries to learn models that are
good on average while at the same time reducing the
risk of performing poorly in a few but important
queries (e.g., medical or legal queries). One way of
reducing risk in learned models is by selecting and
removing noisy, redundant features, or features that
promote some queries to the detriment of others. This
is exacerbated by learning methods that usually
maximize an average metric (e.g., mean average
precision (MAP) or Normalized Discounted Cumulative
Gain (NDCG)). However, historically, feature selection
(FS) methods have focused only on effectiveness and
feature reduction as the main objectives. Accordingly,
in this work, we propose to evaluate FS for L2R with an
additional objective in mind, namely
risk-sensitiveness. We present novel single and
multi-objective criteria to optimize feature reduction,
effectiveness, and risk-sensitiveness, all at the same
time. We also introduce a new methodology to explore
the search space, suggesting effective and efficient
extensions of a well-known Evolutionary Algorithm
(SPEA2) for FS applied to L2R. Our experiments show
that explicitly including risk as an objective
criterion is crucial to achieving a more effective and
risk-sensitive performance. We also provide a thorough
analysis of our methodology and experimental results.",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Pibiri:2019:HMG,
author = "Giulio Ermanno Pibiri and Rossano Venturini",
title = "Handling Massive {$N$}-Gram Datasets Efficiently",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "25:1--25:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3302913",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3302913",
abstract = "Two fundamental problems concern the handling of large
n -gram language models: indexing, that is, compressing
the n -grams and associated satellite values without
compromising their retrieval speed, and estimation,
that is, computing the probability distribution of the
n -grams extracted from a large textual source.
Performing these two tasks efficiently is vital for
several applications in the fields of Information
Retrieval, Natural Language Processing, and Machine
Learning, such as auto-completion in search engines and
machine translation. Regarding the problem of indexing,
we describe compressed, exact, and lossless data
structures that simultaneously achieve high space
reductions and no time degradation with respect to the
state-of-the-art solutions and related software
packages. In particular, we present a compressed trie
data structure in which each word of an n -gram
following a context of fixed length k, that is, its
preceding k words, is encoded as an integer whose value
is proportional to the number of words that follow such
context. Since the number of words following a given
context is typically very small in natural languages,
we lower the space of representation to compression
levels that were never achieved before, allowing the
indexing of billions of strings. Despite the
significant savings in space, our technique introduces
a negligible penalty at query time. Specifically, the
most space-efficient competitors in the literature,
which are both quantized and lossy, do not take less
than our trie data structure and are up to 5 times
slower. Conversely, our trie is as fast as the fastest
competitor but also retains an advantage of up to 65\%
in absolute space. Regarding the problem of estimation,
we present a novel algorithm for estimating modified
Kneser-Ney language models that have emerged as the
de-facto choice for language modeling in both academia
and industry thanks to their relatively low perplexity
performance. Estimating such models from large textual
sources poses the challenge of devising algorithms that
make a parsimonious use of the disk. The
state-of-the-art algorithm uses three sorting steps in
external memory: we show an improved construction that
requires only one sorting step by exploiting the
properties of the extracted n -gram strings. With an
extensive experimental analysis performed on billions
of n -grams, we show an average improvement of 4.5
times on the total runtime of the previous approach.",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhan:2019:LMA,
author = "Xueying Zhan and Yaowei Wang and Yanghui Rao and Qing
Li",
title = "Learning from Multi-annotator Data: a Noise-aware
Classification Framework",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "26:1--26:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3309543",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309543",
abstract = "In the field of sentiment analysis and emotion
detection in social media, or other tasks such as text
classification involving supervised learning,
researchers rely more heavily on large and accurate
labelled training datasets. However, obtaining
large-scale labelled datasets is time-consuming and
high-quality labelled datasets are expensive and
scarce. To deal with these problems, online
crowdsourcing systems provide us an efficient way to
accelerate the process of collecting training data via
distributing the enormous tasks to various annotators
to help create large amounts of labelled data at an
affordable cost. Nowadays, these crowdsourcing
platforms are heavily needed in dealing with social
media text, since the social network platforms (e.g.,
Twitter) generate huge amounts of data in textual form
everyday. However, people from different social and
knowledge backgrounds have different views on various
texts, which may lead to noisy labels. The existing
noisy label aggregation/refinement algorithms mostly
focus on aggregating labels from noisy annotations,
which would not guarantee their effectiveness on the
subsequent classification/ranking tasks. In this
article, we propose a noise-aware classification
framework that integrates the steps of noisy label
aggregation and classification. The aggregated noisy
crowd labels are fed into a classifier for training,
while the predicted labels are employed as feedback for
adjusting the parameters at the label aggregating
stage. The classification framework is suitable for
directly running on crowdsourcing datasets and applies
to various kinds of classification algorithms. The
feedback strategy makes it possible for us to find
optimal parameters instead of using known data for
parameter selection. Simulation experiments demonstrate
that our method provide significant label aggregation
performance for both binary and multiple classification
tasks under various noisy environments. Experimenting
on real-world data validates the feasibility of our
framework in real noise data and helps us verify the
reasonableness of the simulated experiment settings.",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Feng:2019:TRR,
author = "Fuli Feng and Xiangnan He and Xiang Wang and Cheng Luo
and Yiqun Liu and Tat-Seng Chua",
title = "Temporal Relational Ranking for Stock Prediction",
journal = j-TOIS,
volume = "37",
number = "2",
pages = "27:1--27:??",
month = mar,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3309547",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309547",
abstract = "Stock prediction aims to predict the future trends of
a stock in order to help investors make good investment
decisions. Traditional solutions for stock prediction
are based on time-series models. With the recent
success of deep neural networks in modeling sequential
data, deep learning has become a promising choice for
stock prediction. However, most existing deep learning
solutions are not optimized toward the target of
investment, i.e., selecting the best stock with the
highest expected revenue. Specifically, they typically
formulate stock prediction as a classification (to
predict stock trends) or a regression problem (to
predict stock prices). More importantly, they largely
treat the stocks as independent of each other. The
valuable signal in the rich relations between stocks
(or companies), such as two stocks are in the same
sector and two companies have a supplier-customer
relation, is not considered. In this work, we
contribute a new deep learning solution, named
Relational Stock Ranking (RSR), for stock prediction.
Our RSR method advances existing solutions in two major
aspects: (1) tailoring the deep learning models for
stock ranking, and (2) capturing the stock relations in
a time-sensitive manner. The key novelty of our work is
the proposal of a new component in neural network
modeling, named Temporal Graph Convolution, which
jointly models the temporal evolution and relation
network of stocks. To validate our method, we perform
back-testing on the historical data of two stock
markets, NYSE and NASDAQ. Extensive experiments
demonstrate the superiority of our RSR method. It
outperforms state-of-the-art stock prediction solutions
achieving an average return ratio of 98\% and 71\% on
NYSE and NASDAQ, respectively.",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Guan:2019:AAM,
author = "Xinyu Guan and Zhiyong Cheng and Xiangnan He and
Yongfeng Zhang and Zhibo Zhu and Qinke Peng and
Tat-Seng Chua",
title = "Attentive Aspect Modeling for Review-Aware
Recommendation",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "28:1--28:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3309546",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309546",
abstract = "In recent years, many studies extract aspects from
user reviews and integrate them with ratings for
improving the recommendation performance. The common
aspects mentioned in a user's reviews and a product's
reviews indicate indirect connections between the user
and product. However, these aspect-based methods suffer
from two problems. First, the common aspects are
usually very sparse, which is caused by the sparsity of
user-product interactions and the diversity of
individual users' vocabularies. Second, a user's
interests on aspects could be different with respect to
different products, which are usually assumed to be
static in existing methods. In this article, we propose
an Attentive Aspect-based Recommendation Model (AARM)
to tackle these challenges. For the first problem, to
enrich the aspect connections between user and product,
besides common aspects, AARM also models the
interactions between synonymous and similar aspects.
For the second problem, a neural attention network
which simultaneously considers user, product, and
aspect information is constructed to capture a user's
attention toward aspects when examining different
products. Extensive quantitative and qualitative
experiments show that AARM can effectively alleviate
the two aforementioned problems and significantly
outperforms several state-of-the-art recommendation
methods on the top-N recommendation task.",
acknowledgement = ack-nhfb,
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Shao:2019:AMI,
author = "Yunqiu Shao and Yiqun Liu and Fan Zhang and Min Zhang
and Shaoping Ma",
title = "On Annotation Methodologies for Image Search
Evaluation",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "29:1--29:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3309994",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3309994",
abstract = "Image search engines differ significantly from general
web search engines in the way of presenting search
results. The difference leads to different interaction
and examination behavior patterns, and therefore
requires changes in evaluation methodologies. However,
evaluation of image search still utilizes the methods
for general web search. In particular, offline metrics
are calculated based on coarse-fine topical relevance
judgments with the assumption that users examine
results in a sequential manner. In this article, we
investigate annotation methods via crowdsourcing for
image search evaluation based on a lab-based user
study. Using user satisfaction as the golden standard,
we make several interesting findings. First, instead of
item-based annotation, annotating relevance in a
row-based way is more efficient without hurting
performance. Second, besides topical relevance, image
quality plays a crucial role when evaluating the image
search results, and the importance of image quality
changes with search intent. Third, compared to
traditional four-level scales, the fine-grain
annotation method outperforms significantly. To our
best knowledge, our work is the first to systematically
study how diverse factors in data annotation impact
image search evaluation. Our results suggest different
strategies for exploiting the crowdsourcing to get data
annotated under different conditions.",
acknowledgement = ack-nhfb,
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ferro:2019:UCS,
author = "Nicola Ferro and Yubin Kim and Mark Sanderson",
title = "Using Collection Shards to Study Retrieval Performance
Effect Sizes",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "30:1--30:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3310364",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3310364",
abstract = "Despite the bulk of research studying how to more
accurately compare the performance of IR systems, less
attention is devoted to better understanding the
different factors that play a role in such performance
and how they interact. This is the case of shards,
i.e., partitioning a document collection into
sub-parts, which are used for many different purposes,
ranging from efficiency to selective search or making
test collection evaluation more accurate. In all these
cases, there is empirical knowledge supporting the
importance of shards, but we lack actual models that
allow us to measure the impact of shards on system
performance and how they interact with topics and
systems. We use the general linear mixed model
framework and present a model that encompasses the
experimental factors of system, topic, shard, and their
interaction effects. This detailed model allows us to
more accurately estimate differences between the effect
of various factors. We study shards created by a range
of methods used in prior work and better explain
observations noted in prior work in a principled
setting and offer new insights. Notably, we discover
that the topic*shard interaction effect, in particular,
is a large effect almost globally across all datasets,
an observation that, to our knowledge, has not been
measured before.",
acknowledgement = ack-nhfb,
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Li:2019:PRP,
author = "Xinyi Li and Yifan Chen and Benjamin Pettit and
Maarten {De Rijke}",
title = "Personalised Reranking of Paper Recommendations Using
Paper Content and User Behavior",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "31:1--31:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3312528",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3312528",
abstract = "Academic search engines have been widely used to
access academic papers, where users' information needs
are explicitly represented as search queries. Some
modern recommender systems have taken one step further
by predicting users' information needs without the
presence of an explicit query. In this article, we
examine an academic paper recommender that sends out
paper recommendations in email newsletters, based on
the users' browsing history on the academic search
engine. Specifically, we look at users who regularly
browse papers on the search engine, and we sign up for
the recommendation newsletters for the first time. We
address the task of reranking the recommendation
candidates that are generated by a production system
for such users. We face the challenge that the users on
whom we focus have not interacted with the recommender
system before, which is a common scenario that every
recommender system encounters when new users sign up.
We propose an approach to reranking candidate
recommendations that utilizes both paper content and
user behavior. The approach is designed to suit the
characteristics unique to our academic recommendation
setting. For instance, content similarity measures can
be used to find the closest match between candidate
recommendations and the papers previously browsed by
the user. To this end, we use a knowledge graph derived
from paper metadata to compare entity similarities
(papers, authors, and journals) in the embedding space.
Since the users on whom we focus have no prior
interactions with the recommender system, we propose a
model to learn a mapping from users' browsed articles
to user clicks on the recommendations. We combine both
content and behavior into a hybrid reranking model that
outperforms the production baseline significantly,
providing a relative 13\% increase in Mean Average
Precision and 28\% in Precision@1. Moreover, we provide
a detailed analysis of the model components,
highlighting where the performance boost comes from.
The obtained insights reveal useful components for the
reranking process and can be generalized to other
academic recommendation settings as well, such as the
utility of graph embedding similarity. Also, recent
papers browsed by users provide stronger evidence for
recommendation than historical ones.",
acknowledgement = ack-nhfb,
articleno = "31",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wang:2019:EHO,
author = "Hongwei Wang and Fuzheng Zhang and Jialin Wang and
Miao Zhao and Wenjie Li and Xing Xie and Minyi Guo",
title = "Exploring High-Order User Preference on the Knowledge
Graph for Recommender Systems",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "32:1--32:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3312738",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3312738",
abstract = "To address the sparsity and cold-start problem of
collaborative filtering, researchers usually make use
of side information, such as social networks or item
attributes, to improve the performance of
recommendation. In this article, we consider the
knowledge graph (KG) as the source of side information.
To address the limitations of existing embedding-based
and path-based methods for KG-aware recommendation, we
propose RippleNet, an end-to-end framework that
naturally incorporates the KG into recommender systems.
RippleNet has two versions: (1) The outward propagation
version, which is analogous to the actual ripples on
water, stimulates the propagation of user preferences
over the set of knowledge entities by automatically and
iteratively extending a user's potential interests
along links in the KG. The multiple ``ripples''
activated by a user's historically clicked items are
thus superposed to form the preference distribution of
the user with respect to a candidate item. (2) The
inward aggregation version aggregates and incorporates
the neighborhood information biasedly when computing
the representation of a given entity. The neighborhood
can be extended to multiple hops away to model
high-order proximity and capture users' long-distance
interests. In addition, we intuitively demonstrate how
a KG assists with recommender systems in RippleNet, and
we also find that RippleNet provides a new perspective
of explainability for the recommended results in terms
of the KG. Through extensive experiments on real-world
datasets, we demonstrate that both versions of
RippleNet achieve substantial gains in a variety of
scenarios, including movie, book, and news
recommendations, over several state-of-the-art
baselines.",
acknowledgement = ack-nhfb,
articleno = "32",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Xue:2019:DIB,
author = "Feng Xue and Xiangnan He and Xiang Wang and Jiandong
Xu and Kai Liu and Richang Hong",
title = "Deep Item-based Collaborative Filtering for Top-{$N$}
Recommendation",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "33:1--33:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3314578",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3314578",
abstract = "Item-based Collaborative Filtering (ICF) has been
widely adopted in recommender systems in industry,
owing to its strength in user interest modeling and
ease in online personalization. By constructing a
user's profile with the items that the user has
consumed, ICF recommends items that are similar to the
user's profile. With the prevalence of machine learning
in recent years, significant processes have been made
for ICF by learning item similarity (or representation)
from data. Nevertheless, we argue that most existing
works have only considered linear and shallow
relationships between items, which are insufficient to
capture the complicated decision-making process of
users. In this article, we propose a more expressive
ICF solution by accounting for the nonlinear and
higher-order relationships among items. Going beyond
modeling only the second-order interaction (e.g.,
similarity) between two items, we additionally consider
the interaction among all interacted item pairs by
using nonlinear neural networks. By doing this, we can
effectively model the higher-order relationship among
items, capturing more complicated effects in user
decision-making. For example, it can differentiate
which historical itemsets in a user's profile are more
important in affecting the user to make a purchase
decision on an item. We treat this solution as a deep
variant of ICF, thus term it as DeepICF. To justify our
proposal, we perform empirical studies on two public
datasets from MovieLens and Pinterest. Extensive
experiments verify the highly positive effect of
higher-order item interaction modeling with nonlinear
neural networks. Moreover, we demonstrate that by more
fine-grained second-order interaction modeling with
attention network, the performance of our DeepICF
method can be further improved.",
acknowledgement = ack-nhfb,
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2019:MAD,
author = "Zheng Zhang and Minlie Huang and Zhongzhou Zhao and
Feng Ji and Haiqing Chen and Xiaoyan Zhu",
title = "Memory-Augmented Dialogue Management for Task-Oriented
Dialogue Systems",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "34:1--34:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3317612",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3317612",
abstract = "Dialogue management (DM) is responsible for predicting
the next action of a dialogue system according to the
current dialogue state and thus plays a central role in
task-oriented dialogue systems. Since DM requires
having access not only to local utterances but also to
the global semantics of the entire dialogue session,
modeling the long-range history information is a
critical issue. To this end, we propose MAD, a novel
memory-augmented dialogue management model that employs
a memory controller and two additional memory
structures (i.e., a slot-value memory and an external
memory). The slot-value memory tracks the dialogue
state by memorizing and updating the values of semantic
slots (i.e., cuisine, price, and location), and the
external memory augments the representation of hidden
states of traditional recurrent neural networks by
storing more context information. To update the
dialogue state efficiently, we also propose slot-level
attention on user utterances to extract specific
semantic information for each slot. Experiments show
that our model can obtain state-of-the-art performance
and outperforms existing baselines.",
acknowledgement = ack-nhfb,
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Wu:2019:DDA,
author = "Zhijing Wu and Ke Zhou and Yiqun Liu and Min Zhang and
Shaoping Ma",
title = "Does Diversity Affect User Satisfaction in Image
Search",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "35:1--35:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3320118",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3320118",
abstract = "Diversity has been taken into consideration by
existing Web image search engines in ranking search
results. However, there is no thorough investigation of
how diversity affects user satisfaction in image
search. In this article, we address the following
questions: (1) How do different factors, such as
content and visual presentations, affect users'
perception of diversity? (2) How does search result
diversity affect user satisfaction with different
search intents? To answer those questions, we conduct a
set of laboratory user studies to collect users'
perceived diversity annotations and search
satisfaction. We find that the existence of nearly
duplicated image results has the largest impact on
users' perceived diversity, followed by the similarity
in content and visual presentations. Besides these
findings, we also investigate the relationship between
diversity and satisfaction in image search.
Specifically, we find that users' preference for
diversity varies across different search intents. When
users want to collect information or save images for
further usage (the Locate search tasks), more
diversified result lists lead to higher satisfaction
levels. The insights may help commercial image search
engines to design better result ranking strategies and
evaluation metrics.",
acknowledgement = ack-nhfb,
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Arguello:2019:EWM,
author = "Jaime Arguello and Bogeum Choi",
title = "The Effects of Working Memory, Perceptual Speed, and
Inhibition in Aggregated Search",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "36:1--36:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3322128",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3322128",
abstract = "Prior work has studied how different characteristics
of individual users (e.g., personality traits and
cognitive abilities) can impact search behaviors and
outcomes. We report on a laboratory study ( N = 32)
that investigated the effects of three different
cognitive abilities (perceptual speed, working memory,
and inhibition) in the context of aggregated search.
Aggregated search systems combine results from multiple
heterogeneous sources (or verticals ) in a unified
presentation. Participants in our study interacted with
two different aggregated search interfaces (a
within-subjects design) that differed based on the
extent to which the layout distinguished between
results originating from different verticals. The
interleaved interface merged results from different
verticals in a fairly unconstrained fashion.
Conversely, the blocked interface displayed results
from the same vertical as a group, displayed each group
of vertical results in the same region on the SERP for
every query, and used a border around each group of
vertical results to help distinguish among results from
different sources. We investigated three research
questions (RQ1--RQ3). Specifically, we investigated the
effects of the interface condition and each cognitive
ability on three types of outcomes: (RQ1) participants'
levels of workload, (RQ2) participants' levels of user
engagement, and (RQ3) participants' search behaviors.
Our results found different main and interaction
effects. Perceptual speed and inhibition did not
significantly affect participants' workload and user
engagement but significantly affected their search
behaviors. Specifically, with the interleaved
interface, participants with lower perceptual speed had
more difficulty finding relevant results on the SERP,
and participants with lower inhibitory attention
control searched at a slower pace. Working memory did
not have a strong effect on participants' behaviors but
had several significant effects on the levels of
workload and user engagement reported by participants.
Specifically, participants with lower working memory
reported higher levels of workload and lower levels of
user engagement. We discuss implications of our results
for designing aggregated search interfaces that are
well suited for users with different cognitive
abilities.",
acknowledgement = ack-nhfb,
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Esuli:2019:FNE,
author = "Andrea Esuli and Alejandro Moreo and Fabrizio
Sebastiani",
title = "Funnelling: a New Ensemble Method for Heterogeneous
Transfer Learning and Its Application to Cross-Lingual
Text Classification",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "37:1--37:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3326065",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3326065",
abstract = "Cross-lingual Text Classification (CLC) consists of
automatically classifying, according to a common set C
of classes, documents each written in one of a set of
languages L, and doing so more accurately than when
``na{\"\i}vely'' classifying each document via its
corresponding language-specific classifier. To obtain
an increase in the classification accuracy for a given
language, the system thus needs to also leverage the
training examples written in the other languages. We
tackle ``multilabel'' CLC via funnelling, a new
ensemble learning method that we propose here.
Funnelling consists of generating a two-tier
classification system where all documents, irrespective
of language, are classified by the same (second-tier)
classifier. For this classifier, all documents are
represented in a common, language-independent feature
space consisting of the posterior probabilities
generated by first-tier, language-dependent
classifiers. This allows the classification of all test
documents, of any language, to benefit from the
information present in all training documents, of any
language. We present substantial experiments, run on
publicly available multilingual text collections, in
which funnelling is shown to significantly outperform a
number of state-of-the-art baselines. All code and
datasets (in vector form) are made publicly
available.",
acknowledgement = ack-nhfb,
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2019:SRR,
author = "Yiqun Liu and Junqi Zhang and Jiaxin Mao and Min Zhang
and Shaoping Ma and Qi Tian and Yanxiong Lu and Leyu
Lin",
title = "Search Result Reranking with Visual and Structure
Information Sources",
journal = j-TOIS,
volume = "37",
number = "3",
pages = "38:1--38:??",
month = jul,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3329188",
ISSN = "1046-8188",
bibdate = "Sat Sep 21 11:52:00 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3329188",
abstract = "Relevance estimation is among the most important tasks
in the ranking of search results. Current methodologies
mainly concentrate on text matching, link analysis, and
user behavior models. However, users judge the
relevance of search results directly from Search Engine
Result Pages (SERPs), which provide valuable signals
for reranking. In this article, we propose two
different approaches to aggregate the visual,
structure, as well as textual information sources of
search results in relevance estimation. The first one
is a late-fusion framework named Joint Relevance
Estimation model (JRE). JRE estimates the relevance
independently from screenshots, textual contents, and
HTML source codes of search results and jointly makes
the final decision through an inter-modality attention
mechanism. The second one is an early-fusion framework
named Tree-based Deep Neural Network (TreeNN), which
embeds the texts and images into the HTML parse tree
through a recursive process. To evaluate the
performance of the proposed models, we construct a
large-scale practical Search Result Relevance (SRR)
dataset that consists of multiple information sources
and relevance labels of over 60,000 search results.
Experimental results show that the proposed two models
achieve better performance than state-of-the-art
ranking solutions as well as the original rankings of
commercial search engines.",
acknowledgement = ack-nhfb,
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Chen:2019:JNC,
author = "Wanyu Chen and Fei Cai and Honghui Chen and Maarten
{De Rijke}",
title = "Joint Neural Collaborative Filtering for Recommender
Systems",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "39:1--39:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3343117",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3343117",
abstract = "We propose a Joint Neural Collaborative Filtering
(J-NCF) method for recommender systems. The J-NCF model
applies a joint neural network that couples deep
feature learning and deep interaction modeling with a
rating matrix. Deep feature learning extracts feature
representations of users and items with a deep learning
architecture based on a user-item rating matrix. Deep
interaction modeling captures non-linear user-item
interactions with a deep neural network using the
feature representations generated by the deep feature
learning process as input. J-NCF enables the deep
feature learning and deep interaction modeling
processes to optimize each other through joint
training, which leads to improved recommendation
performance. In addition, we design a new loss function
for optimization that takes both implicit and explicit
feedback, point-wise and pair-wise loss into account.
Experiments on several real-world datasets show
significant improvements of J-NCF over state-of-the-art
methods, with improvements of up to 8.24\% on the
MovieLens 100K dataset, 10.81\% on the MovieLens 1M
dataset, and 10.21\% on the Amazon Movies dataset in
terms of HR@10. NDCG@10 improvements are 12.42\%,
14.24\%, and 15.06\%, respectively. We also conduct
experiments to evaluate the scalability and sensitivity
of J-NCF. Our experiments show that the J-NCF model has
a competitive recommendation performance with inactive
users and different degrees of data sparsity when
compared to state-of-the-art baselines.",
acknowledgement = ack-nhfb,
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2019:QAK,
author = "Richong Zhang and Yue Wang and Yongyi Mao and Jinpeng
Huai",
title = "Question Answering in Knowledge Bases: a Verification
Assisted Model with Iterative Training",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "40:1--40:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3345557",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3345557",
abstract = "Question answering over knowledge bases aims to take
full advantage of the information in knowledge bases
with the ultimate purpose of returning answers to
questions. To access the substantial knowledge within
the KB, many model architectures are hindered by the
bottleneck of accurately predicting relations that
connect subject entities in questions to object
entities in the knowledge base. To break the
bottleneck, this article presents a novel model
architecture, APVA, which includes a verification
mechanism to check the correctness of predicted
relations. Specifically, APVA takes advantage of
KB-based information to improve relation prediction but
verifies the correctness of the predicted relation by
means of simple negative sampling in a logistic
regression framework. The APVA architecture offers a
natural way to integrate an iterative training
procedure, which we call turbo training. Accordingly,
we introduce APVA-TURBO to perform question answering
over knowledge bases. We demonstrate extensive
experiments to show that APVA-TURBO outperforms
existing approaches on question answering.",
acknowledgement = ack-nhfb,
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Benham:2019:BSP,
author = "Rodger Benham and Joel Mackenzie and Alistair Moffat
and J. Shane Culpepper",
title = "Boosting Search Performance Using Query Variations",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "41:1--41:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3345001",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3345001",
abstract = "Rank fusion is a powerful technique that allows
multiple sources of information to be combined into a
single result set. Query variations covering the same
information need represent one way in which different
sources of information might arise. However, when
implemented in the obvious manner, fusion over query
variations is not cost-effective, at odds with the
usual web-search requirement for strict per-query
efficiency guarantees. In this work, we propose a novel
solution to query fusion by splitting the computation
into two parts: one phase that is carried out offline,
to generate pre-computed centroid answers for queries
addressing broadly similar information needs, and then
a second online phase that uses the corresponding topic
centroid to compute a result page for each query. To
achieve this, we make use of score-based fusion
algorithms whose costs can be amortized via the
pre-processing step and that can then be efficiently
combined during subsequent per-query re-ranking
operations. Experimental results using the ClueWeb12B
collection and the UQV100 query variations demonstrate
that centroid-based approaches allow improved retrieval
effectiveness at little or no loss in query throughput
or latency and within reasonable pre-processing
requirements. We additionally show that queries that do
not match any of the pre-computed clusters can be
accurately identified and efficiently processed in our
proposed ranking pipeline.",
acknowledgement = ack-nhfb,
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Tamine:2019:OVO,
author = "Lynda Tamine and Laure Soulier and Gia-Hung Nguyen and
Nathalie Souf",
title = "Offline versus Online Representation Learning of
Documents Using External Knowledge",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "42:1--42:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3349527",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3349527",
abstract = "An intensive recent research work investigated the
combined use of hand-curated knowledge resources and
corpus-driven resources to learn effective text
representations. The overall learning process could be
run by online revising the learning objective or by
offline refining an original learned representation.
The differentiated impact of each of the learning
approaches on the quality of the learned
representations has not been studied so far in the
literature. This article focuses on the design of
comparable offline vs. online knowledge-enhanced
document representation learning models and the
comparison of their effectiveness using a set of
standard IR and NLP downstream tasks. The results of
quantitative and qualitative analyses show that (1)
offline vs. online learning approaches have dissimilar
result trends regarding the task as well as the dataset
distribution counts with regard to domain application;
(2) while considering external knowledge resources is
undoubtedly beneficial, the way used to express
relational constraints could affect semantic inference
effectiveness. The findings of this work present
opportunities for the design of future representation
learning models, but also for providing insights about
the evaluation of such models.",
acknowledgement = ack-nhfb,
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zheng:2019:CCM,
author = "Yukun Zheng and Jiaxin Mao and Yiqun Liu and Cheng Luo
and Min Zhang and Shaoping Ma",
title = "Constructing Click Model for Mobile Search with
Viewport Time",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "43:1--43:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3360486",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3360486",
abstract = "A series of click models has been proposed to extract
accurate and unbiased relevance feedback from valuable
yet noisy click-through data in search logs. Previous
works have shown that users search behavior in mobile
and desktop scenarios are rather different in many
aspects, therefore, the click models designed for
desktop search may not be effective in the mobile
context. To address this problem, we propose two novel
click models for mobile search: (1) Mobile Click Model
(MCM), which models click necessity bias and
examination satisfaction bias; (2) Viewport Time Click
Model (VTCM), which further extends MCM by utilizing
the viewport time. Extensive experiments on large-scale
real mobile search logs show that: (1) MCM and VTCM
outperform existing models in predicting users' clicks
and estimating result relevance; (2) MCM and VTCM can
extract richer information, such as the click necessity
of search results and the probability of user
satisfaction, from mobile click logs; (3) By modeling
the viewport time distributions of heterogeneous
results, VTCM can bring a significant improvement over
MCM in click prediction and relevance estimation tasks.
Our proposed click models can help better understand
user behavior patterns in mobile search and improve the
ranking performance of mobile search engines.",
acknowledgement = ack-nhfb,
articleno = "43",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Raiber:2019:RFW,
author = "Fiana Raiber and Oren Kurland",
title = "Relevance Feedback: The Whole Is Inferior to the Sum
of Its Parts",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "44:1--44:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3360487",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3360487",
abstract = "Document retrieval methods that utilize relevance
feedback often induce a single query model from the set
of feedback documents, specifically, the relevant
documents. We empirically show that for a few
state-of-the-art query-model induction methods,
retrieval performance can be significantly improved by
constructing the query model from a subset of the
relevant documents rather than from all of them.
Motivated by this finding, we propose a new approach
for relevance-feedback-based retrieval. The approach,
derived from the risk minimization framework, is based
on utilizing multiple query models induced from all
subsets of the given relevant documents. Empirical
evaluation shows that the approach posts performance
that is statistically significantly better than that of
applying the standard practice of utilizing a single
query model induced from the relevant documents. While
the average relative improvements are small to
moderate, the robustness of the approach is
substantially higher than that of a variety of
reference comparison methods that address various
challenges in using relevance feedback.",
acknowledgement = ack-nhfb,
articleno = "44",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Liu:2019:ALL,
author = "Huafeng Liu and Liping Jing and Yuhua Qian and Jian
Yu",
title = "Adaptive Local Low-rank Matrix Approximation for
Recommendation",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "45:1--45:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3360488",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3360488",
abstract = "Low-rank matrix approximation (LRMA) has attracted
more and more attention in the community of
recommendation. Even though LRMA-based recommendation
methods (including Global LRMA and Local LRMA) obtain
promising results, they suffer from the complicated
structure of the large-scale and sparse rating matrix,
especially when the underlying system includes a large
set of items with various types and a huge amount of
users with diverse interests. Thus, they have to
predefine the important parameters, such as the rank of
the rating matrix and the number of submatrices.
Moreover, most existing Local LRMA methods are usually
designed in a two-phase separated framework and do not
consider the missing mechanisms of rating matrix. In
this article, a non-parametric unified Bayesian
graphical model is proposed for Adaptive Local
low-rank Matrix Approximation (ALoMA). ALoMA has
ability to simultaneously identify rating submatrices,
determine the optimal rank for each submatrix, and
learn the submatrix-specific user/item latent factors.
Meanwhile, the missing mechanism is adopted to
characterize the whole rating matrix. These four parts
are seamlessly integrated and enhance each other in a
unified framework. Specifically, the user-item rating
matrix is adaptively divided into proper number of
submatrices in ALoMA by exploiting the Chinese
Restaurant Process. For each submatrix, by considering
both global/local structure information and missing
mechanisms, the latent user/item factors are identified
in an optimal latent space by adopting automatic
relevance determination technique. We theoretically
analyze the model's generalization error bounds and
give an approximation guarantee. Furthermore, an
efficient Gibbs sampling-based algorithm is designed to
infer the proposed model. A series of experiments have
been conducted on six real-world datasets ( Epinions,
Douban, Dianping, Yelp, Movielens (10M), and Netflix ).
The results demonstrate that ALoMA outperforms the
state-of-the-art LRMA-based methods and can easily
provide interpretable recommendation results.",
acknowledgement = ack-nhfb,
articleno = "45",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Li:2019:NNN,
author = "Xin Li and Dongcheng Han and Jing He and Lejian Liao
and Mingzhong Wang",
title = "Next and Next New {POI} Recommendation via Latent
Behavior Pattern Inference",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "46:1--46:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3354187",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3354187",
abstract = "Next and next new point-of-interest (POI)
recommendation are essential instruments in promoting
customer experiences and business operations related to
locations. However, due to the sparsity of the check-in
records, they still remain insufficiently studied. In
this article, we propose to utilize personalized latent
behavior patterns learned from contextual features,
e.g., time of day, day of week, and location category,
to improve the effectiveness of the recommendations.
Two variations of models are developed, including GPDM,
which learns a fixed pattern distribution for all
users; and PPDM, which learns personalized pattern
distribution for each user. In both models, a soft-max
function is applied to integrate the personalized
Markov chain with the latent patterns, and a sequential
Bayesian Personalized Ranking (S-BPR) is applied as the
optimization criterion. Then, Expectation Maximization
(EM) is in charge of finding optimized model
parameters. Extensive experiments on three large-scale
commonly adopted real-world LBSN data sets prove that
the inclusion of location category and latent patterns
helps to boost the performance of POI recommendations.
Specifically, our models in general significantly
outperform other state-of-the-art methods for both next
and next new POI recommendation tasks. Moreover, our
models are capable of making accurate recommendations
regardless of the short/long duration or distance.",
acknowledgement = ack-nhfb,
articleno = "46",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Du:2019:MED,
author = "Xiaoyu Du and Xiangnan He and Fajie Yuan and Jinhui
Tang and Zhiguang Qin and Tat-Seng Chua",
title = "Modeling Embedding Dimension Correlations via
Convolutional Neural Collaborative Filtering",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "47:1--47:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3357154",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3357154",
abstract = "As the core of recommender systems, collaborative
filtering (CF) models the affinity between a user and
an item from historical user-item interactions, such as
clicks, purchases, and so on. Benefiting from the
strong representation power, neural networks have
recently revolutionized the recommendation research,
setting up a new standard for CF. However, existing
neural recommender models do not explicitly consider
the correlations among embedding dimensions, making
them less effective in modeling the interaction
function between users and items. In this work, we
emphasize on modeling the correlations among embedding
dimensions in neural networks to pursue higher
effectiveness for CF. We propose a novel and general
neural collaborative filtering framework-namely,
ConvNCF, which is featured with two designs: (1)
applying outer product on user embedding and item
embedding to explicitly model the pairwise correlations
between embedding dimensions, and (2) employing
convolutional neural network above the outer product to
learn the high-order correlations among embedding
dimensions. To justify our proposal, we present three
instantiations of ConvNCF by using different inputs to
represent a user and conduct experiments on two
real-world datasets. Extensive results verify the
utility of modeling embedding dimension correlations
with ConvNCF, which outperforms several competitive CF
methods.",
acknowledgement = ack-nhfb,
articleno = "47",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lin:2019:EPR,
author = "Xiao Lin and Min Zhang and Yiqun Liu and Shaoping Ma",
title = "Enhancing Personalized Recommendation by Implicit
Preference Communities Modeling",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "48:1--48:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3352592",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3352592",
abstract = "Recommender systems aim to capture user preferences
and provide accurate recommendations to users
accordingly. For each user, there usually exist others
with similar preferences, and a collection of users may
also have similar preferences with each other, thus
forming a community. However, such communities may not
necessarily be explicitly given, and the users inside
the same communities may not know each other; they are
formally defined and named Implicit Preference
Communities (IPCs) in this article. By enriching user
preferences with the information of other users in the
communities, the performance of recommender systems can
also be enhanced. Historical explicit ratings are a
good resource to construct the IPCs of users but is
usually sparse. Meanwhile, user preferences are easily
affected by their social connections, which can be
jointly used for IPC modeling with the ratings.
However, this imposes two challenges for model design.
First, the rating and social domains are heterogeneous;
thus, it is challenging to coordinate social
information and rating behaviors for a same learning
task. Therefore, transfer learning is a good strategy
for IPC modeling. Second, the communities are not
explicitly labeled, and existing supervised learning
approaches do not fit the requirement of IPC modeling.
As co-clustering is an effective unsupervised learning
approach for discovering block structures in
high-dimensional data, it is a cornerstone for
discovering the structure of IPCs. In this article, we
propose a recommendation model with Implicit Preference
Communities from user ratings and social connections.
To tackle the unsupervised learning limitation, we
design a Bayesian probabilistic graphical model to
capture the IPC structure for recommendation.
Meanwhile, following the spirit of transfer learning,
both rating behaviors and social connections are
introduced into the model by parameter sharing.
Moreover, Gibbs sampling-based algorithms are proposed
for parameter inferences of the models. Furthermore, to
meet the need for online scenarios when the data arrive
sequentially as a stream, a novel online sampling-based
parameter inference algorithm for recommendation is
proposed. To the best of our knowledge, this is the
first attempt to propose and formally define the
concept of IPC.",
acknowledgement = ack-nhfb,
articleno = "48",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{deRijke:2019:RAT,
author = "Maarten de Rijke",
title = "Reviewers for {{\booktitle{ACM Transactions on
Information Systems}}} Volume 37",
journal = j-TOIS,
volume = "37",
number = "4",
pages = "49:1--49:??",
month = dec,
year = "2019",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3365367",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3365367",
acknowledgement = ack-nhfb,
articleno = "49",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Han:2020:GDR,
author = "Jungkyu Han and Hayato Yamana",
title = "Geographic Diversification of Recommended {POIs} in
Frequently Visited Areas",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "1:1--1:??",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3362505",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3362505",
abstract = "In the personalized Point-Of-Interest (POI) (or venue)
recommendation, the diversity of recommended POIs is an
important aspect. Diversity is especially important
when POIs are recommended in the target users'
frequently visited areas, because users are likely to
revisit such areas. In addition to the (POI) category
diversity that is a popular diversification objective
in recommendation domains, diversification of
recommended POI locations is an interesting subject
itself. Despite its importance, existing POI
recommender studies generally focus on and evaluate
prediction accuracy. In this article, geographical
diversification (geo-diversification), a novel
diversification concept that aims to increase
recommendation coverage for a target users' geographic
areas of interest, is introduced, from which a method
that improves geo-diversity as an addition to existing
state-of-the-art POI recommenders is proposed. In
experiments with the datasets from two real Location
Based Social Networks (LSBNs), we first analyze the
performance of four state-of-the-art POI recommenders
from various evaluation perspectives including category
diversity and geo-diversity that have not been examined
previously. The proposed method consistently improves
geo-diversity (CPR(geo)@20) by 5 to 12\% when combined
with four state-of-the-art POI recommenders with
negligible prediction accuracy (Recall@20) loss and
provides 6 to 18\% geo-diversity improvement with
tolerable prediction accuracy loss (up to 2.4\%).",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2020:UAC,
author = "Xiaoying Zhang and Hong Xie and Junzhou Zhao and John
C. S. Lui",
title = "Understanding Assimilation-contrast Effects in Online
Rating Systems: Modelling, Debiasing, and
Applications",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "2:1--2:??",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3362651",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3362651",
abstract = "``Unbiasedness,'' which is an important property to
ensure that users' ratings indeed reflect their true
evaluations of products, is vital both in shaping
consumer purchase decisions and providing reliable
recommendations in online rating systems. Recent
experimental studies showed that distortions from
historical ratings would ruin the unbiasedness of
subsequent ratings. How to ``discover'' historical
distortions in each single rating (or at the
micro-level), and perform the ``debiasing operations''
are our main objective. Using 42M real customer
ratings, we first show that users either ``assimilate''
or ``contrast'' to historical ratings under different
scenarios, which can be further explained by a
well-known psychological argument: the
``Assimilate-Contrast'' theory. This motivates us to
propose the Historical Influence Aware Latent Factor
Model (HIALF), the ``first'' model for real rating
systems to capture and mitigate historical distortions
in each single rating. HIALF allows us to study the
influence patterns of historical ratings from a
modelling perspective, which perfectly matches the
assimilation and contrast effects observed in
experiments. Moreover, HIALF achieves significant
improvements in predicting subsequent ratings and
characterizing relationships in ratings. It also
contributes to better recommendations, wiser consumer
purchase decisions, and deeper understanding of
historical distortions in both honest rating and
misbehaving rating settings.",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Lv:2020:BAR,
author = "Pengtao Lv and Xiangwu Meng and Yujie Zhang",
title = "{BoRe}: Adapting to Reader Consumption Behavior
Instability for News Recommendation",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "3:1--3:??",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3361217",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3361217",
abstract = "News recommendation has become an essential way to
help readers discover interesting stories. While a
growing line of research has focused on modeling
reading preferences for news recommendation, they
neglect the instability of reader consumption
behaviors, i.e., consumption behaviors of readers may
be influenced by other factors in addition to user
interests, which degrades the recommendation
effectiveness of existing methods. In this article, we
propose a probabilistic generative model, BoRe, where
user interests and crowd effects are used to adapt to
the instability of reader consumption behaviors, and
reading sequences are utilized to adapt user interests
evolving over time. Further, the extreme sparsity
problem in the domain of news severely hinders
accurately modeling user interests and reading
sequences, which discounts BoRe's ability to adapt to
the instability. Accordingly, we leverage
domain-specific features to model user interests in the
situation of extreme sparsity. Meanwhile, we consider
groups of users instead of individuals to capture
reading sequences. Besides, we study how to reduce the
computation to allow online application. Extensive
experiments have been conducted to evaluate the
effectiveness and efficiency of BoRe on real-world
datasets. The experimental results show the superiority
of BoRe, compared with the state-of-the-art competing
methods.",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Ai:2020:EPS,
author = "Qingyao Ai and Yongfeng Zhang and Keping Bi and W.
Bruce Croft",
title = "Explainable Product Search with a Dynamic Relation
Embedding Model",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "4:1--4:??",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3361738",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3361738",
abstract = "Product search is one of the most popular methods for
customers to discover products online. Most existing
studies on product search focus on developing effective
retrieval models that rank items by their likelihood to
be purchased. However, they ignore the problem that
there is a gap between how systems and customers
perceive the relevance of items. Without explanations,
users may not understand why product search engines
retrieve certain items for them, which consequentially
leads to imperfect user experience and suboptimal
system performance in practice. In this work, we tackle
this problem by constructing explainable retrieval
models for product search. Specifically, we propose to
model the ``search and purchase'' behavior as a dynamic
relation between users and items, and create a dynamic
knowledge graph based on both the multi-relational
product data and the context of the search session.
Ranking is conducted based on the relationship between
users and items in the latent space, and explanations
are generated with logic inferences and entity soft
matching on the knowledge graph. Empirical experiments
show that our model, which we refer to as the Dynamic
Relation Embedding Model (DREM), significantly
outperforms the state-of-the-art baselines and has the
ability to produce reasonable explanations for search
results.",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Zhang:2020:MLC,
author = "Dong Zhang and Shu Zhao and Zhen Duan and Jie Chen and
Yanping Zhang and Jie Tang",
title = "A Multi-Label Classification Method Using a
Hierarchical and Transparent Representation for
Paper-Reviewer Recommendation",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "5:1--5:20",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3361719",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:56:24 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3361719",
abstract = "The paper-reviewer recommendation task is of
significant academic importance for conference chairs
and journal editors. It aims to recommend appropriate
experts in a discipline to comment on the quality of
papers of others in that discipline. How to \ldots{}",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ahmad:2020:DLA,
author = "Faizan Ahmad and Ahmed Abbasi and Jingjing Li and
David G. Dobolyi and Richard G. Netemeyer and Gari D.
Clifford and Hsinchun Chen",
title = "A Deep Learning Architecture for Psychometric Natural
Language Processing",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "6:1--6:29",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3365211",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:56:24 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3365211",
abstract = "Psychometric measures reflecting people's knowledge,
ability, attitudes, and personality traits are critical
for many real-world applications, such as e-commerce,
health care, and cybersecurity. However, traditional
methods cannot collect and measure \ldots{}",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zeng:2020:NIR,
author = "Zijie Zeng and Jing Lin and Lin Li and Weike Pan and
Zhong Ming",
title = "Next-Item Recommendation via Collaborative Filtering
with Bidirectional Item Similarity",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "7:1--7:22",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3366172",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:56:24 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3366172",
abstract = "Exploiting temporal effect has empirically been
recognized as a promising way to improve recommendation
performance in recent years. In real-world
applications, one-class data in the form of (user,
item, timestamp) are usually more accessible and
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sun:2020:ECG,
author = "Xiao Sun and Jia Li and Xing Wei and Changliang Li and
Jianhua Tao",
title = "Emotional Conversation Generation Based on a
{Bayesian} Deep Neural Network",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "8:1--8:24",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3368960",
ISSN = "1046-8188",
bibdate = "Wed Dec 11 07:07:43 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
abstract = "The field of conversation generation using neural
networks has attracted increasing attention from
researchers for several years. However, traditional
neural language models tend to generate a generic reply
with poor semantic logic and no emotion. This article
proposes an emotional conversation generation model
based on a Bayesian deep neural network that can
generate replies with rich emotions, clear themes, and
diverse sentences. The topic and emotional keywords of
the replies are pregenerated by introducing commonsense
knowledge in the model. The reply is divided into
multiple clauses, and then a multidimensional generator
based on the transformer mechanism proposed in this
article is used to iteratively generate clauses from
two dimensions: sentence granularity and sentence
structure. Subjective and objective experiments prove
that compared with existing models, the proposed model
effectively improves the semantic logic and emotional
accuracy of replies. This model also significantly
enhances the diversity of replies, largely overcoming
the shortcomings of traditional models that generate
safe replies.",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J779",
}
@Article{Choi:2020:ETC,
author = "Bogeum Choi and Austin Ward and Yuan Li and Jaime
Arguello and Robert Capra",
title = "The Effects of Task Complexity on the Use of Different
Types of Information in a Search Assistance Tool",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "9:1--9:28",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3371707",
ISSN = "1046-8188",
bibdate = "Mon Feb 10 12:32:39 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3371707",
abstract = "In interactive information retrieval, an important
research question is: How do task characteristics
influence users' needs and behaviors? We report on a
laboratory study $(N = 32)$ that investigated the
effects of task complexity on the types of \ldots{}",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Thomas:2020:ISM,
author = "Paul Thomas and Bodo Billerbeck and Nick Craswell and
Ryen W. White",
title = "Investigating Searchers' Mental Models to Inform
Search Explanations",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "10:1--10:25",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3371390",
ISSN = "1046-8188",
bibdate = "Mon Feb 10 12:32:39 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3371390",
abstract = "Modern web search engines use many signals to select
and rank results in response to queries. However,
searchers' mental models of search are relatively
unsophisticated, hindering their ability to use search
engines efficiently and effectively. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ding:2020:IIR,
author = "Jingtao Ding and Guanghui Yu and Yong Li and Xiangnan
He and Depeng Jin",
title = "Improving Implicit Recommender Systems with Auxiliary
Data",
journal = j-TOIS,
volume = "38",
number = "1",
pages = "11:1--11:27",
month = feb,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3372338",
ISSN = "1046-8188",
bibdate = "Mon Feb 10 12:32:39 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3372338",
abstract = "Most existing recommender systems leverage the primary
feedback only, despite the fact that users also
generate a large amount of auxiliary feedback. These
feedback usually indicate different user preferences
when comparing to the primary feedback \ldots{}",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2020:LVF,
author = "Yifan Chen and Yang Wang and Xiang Zhao and Hongzhi
Yin and Ilya Markov and MAARTEN De Rijke",
title = "Local Variational Feature-Based Similarity Models for
Recommending Top-{$N$} New Items",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "12:1--12:33",
month = mar,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3372154",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:51:00 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3372154",
abstract = "The top-$N$ recommendation problem has been studied
extensively. Item-based collaborative filtering
recommendation algorithms show promising results for
the problem. They predict a user's preferences by
estimating similarities between a target and
user-\ldots{}",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Arapakis:2020:PPA,
author = "Ioannis Arapakis and Antonio Penta and Hideo Joho and
Luis A. Leiva",
title = "A Price-per-attention Auction Scheme Using Mouse
Cursor Information",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "13:1--13:30",
month = jan,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3374210",
ISSN = "1046-8188",
bibdate = "Mon Feb 10 12:32:40 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3374210",
abstract = "Payments in online ad auctions are typically derived
from click-through rates, so that advertisers do not
pay for ineffective ads. But advertisers often care
about more than just clicks. That is, for example, if
they aim to raise brand awareness or \ldots{}",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2020:ENM,
author = "Chong Chen and Min Zhang and Yongfeng Zhang and Yiqun
Liu and Shaoping Ma",
title = "Efficient Neural Matrix Factorization without Sampling
for Recommendation",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "14:1--14:28",
month = jan,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3373807",
ISSN = "1046-8188",
bibdate = "Mon Feb 10 12:32:40 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3373807",
abstract = "Recommendation systems play a vital role to keep users
engaged with personalized contents in modern online
platforms. Recently, deep learning has revolutionized
many research fields and there is a surge of interest
in applying it for recommendation. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qin:2020:ENN,
author = "Chuan Qin and Hengshu Zhu and Tong Xu and Chen Zhu and
Chao Ma and Enhong Chen and Hui Xiong",
title = "An Enhanced Neural Network Approach to Person-Job Fit
in Talent Recruitment",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "15:1--15:33",
month = mar,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3376927",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:51:00 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3376927",
abstract = "The widespread use of online recruitment services has
led to an information explosion in the job market. As a
result, recruiters have to seek intelligent ways for
Person-Job Fit, which is the bridge for adapting the
right candidates to the right \ldots{}",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Meng:2020:JLR,
author = "Zaiqiao Meng and Shangsong Liang and Xiangliang Zhang
and Richard McCreadie and Iadh Ounis",
title = "Jointly Learning Representations of Nodes and
Attributes for Attributed Networks",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "16:1--16:32",
month = jan,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3377850",
ISSN = "1046-8188",
bibdate = "Mon Feb 10 12:32:40 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3377850",
abstract = "Previous embedding methods for attributed networks aim
at learning low-dimensional vector representations only
for nodes but not for both nodes and attributes,
resulting in the fact that node embeddings cannot be
directly used to recover the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2020:LSR,
author = "Wayne Xin Zhao and Yupeng Hou and Junhua Chen and
Jonathan J. H. Zhu and Eddy Jing Yin and Hanting Su and
Ji-Rong Wen",
title = "Learning Semantic Representations from Directed Social
Links to Tag Microblog Users at Scale",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "17:1--17:30",
month = mar,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3377550",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:51:00 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3377550",
abstract = "This article presents a network embedding approach to
automatically generate tags for microblog users.
Instead of using text data, we aim to annotate
microblog users with meaningful tags by leveraging rich
social link data. To utilize directed social \ldots{}",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Naskar:2020:EDP,
author = "Debashis Naskar and Sanasam Ranbir Singh and Durgesh
Kumar and Sukumar Nandi and Eva Onaindia de la
Rivaherrera",
title = "Emotion Dynamics of Public Opinions on {Twitter}",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "18:1--18:24",
month = mar,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3379340",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:51:00 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3379340",
abstract = "Recently, social media has been considered the fastest
medium for information broadcasting and sharing.
Considering the wide range of applications such as
viral marketing, political campaigns, social
advertisement, and so on, influencing characteristics
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Huang:2020:LFD,
author = "Zhenya Huang and Qi Liu and Yuying Chen and Le Wu and
Keli Xiao and Enhong Chen and Haiping Ma and Guoping
Hu",
title = "Learning or Forgetting? {A} Dynamic Approach for
Tracking the Knowledge Proficiency of Students",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "19:1--19:33",
month = mar,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3379507",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:51:00 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3379507",
abstract = "The rapid development of the technologies for online
learning provides students with extensive resources for
self-learning and brings new opportunities for
data-driven research on educational management. An
important issue of online learning is to \ldots{}",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Nie:2020:LSQ,
author = "Liqiang Nie and Yongqi Li and Fuli Feng and Xuemeng
Song and Meng Wang and Yinglong Wang",
title = "Large-Scale Question Tagging via Joint Question-Topic
Embedding Learning",
journal = j-TOIS,
volume = "38",
number = "2",
pages = "20:1--20:23",
month = mar,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3380954",
ISSN = "1046-8188",
bibdate = "Thu Mar 19 10:51:00 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3380954",
abstract = "Recent years have witnessed a flourishing of
community-driven question answering (cQA), like Yahoo!
Answers and AnswerBag, where people can seek precise
information. After 2010, some novel cQA systems,
including Quora and Zhihu, gained momentum. Besides
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Huang:2020:CBI,
author = "Minlie Huang and Xiaoyan Zhu and Jianfeng Gao",
title = "Challenges in Building Intelligent Open-domain Dialog
Systems",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "21:1--21:32",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3383123",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3383123",
abstract = "There is a resurgent interest in developing
intelligent open-domain dialog systems due to the
availability of large amounts of conversational data
and the recent progress on neural approaches to
conversational AI [33]. Unlike traditional
task-oriented \ldots{}",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qiu:2020:ECS,
author = "Ruihong Qiu and Zi Huang and Jingjing Li and Hongzhi
Yin",
title = "Exploiting Cross-session Information for Session-based
Recommendation with Graph Neural Networks",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "22:1--22:23",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3382764",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3382764",
abstract = "Different from the traditional recommender system, the
session-based recommender system introduces the concept
of the session, i.e., a sequence of interactions
between a user and multiple items within a period, to
preserve the user's recent interest. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{deOliveira:2020:OSA,
author = "Wyverson Bonasoli de Oliveira and Leyza Baldo Dorini
and Rodrigo Minetto and Thiago H. Silva",
title = "{OutdoorSent}: Sentiment Analysis of Urban Outdoor
Images by Using Semantic and Deep Features",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "23:1--23:28",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3385186",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3385186",
abstract = "Opinion mining in outdoor images posted by users
during different activities can provide valuable
information to better understand urban areas. In this
regard, we propose a framework to classify the
sentiment of outdoor images shared by users on social
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Jagerman:2020:SEO,
author = "Rolf Jagerman and Ilya Markov and Maarten {De Rijke}",
title = "Safe Exploration for Optimizing Contextual Bandits",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "24:1--24:23",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3385670",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3385670",
abstract = "Contextual bandit problems are a natural fit for many
information retrieval tasks, such as learning to rank,
text classification, recommendation, and so on.
However, existing learning methods for contextual
bandit problems have one of two drawbacks: \ldots{}",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2020:FDN,
author = "Yang Liu and Yi-Fang Brook Wu",
title = "{FNED}: a Deep Network for Fake News Early Detection
on Social Media",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "25:1--25:33",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3386253",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3386253",
abstract = "The fast spreading of fake news stories on social
media can cause inestimable social harm. Developing
effective methods to detect them early is of paramount
importance. A major challenge of fake news early
detection is fully utilizing the limited data
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Alserafi:2020:KDL,
author = "Ayman Alserafi and Alberto Abell{\'o} and Oscar Romero
and Toon Calders",
title = "Keeping the Data Lake in Form: Proximity Mining for
Pre-Filtering Schema Matching",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "26:1--26:30",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3388870",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3388870",
abstract = "Data lakes (DLs) are large repositories of raw
datasets from disparate sources. As more datasets are
ingested into a DL, there is an increasing need for
efficient techniques to profile them and to detect the
relationships among their schemata, commonly \ldots{}",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zou:2020:TQB,
author = "Jie Zou and Evangelos Kanoulas",
title = "Towards Question-based High-recall Information
Retrieval: Locating the Last Few Relevant Documents for
Technology-assisted Reviews",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "27:1--27:35",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3388640",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3388640",
abstract = "While continuous active learning algorithms have
proven effective in finding most of the relevant
documents in a collection, the cost for locating the
last few remains high for applications such as
Technology-assisted Reviews (TAR). To locate these last
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Huang:2020:NHN,
author = "Jie Huang and Chuan Chen and Fanghua Ye and Weibo Hu
and Zibin Zheng",
title = "Nonuniform Hyper-Network Embedding with Dual
Mechanism",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "28:1--28:18",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3388924",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3388924",
abstract = "Network embedding which aims to learn the
low-dimensional representations for vertices in
networks has been extensively studied in recent years.
Although there are various models designed for networks
with different properties and different structures
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Tonellotto:2020:UII,
author = "Nicola Tonellotto and Craig Macdonald",
title = "Using an Inverted Index Synopsis for Query Latency and
Performance Prediction",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "29:1--29:33",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3389795",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3389795",
abstract = "Predicting the query latency by a search engine has
important benefits, for instance, in allowing the
search engine to adjust its configuration to address
long-running queries without unnecessarily sacrificing
its effectiveness. However, for the dynamic \ldots{}",
acknowledgement = ack-nhfb,
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Cheng:2020:RUC,
author = "Miaomiao Cheng and Liping Jing and Michael K. Ng",
title = "Robust Unsupervised Cross-modal Hashing for Multimedia
Retrieval",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "30:1--30:25",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3389547",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3389547",
abstract = "With the quick development of social websites, there
are more opportunities to have different media types
(such as text, image, video, etc.) describing the same
topic from large-scale heterogeneous data sources. To
efficiently identify the inter-media correlations for
multimedia retrieval, unsupervised cross-modal hashing
(UCMH) has gained increased interest due to the
significant reduction in computation and storage.
However, most UCMH methods assume that the data from
different modalities are well paired. As a result,
existing UCMH methods may not achieve satisfactory
performance when partially paired data are given only.
In this article, we propose a new-type of UCMH method
called robust unsupervised cross-modal hashing (RUCMH).
The major contribution lies in jointly learning
modal-specific hash function, exploring the
correlations among modalities with partial or even
without any pairwise correspondence, and preserving the
information of original features as much as possible.
The learning process can be modeled via a joint
minimization problem, and the corresponding
optimization algorithm is presented. A series of
experiments is conducted on four real-world datasets
(Wiki, MIRFlickr, NUS-WIDE, and MS-COCO). The results
demonstrate that RUCMH can significantly outperform the
state-of-the-art unsupervised cross-modal hashing
methods, especially for the partially paired case,
which validates the effectiveness of RUCMH.",
acknowledgement = ack-nhfb,
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2020:DFG,
author = "Ruqing Zhang and Jiafeng Guo and Yixing Fan and Yanyan
Lan and Xueqi Cheng",
title = "Dual-factor Generation Model for Conversation",
journal = j-TOIS,
volume = "38",
number = "3",
pages = "31:1--31:31",
month = jun,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3394052",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Jun 27 14:50:14 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3394052",
abstract = "The conversation task is usually formulated as a
conditional generation problem, i.e., to generate a
natural and meaningful response given the input
utterance. Generally speaking, this formulation is
apparently based on an oversimplified assumption that
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "31",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lin:2020:EEB,
author = "Hao Lin and Hengshu Zhu and Junjie Wu and Yuan Zuo and
Chen Zhu and Hui Xiong",
title = "Enhancing Employer Brand Evaluation with Collaborative
Topic Regression Models",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "32:1--32:33",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3392734",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3392734",
abstract = "Employer Brand Evaluation (EBE) is to understand an
employer's unique characteristics to identify
competitive edges. Traditional approaches rely heavily
on employers' financial information, including
financial reports and filings submitted to the
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "32",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Moffat:2020:LAS,
author = "Alistair Moffat and Matthias Petri",
title = "Large-Alphabet Semi-Static Entropy Coding Via
Asymmetric Numeral Systems",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "33:1--33:33",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3397175",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3397175",
abstract = "An entropy coder takes as input a sequence of symbol
identifiers over some specified alphabet and represents
that sequence as a bitstring using as few bits as
possible, typically assuming that the elements of the
sequence are independent of each other. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ren:2020:CCR,
author = "Xuhui Ren and Hongzhi Yin and Tong Chen and Hao Wang
and Nguyen Quoc Viet Hung and Zi Huang and Xiangliang
Zhang",
title = "{CRSAL}: Conversational Recommender Systems with
Adversarial Learning",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "34:1--34:40",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3394592",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3394592",
abstract = "Recommender systems have been attracting much
attention from both academia and industry because of
their ability to capture user interests and generate
personalized item recommendations. As the life pace in
contemporary society speeds up, traditional \ldots{}",
acknowledgement = ack-nhfb,
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2020:SHO,
author = "Xiancong Chen and Lin Li and Weike Pan and Zhong
Ming",
title = "A Survey on Heterogeneous One-class Collaborative
Filtering",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "35:1--35:54",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3402521",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3402521",
abstract = "Recommender systems play an important role in
providing personalized services for users in the
context of information overload. Generally, users'
feedback toward items often contain the most
significant information reflecting their preferences,
which \ldots{}",
acknowledgement = ack-nhfb,
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2020:PLP,
author = "Richong Zhang and Samuel Mensah and Fanshuang Kong and
Zhiyuan Hu and Yongyi Mao and Xudong Liu",
title = "Pairwise Link Prediction Model for Out of Vocabulary
Knowledge Base Entities",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "36:1--36:28",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3406116",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3406116",
abstract = "Real-world knowledge bases such as DBPedia, Yago, and
Freebase contain sparse linkage connectivity, which
poses a severe challenge to link prediction between
entities. To cope with such data scarcity issues,
recent models have focused on learning \ldots{}",
acknowledgement = ack-nhfb,
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2020:FGP,
author = "Xiaolin Chen and Xuemeng Song and Ruiyang Ren and Lei
Zhu and Zhiyong Cheng and Liqiang Nie",
title = "Fine-Grained Privacy Detection with Graph-Regularized
Hierarchical Attentive Representation Learning",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "37:1--37:26",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3406109",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3406109",
abstract = "Due to the complex and dynamic environment of social
media, user generated contents (UGCs) may inadvertently
leak users' personal aspects, such as the personal
attributes, relationships and even the health
condition, and thus place users at high privacy
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Agosti:2020:LUK,
author = "Maristella Agosti and Stefano Marchesin and Gianmaria
Silvello",
title = "Learning Unsupervised Knowledge-Enhanced
Representations to Reduce the Semantic Gap in
Information Retrieval",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "38:1--38:48",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3417996",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3417996",
abstract = "The semantic mismatch between query and document
terms-i.e., the semantic gap-is a long-standing problem
in Information Retrieval (IR). Two main linguistic
features related to the semantic gap that can be
exploited to improve retrieval are synonymy and
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Kim:2020:ETM,
author = "Youngwoo Kim and Myungha Jang and James Allan",
title = "Explaining Text Matching on Neural Natural Language
Inference",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "39:1--39:23",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3418052",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3418052",
abstract = "Natural language inference (NLI) is the task of
detecting the existence of entailment or contradiction
in a given sentence pair. Although NLI techniques could
help numerous information retrieval tasks, most
solutions for NLI are neural approaches whose
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2020:MME,
author = "Chang Li and Ilya Markov and Maarten {De Rijke} and
Masrour Zoghi",
title = "{MergeDTS}: a Method for Effective Large-Scale Online
Ranker Evaluation",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "40:1--40:28",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3411753",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3411753",
abstract = "Online ranker evaluation is one of the key challenges
in information retrieval. Although the preferences of
rankers can be inferred by interleaving methods, the
problem of how to effectively choose the ranker pair
that generates the interleaved list \ldots{}",
acknowledgement = ack-nhfb,
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2020:WSR,
author = "Dan Li and Evangelos Kanoulas",
title = "When to Stop Reviewing in Technology-Assisted Reviews:
Sampling from an Adaptive Distribution to Estimate
Residual Relevant Documents",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "41:1--41:36",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3411755",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3411755",
abstract = "Technology-Assisted Reviews (TAR) aim to expedite
document reviewing (e.g., medical articles or legal
documents) by iteratively incorporating machine
learning algorithms and human feedback on document
relevance. Continuous Active Learning (CAL) \ldots{}",
acknowledgement = ack-nhfb,
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2020:BAI,
author = "Yifan Chen and Yang Wang and Xiang Zhao and Jie Zou
and Maarten {De Rijke}",
title = "Block-Aware Item Similarity Models for Top-{$N$}
Recommendation",
journal = j-TOIS,
volume = "38",
number = "4",
pages = "42:1--42:26",
month = oct,
year = "2020",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3411754",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Oct 14 06:47:18 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3411754",
abstract = "Top- N recommendations have been studied extensively.
Promising results have been achieved by recent
item-based collaborative filtering (ICF) methods. The
key to ICF lies in the estimation of item similarities.
Observing the block-diagonal structure of \ldots{}",
acknowledgement = ack-nhfb,
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2021:PES,
author = "Guangzhen Zhao and Peng Yang",
title = "Pretrained Embeddings for Stance Detection with
Hierarchical Capsule Network on Social Media",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "1:1--1:32",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3412362",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3412362",
abstract = "Stance detection on social media aims to identify the
stance of social media users toward a topic or claim,
which can provide powerful information for various
downstream tasks. Many existing stance detection
approaches neglect to model the deep semantic
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2021:GBR,
author = "Yuan Zhang and Fei Sun and Xiaoyong Yang and Chen Xu
and Wenwu Ou and Yan Zhang",
title = "Graph-based Regularization on Embedding Layers for
Recommendation",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "2:1--2:27",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3414067",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3414067",
abstract = "Neural networks have been extensively used in
recommender systems. Embedding layers are not only
necessary but also crucial for neural models in
recommendation as a typical discrete task. In this
article, we argue that the widely used $l_2$
regularization \ldots{}",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mousset:2021:EEN,
author = "Paul Mousset and Yoann Pitarch and Lynda Tamine",
title = "End-to-End Neural Matching for Semantic Location
Prediction of Tweets",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "3:1--3:35",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3415149",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3415149",
abstract = "The impressive increasing availability of social media
posts has given rise to considerable research
challenges. This article is concerned with the problem
of semantic location prediction of geotagged tweets.
The underlying task is to associate to a \ldots{}",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mcdonald:2021:HAC,
author = "Graham Mcdonald and Craig Macdonald and Iadh Ounis",
title = "How the Accuracy and Confidence of Sensitivity
Classification Affects Digital Sensitivity Review",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "4:1--4:34",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3417334",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3417334",
abstract = "Government documents must be manually reviewed to
identify any sensitive information, e.g., confidential
information, before being publicly archived. However,
human-only sensitivity review is not practical for
born-digital documents due to, for example, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mendoza:2021:BSI,
author = "Marcelo Mendoza and Maurizio Tesconi and Stefano
Cresci",
title = "Bots in Social and Interaction Networks: Detection and
Impact Estimation",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "5:1--5:32",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3419369",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3419369",
abstract = "The rise of bots and their influence on social
networks is a hot topic that has aroused the interest
of many researchers. Despite the efforts to detect
social bots, it is still difficult to distinguish them
from legitimate users. Here, we propose a \ldots{}",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2021:ABD,
author = "Bulou Liu and Chenliang Li and Wei Zhou and Feng Ji
and Yu Duan and Haiqing Chen",
title = "An Attention-based Deep Relevance Model for Few-shot
Document Filtering",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "6:1--6:35",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3419972",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3419972",
abstract = "With the large quantity of textual information
produced on the Internet, a critical necessity is to
filter out the irrelevant information and organize the
rest into categories of interest (e.g., an emerging
event). However, supervised-learning document
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lan:2021:PNA,
author = "Tian Lan and Xian-Ling Mao and Wei Wei and Xiaoyan Gao
and Heyan Huang",
title = "{PONE}: a Novel Automatic Evaluation Metric for
Open-domain Generative Dialogue Systems",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "7:1--7:37",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3423168",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3423168",
abstract = "Open-domain generative dialogue systems have attracted
considerable attention over the past few years.
Currently, how to automatically evaluate them is still
a big challenge. As far as we know, there are three
kinds of automatic evaluations for open-\ldots{}",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2021:NFA,
author = "Xu Chen and Kun Xiong and Yongfeng Zhang and Long Xia
and Dawei Yin and Jimmy Xiangji Huang",
title = "Neural Feature-aware Recommendation with Signed
Hypergraph Convolutional Network",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "8:1--8:22",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3423322",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3423322",
abstract = "Understanding user preference is of key importance for
an effective recommender system. For comprehensive user
profiling, many efforts have been devoted to extract
user feature-level preference from the review
information. Despite effectiveness, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Manioudakis:2021:FSO,
author = "Kostas Manioudakis and Yannis Tzitzikas",
title = "Faceted Search with Object Ranking and Answer Size
Constraints",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "9:1--9:33",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3425603",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3425603",
abstract = "Faceted Search is a widely used interaction scheme in
digital libraries, e-commerce, and recently also in
Linked Data. Surprisingly, object ranking in the
context of Faceted Search is not well studied in the
literature. In this article, we propose an \ldots{}",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Fang:2021:DLS,
author = "Hui Fang and Danning Zhang and Yiheng Shu and Guibing
Guo",
title = "Deep Learning for Sequential Recommendation:
Algorithms, Influential Factors, and Evaluations",
journal = j-TOIS,
volume = "39",
number = "1",
pages = "10:1--10:42",
month = jan,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3426723",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sun Mar 28 09:55:32 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3426723",
abstract = "In the field of sequential recommendation, deep
learning--(DL) based methods have received a lot of
attention in the past few years and surpassed
traditional models such as Markov chain-based and
factorization-based ones. However, there is little
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Muntean:2021:WPE,
author = "Cristina Ioana Muntean and Franco Maria Nardini and
Raffaele Perego and Nicola Tonellotto and Ophir
Frieder",
title = "Weighting Passages Enhances Accuracy",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "11:1--11:11",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3428687",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3428687",
abstract = "We observe that in curated documents the distribution
of the occurrences of salient terms, e.g., terms with a
high Inverse Document Frequency, is not uniform, and
such terms are primarily concentrated towards the
beginning and the end of the document. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Gao:2021:LRY,
author = "Shen Gao and Xiuying Chen and Li Liu and Dongyan Zhao
and Rui Yan",
title = "Learning to Respond with Your Favorite Stickers: a
Framework of Unifying Multi-Modality and User
Preference in Multi-Turn Dialog",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "12:1--12:32",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3429980",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3429980",
abstract = "Stickers with vivid and engaging expressions are
becoming increasingly popular in online messaging apps,
and some works are dedicated to automatically select
sticker response by matching the stickers image with
previous utterances. However, existing \ldots{}",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Adomavicius:2021:EPA,
author = "Gediminas Adomavicius and Jesse Bockstedt and Shawn
Curley and Jingjing Zhang",
title = "Effects of Personalized and Aggregate Top-{$N$}
Recommendation Lists on User Preference Ratings",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "13:1--13:38",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3430028",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3430028",
abstract = "Prior research has shown a robust effect of
personalized product recommendations on user preference
judgments for items. Specifically, the display of
system-predicted preference ratings as item
recommendations has been shown in multiple studies to
bias \ldots{}",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sakai:2021:REM,
author = "Tetsuya Sakai and Zhaohao Zeng",
title = "Retrieval Evaluation Measures that Agree with Users'
{SERP} Preferences: Traditional, Preference-based, and
Diversity Measures",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "14:1--14:35",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3431813",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3431813",
abstract = "We examine the ``goodness'' of ranked retrieval
evaluation measures in terms of how well they align
with users' Search Engine Result Page (SERP)
preferences for web search. The SERP preferences cover
1,127 topic-SERP-SERP triplets extracted from the
NTCIR-. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2021:MRA,
author = "Peng Liu and Lemei Zhang and Jon Atle Gulla",
title = "Multilingual Review-aware Deep Recommender System via
Aspect-based Sentiment Analysis",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "15:1--15:33",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3432049",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3432049",
abstract = "With the dramatic expansion of international markets,
consumers write reviews in different languages, which
poses a new challenge for Recommender Systems (RSs)
dealing with this increasing amount of multilingual
information. Recent studies that leverage \ldots{}",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2021:TDU,
author = "Chenyang Wang and Weizhi Ma and Min Zhang and Chong
Chen and Yiqun Liu and Shaoping Ma",
title = "Toward Dynamic User Intention: Temporal Evolutionary
Effects of Item Relations in Sequential
Recommendation",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "16:1--16:33",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3432244",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3432244",
abstract = "User intention is an important factor to be considered
for recommender systems, which always changes
dynamically in different contexts. Recent studies
(represented by sequential recommendation) begin to
focus on predicting what users want beyond what
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{White:2021:MD,
author = "Ryen W. White and Elnaz Nouri and James Woffinden-Luey
and Mark Encarnaci{\'o}N and Sujay Kumar Jauhar",
title = "Microtask Detection",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "17:1--17:29",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3432290",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3432290",
abstract = "Information systems, such as task management
applications and digital assistants, can help people
keep track of tasks of different types and different
time durations, ranging from a few minutes to days or
weeks. Helping people better manage their tasks
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Gao:2021:MAG,
author = "Shen Gao and Xiuying Chen and Zhaochun Ren and Dongyan
Zhao and Rui Yan",
title = "Meaningful Answer Generation of E-Commerce
Question-Answering",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "18:1--18:26",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3432689",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3432689",
abstract = "In e-commerce portals, generating answers for
product-related questions has become a crucial task. In
this article, we focus on the task of product-aware
answer generation, which learns to generate an accurate
and complete answer from large-scale \ldots{}",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Esuli:2021:CRS,
author = "Andrea Esuli and Alessio Molinari and Fabrizio
Sebastiani",
title = "A Critical Reassessment of the
{Saerens--Latinne--Decaestecker} Algorithm for
Posterior Probability Adjustment",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "19:1--19:34",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3433164",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3433164",
abstract = "We critically re-examine the
Saerens-Latinne-Decaestecker (SLD) algorithm, a
well-known method for estimating class prior
probabilities (``priors'') and adjusting posterior
probabilities (``posteriors'') in scenarios
characterized by distribution shift, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Dacrema:2021:TAR,
author = "Maurizio Ferrari Dacrema and Simone Boglio and Paolo
Cremonesi and Dietmar Jannach",
title = "A Troubling Analysis of Reproducibility and Progress
in Recommender Systems Research",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "20:1--20:49",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3434185",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3434185",
abstract = "The design of algorithms that generate personalized
ranked item lists is a central topic of research in the
field of recommender systems. In the past few years, in
particular, approaches based on deep learning (neural)
techniques have become dominant in \ldots{}",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ai:2021:ULR,
author = "Qingyao Ai and Tao Yang and Huazheng Wang and Jiaxin
Mao",
title = "Unbiased Learning to Rank: Online or Offline?",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "21:1--21:29",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3439861",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3439861",
abstract = "How to obtain an unbiased ranking model by learning to
rank with biased user feedback is an important research
question for IR. Existing work on unbiased learning to
rank (ULTR) can be broadly categorized into two
groups-the studies on unbiased learning \ldots{}",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2021:VNV,
author = "Wei Wang and Longbing Cao",
title = "{VM-NSP}: Vertical Negative Sequential Pattern Mining
with Loose Negative Element Constraints",
journal = j-TOIS,
volume = "39",
number = "2",
pages = "22:1--22:27",
month = mar,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3440874",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Apr 1 09:57:35 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3440874",
abstract = "Negative sequential patterns (NSPs) capture more
informative and actionable knowledge than classic
positive sequential patterns (PSPs) due to the
involvement of both occurring and nonoccurring
behaviors and events, which can contribute to many
relevant \ldots{}",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2021:EMN,
author = "Min Zhang",
title = "Editorial Message from the New {Editor-in-Chief}",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "23e:1--23e:2",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3447945",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3447945",
acknowledgement = ack-nhfb,
articleno = "23e",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2021:MMC,
author = "Yanan Xu and Yanmin Zhu and Jiadi Yu",
title = "Modeling Multiple Coexisting Category-Level Intentions
for Next Item Recommendation",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "23:1--23:24",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3441642",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3441642",
abstract = "Purchase intentions have a great impact on future
purchases and thus can be exploited for making
recommendations. However, purchase intentions are
typically complex and may change from time to time.
Through empirical study with two e-commerce datasets,
we \ldots{}",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2021:ISB,
author = "Wei Wang and Longbing Cao",
title = "Interactive Sequential Basket Recommendation by
Learning Basket Couplings and Positive\slash Negative
Feedback",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "24:1--24:26",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3444368",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3444368",
abstract = "Sequential recommendation, such as next-basket
recommender systems (NBRS), which model users'
sequential behaviors and the relevant context/session,
has recently attracted much attention from the research
community. Existing session-based NBRS involve
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2021:TCU,
author = "Hongtao Liu and Wenjun Wang and Qiyao Peng and Nannan
Wu and Fangzhao Wu and Pengfei Jiao",
title = "Toward Comprehensive User and Item Representations via
Three-tier Attention Network",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "25:1--25:22",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3446341",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3446341",
abstract = "Product reviews can provide rich information about the
opinions users have of products. However, it is
nontrivial to effectively infer user preference and
item characteristics from reviews due to the
complicated semantic understanding. Existing methods
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zeng:2021:RLB,
author = "Weixin Zeng and Xiang Zhao and Jiuyang Tang and Xuemin
Lin and Paul Groth",
title = "Reinforcement Learning-based Collective Entity
Alignment with Adaptive Features",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "26:1--26:31",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3446428",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3446428",
abstract = "Entity alignment (EA) is the task of identifying the
entities that refer to the same real-world object but
are located in different knowledge graphs (KGs). For
entities to be aligned, existing EA solutions treat
them separately and generate alignment \ldots{}",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yao:2021:RRL,
author = "Jing Yao and Zhicheng Dou and Jun Xu and Ji-Rong Wen",
title = "{RLPS}: a Reinforcement Learning-Based Framework for
Personalized Search",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "27:1--27:29",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3446617",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3446617",
abstract = "Personalized search is a promising way to improve
search qualities by taking user interests into
consideration. Recently, machine learning and deep
learning techniques have been successfully applied to
search result personalization. Most existing models
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2021:DPR,
author = "Jingyuan Wang and Xin Lin and Yuan Zuo and Junjie Wu",
title = "{DGeye}: Probabilistic Risk Perception and Prediction
for Urban Dangerous Goods Management",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "28:1--28:30",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3448256",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3448256",
abstract = "Recent years have witnessed the emergence of worldwide
megalopolises and the accompanying public safety
events, making urban safety a top priority in modern
urban management. Among various threats, dangerous
goods such as gas and hazardous chemicals \ldots{}",
acknowledgement = ack-nhfb,
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Aliannejadi:2021:CAT,
author = "Mohammad Aliannejadi and Hamed Zamani and Fabio
Crestani and W. Bruce Croft",
title = "Context-aware Target Apps Selection and Recommendation
for Enhancing Personal Mobile Assistants",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "29:1--29:30",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3447678",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3447678",
abstract = "Users install many apps on their smartphones, raising
issues related to information overload for users and
resource management for devices. Moreover, the recent
increase in the use of personal assistants has made
mobile devices even more pervasive in \ldots{}",
acknowledgement = ack-nhfb,
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2021:HFS,
author = "Jia Chen and Jiaxin Mao and Yiqun Liu and Ziyi Ye and
Weizhi Ma and Chao Wang and Min Zhang and Shaoping Ma",
title = "A Hybrid Framework for Session Context Modeling",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "30:1--30:35",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3448127",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3448127",
abstract = "Understanding user intent is essential for various
retrieval tasks. By leveraging contextual information
within sessions, e.g., query history and user click
behaviors, search systems can capture user intent more
accurately and thus perform better. However,.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Vuong:2021:SCC,
author = "Tung Vuong and Salvatore Andolina and Giulio Jacucci
and Tuukka Ruotsalo",
title = "Spoken Conversational Context Improves Query
Auto-completion in {Web} Search",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "31:1--31:32",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3447875",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3447875",
abstract = "Web searches often originate from conversations in
which people engage before they perform a search.
Therefore, conversations can be a valuable source of
context with which to support the search process. We
investigate whether spoken input from \ldots{}",
acknowledgement = ack-nhfb,
articleno = "31",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yang:2021:HHG,
author = "Tianchi Yang and Linmei Hu and Chuan Shi and Houye Ji
and Xiaoli Li and Liqiang Nie",
title = "{HGAT}: Heterogeneous Graph Attention Networks for
Semi-supervised Short Text Classification",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "32:1--32:29",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3450352",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3450352",
abstract = "Short text classification has been widely explored in
news tagging to provide more efficient search
strategies and more effective search results for
information retrieval. However, most existing studies,
concentrating on long text classification, deliver
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "32",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Clarke:2021:ATP,
author = "Charles L. A. Clarke and Alexandra Vtyurina and Mark
D. Smucker",
title = "Assessing Top-$k$ Preferences",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "33:1--33:21",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3451161",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3451161",
abstract = "Assessors make preference judgments faster and more
consistently than graded judgments. Preference
judgments can also recognize distinctions between items
that appear equivalent under graded judgments.
Unfortunately, preference judgments can require more
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2021:CEC,
author = "Jiawei Chen and Chengquan Jiang and Can Wang and Sheng
Zhou and Yan Feng and Chun Chen and Martin Ester and
Xiangnan He",
title = "{CoSam}: an Efficient Collaborative Adaptive Sampler
for Recommendation",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "34:1--34:24",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3450289",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3450289",
abstract = "Sampling strategies have been widely applied in many
recommendation systems to accelerate model learning
from implicit feedback data. A typical strategy is to
draw negative instances with uniform distribution,
which, however, will severely affect a model'.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2021:ICR,
author = "Chuxu Zhang and Huaxiu Yao and Lu Yu and Chao Huang
and Dongjin Song and Haifeng Chen and Meng Jiang and
Nitesh V. Chawla",
title = "Inductive Contextual Relation Learning for
Personalization",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "35:1--35:22",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3450353",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3450353",
abstract = "Web personalization, e.g., recommendation or relevance
search, tailoring a service/product to accommodate
specific online users, is becoming increasingly
important. Inductive personalization aims to infer the
relations between existing entities and unseen
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mena-Maldonado:2021:PBF,
author = "Elisa Mena-Maldonado and Roc{\'\i}o Ca{\~n}amares and
Pablo Castells and Yongli Ren and Mark Sanderson",
title = "Popularity Bias in False-positive Metrics for
Recommender Systems Evaluation",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "36:1--36:43",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3452740",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3452740",
abstract = "We investigate the impact of popularity bias in
false-positive metrics in the offline evaluation of
recommender systems. Unlike their true-positive
complements, false-positive metrics reward systems that
minimize recommendations disliked by users. Our
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2021:ERT,
author = "Qi Zhang and Hengshu Zhu and Qi Liu and Enhong Chen
and Hui Xiong",
title = "Exploiting Real-time Search Engine Queries for
Earthquake Detection: a Summary of Results",
journal = j-TOIS,
volume = "39",
number = "3",
pages = "37:1--37:32",
month = jul,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3453842",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue Aug 10 13:18:19 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3453842",
abstract = "Online search engine has been widely regarded as the
most convenient approach for information acquisition.
Indeed, the intensive information-seeking behaviors of
search engine users make it possible to exploit search
engine queries as effective ``crowd \ldots{}''",
acknowledgement = ack-nhfb,
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Hauff:2021:CSR,
author = "Claudia Hauff and Julia Kiseleva and Mark Sanderson
and Hamed Zamani and Yongfeng Zhang",
title = "Conversational Search and Recommendation: Introduction
to the Special Issue",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "38:1--38:6",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3465272",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3465272",
acknowledgement = ack-nhfb,
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Thomas:2021:TCC,
author = "Paul Thomas and Mary Czerwinksi and Daniel Mcduff and
Nick Craswell",
title = "Theories of Conversation for Conversational {IR}",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "39:1--39:23",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3439869",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3439869",
abstract = "Conversational information retrieval is a relatively
new and fast-developing research area, but conversation
itself has been well studied for decades. Researchers
have analysed linguistic phenomena such as structure
and semantics but also paralinguistic \ldots{}",
acknowledgement = ack-nhfb,
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2021:SUA,
author = "Shijun Li and Wenqiang Lei and Qingyun Wu and Xiangnan
He and Peng Jiang and Tat-Seng Chua",
title = "Seamlessly Unifying Attributes and Items:
Conversational Recommendation for Cold-start Users",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "40:1--40:29",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3446427",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3446427",
abstract = "Static recommendation methods like collaborative
filtering suffer from the inherent limitation of
performing real-time personalization for cold-start
users. Online recommendation, e.g., multi-armed bandit
approach, addresses this limitation by \ldots{}",
acknowledgement = ack-nhfb,
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Contreras:2021:ICL,
author = "David Contreras and Maria Salam{\'o} and Ludovico
Boratto",
title = "Integrating Collaboration and Leadership in
Conversational Group Recommender Systems",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "41:1--41:32",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3462759",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3462759",
abstract = "Recent observational studies highlight the importance
of considering the interactions between users in the
group recommendation process, but to date their
integration has been marginal. In this article, we
propose a collaborative model based on the social
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wilkinson:2021:WWE,
author = "Daricia Wilkinson and {\"O}znur Alkan and Q. Vera Liao
and Massimiliano Mattetti and Inge Vejsbjerg and Bart
P. Knijnenburg and Elizabeth Daly",
title = "Why or Why Not? {The} Effect of Justification Styles
on Chatbot Recommendations",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "42:1--42:21",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3441715",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3441715",
abstract = "Chatbots or conversational recommenders have gained
increasing popularity as a new paradigm for Recommender
Systems (RS). Prior work on RS showed that providing
explanations can improve transparency and trust, which
are critical for the adoption of RS. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wei:2021:TGE,
author = "Wei Wei and Jiayi Liu and Xianling Mao and Guibing Guo
and Feida Zhu and Pan Zhou and Yuchong Hu and Shanshan
Feng",
title = "Target-guided Emotion-aware Chat Machine",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "43:1--43:24",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3456414",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3456414",
abstract = "The consistency of a response to a given post at the
semantic level and emotional level is essential for a
dialogue system to deliver humanlike interactions.
However, this challenge is not well addressed in the
literature, since most of the approaches \ldots{}",
acknowledgement = ack-nhfb,
articleno = "43",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2021:RRM,
author = "Ruijian Xu and Chongyang Tao and Jiazhan Feng and Wei
Wu and Rui Yan and Dongyan Zhao",
title = "Response Ranking with Multi-types of Deep Interactive
Representations in Retrieval-based Dialogues",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "44:1--44:28",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3462207",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3462207",
abstract = "Building an intelligent dialogue system with the
ability to select a proper response according to a
multi-turn context is challenging in three aspects: (1)
the meaning of a context-response pair is built upon
language units from multiple granularities \ldots{}",
acknowledgement = ack-nhfb,
articleno = "44",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2021:DHM,
author = "Juntao Li and Chang Liu and Chongyang Tao and
Zhangming Chan and Dongyan Zhao and Min Zhang and Rui
Yan",
title = "Dialogue History Matters! {Personalized} Response
Selection in Multi-Turn Retrieval-Based Chatbots",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "45:1--45:25",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3453183",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3453183",
abstract = "Existing multi-turn context-response matching methods
mainly concentrate on obtaining multi-level and
multi-dimension representations and better interactions
between context utterances and response. However, in
real-place conversation scenarios, whether a \ldots{}",
acknowledgement = ack-nhfb,
articleno = "45",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Musto:2021:MDA,
author = "Cataldo Musto and Fedelucio Narducci and Marco
Polignano and Marco {De Gemmis} and Pasquale Lops and
Giovanni Semeraro",
title = "{MyrrorBot}: a Digital Assistant Based on Holistic
User Models for Personalized Access to Online
Services",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "46:1--46:34",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3447679",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3447679",
abstract = "In this article, we present MyrrorBot, a personal
digital assistant implementing a natural language
interface that allows the users to: (i) access online
services, such as music, video, news, and food
recommendation s, in a personalized way, by exploiting
a \ldots{}",
acknowledgement = ack-nhfb,
articleno = "46",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ren:2021:CSE,
author = "Pengjie Ren and Zhumin Chen and Zhaochun Ren and
Evangelos Kanoulas and Christof Monz and Maarten {De
Rijke}",
title = "Conversations with Search Engines: {SERP-based}
Conversational Response Generation",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "47:1--47:29",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3432726",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3432726",
abstract = "In this article, we address the problem of answering
complex information needs by conducting conversations
with search engines, in the sense that users can
express their queries in natural language and directly
receive the information they need from a \ldots{}",
acknowledgement = ack-nhfb,
articleno = "47",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lin:2021:MSC,
author = "Sheng-Chieh Lin and Jheng-Hong Yang and Rodrigo
Nogueira and Ming-Feng Tsai and Chuan-Ju Wang and Jimmy
Lin",
title = "Multi-Stage Conversational Passage Retrieval: an
Approach to Fusing Term Importance Estimation and
Neural Query Rewriting",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "48:1--48:29",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3446426",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3446426",
abstract = "Conversational search plays a vital role in
conversational information seeking. As queries in
information seeking dialogues are ambiguous for
traditional ad hoc information retrieval (IR) systems
due to the coreference and omission resolution problems
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "48",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Vakulenko:2021:LSA,
author = "Svitlana Vakulenko and Evangelos Kanoulas and Maarten
{De Rijke}",
title = "A Large-scale Analysis of Mixed Initiative in
Information-Seeking Dialogues for Conversational
Search",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "49:1--49:32",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3466796",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3466796",
abstract = "Conversational search is a relatively young area of
research that aims at automating an information-seeking
dialogue. In this article, we help to position it with
respect to other research areas within conversational
artificial intelligence (AI) by \ldots{}",
acknowledgement = ack-nhfb,
articleno = "49",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Kiesel:2021:MIC,
author = "Johannes Kiesel and Lars Meyer and Martin Potthast and
Benno Stein",
title = "Meta-Information in Conversational Search",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "50:1--50:44",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3468868",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3468868",
abstract = "The exchange of meta-information has always formed
part of information behavior. In this article, we show
that this rule also extends to conversational search.
Information about the user's information need, their
preferences, and the quality of search \ldots{}",
acknowledgement = ack-nhfb,
articleno = "50",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lipani:2021:HDE,
author = "Aldo Lipani and Ben Carterette and Emine Yilmaz",
title = "How Am {I} Doing?: Evaluating Conversational Search
Systems Offline",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "51:1--51:22",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3451160",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3451160",
abstract = "As conversational agents like Siri and Alexa gain in
popularity and use, conversation is becoming a more and
more important mode of interaction for search.
Conversational search shares some features with
traditional search, but differs in some important
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "51",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2021:MEC,
author = "Zeyang Liu and Ke Zhou and Max L. Wilson",
title = "Meta-evaluation of Conversational Search Evaluation
Metrics",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "52:1--52:42",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3445029",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3445029",
abstract = "Conversational search systems, such as Google
assistant and Microsoft Cortana, enable users to
interact with search systems in multiple rounds through
natural language dialogues. Evaluating such systems is
very challenging, given that any natural language
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "52",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Corno:2021:UII,
author = "Fulvio Corno and Luigi {De Russis} and Alberto Monge
Roffarello",
title = "From Users' Intentions to {IF--THEN} Rules in the
{Internet of Things}",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "53:1--53:33",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3447264",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3447264",
abstract = "In the Internet of Things era, users are willing to
personalize the joint behavior of their connected
entities, i.e., smart devices and online service, by
means of trigger-action rules such as ``IF the entrance
Nest security camera detects a movement, THEN
\ldots{}''",
acknowledgement = ack-nhfb,
articleno = "53",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yan:2021:MRA,
author = "Rui Yan and Weiheng Liao and Dongyan Zhao and Ji-Rong
Wen",
title = "Multi-Response Awareness for Retrieval-Based
Conversations: Respond with Diversity via Dynamic
Representation Learning",
journal = j-TOIS,
volume = "39",
number = "4",
pages = "54:1--54:29",
month = oct,
year = "2021",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3470450",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Sat Oct 23 06:30:06 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3470450",
abstract = "Conversational systems now attract great attention due
to their promising potential and commercial values. To
build a conversational system with moderate
intelligence is challenging and requires big
(conversational) data, as well as interdisciplinary
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "54",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Patil:2022:GTA,
author = "Shubham Patil and Debopriyo Banerjee and Shamik
Sural",
title = "A Graph Theoretic Approach for Multi-Objective Budget
Constrained Capsule Wardrobe Recommendation",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "1:1--1:33",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3457182",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3457182",
abstract = "Traditionally, capsule wardrobes are manually designed
by expert fashionistas through their creativity and
technical prowess. The goal is to curate minimal
fashion items that can be assembled into several
compatible and versatile outfits. It is usually a
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Deng:2022:CKA,
author = "Yang Deng and Yuexiang Xie and Yaliang Li and Min Yang
and Wai Lam and Ying Shen",
title = "Contextualized Knowledge-aware Attentive Neural
Network: Enhancing Answer Selection with Knowledge",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "2:1--2:33",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3457533",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3457533",
abstract = "Answer selection, which is involved in many natural
language processing applications, such as dialog
systems and question answering (QA), is an important
yet challenging task in practice, since conventional
methods typically suffer from the issues of \ldots{}",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Guo:2022:HHE,
author = "Lei Guo and Hongzhi Yin and Tong Chen and Xiangliang
Zhang and Kai Zheng",
title = "Hierarchical Hyperedge Embedding-Based Representation
Learning for Group Recommendation",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "3:1--3:27",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3457949",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3457949",
abstract = "Group recommendation aims to recommend items to a
group of users. In this work, we study group
recommendation in a particular scenario, namely
occasional group recommendation, where groups are
formed ad hoc and users may just constitute a group for
the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Jadidinejad:2022:SPO,
author = "Amir H. Jadidinejad and Craig Macdonald and Iadh
Ounis",
title = "The {Simpson's Paradox} in the Offline Evaluation of
Recommendation Systems",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "4:1--4:22",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3458509",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3458509",
abstract = "Recommendation systems are often evaluated based on
user's interactions that were collected from an
existing, already deployed recommendation system. In
this situation, users only provide feedback on the
exposed items and they may not leave feedback on
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Bahrainian:2022:CCA,
author = "Seyed Ali Bahrainian and George Zerveas and Fabio
Crestani and Carsten Eickhoff",
title = "{CATS}: Customizable Abstractive Topic-based
Summarization",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "5:1--5:24",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464299",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464299",
abstract = "Neural sequence-to-sequence models are the
state-of-the-art approach used in abstractive
summarization of textual documents, useful for
producing condensed versions of source text narratives
without being restricted to using only words from the
original \ldots{}",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mu:2022:KGD,
author = "Shanlei Mu and Yaliang Li and Wayne Xin Zhao and
Siqing Li and Ji-Rong Wen",
title = "Knowledge-Guided Disentangled Representation Learning
for Recommender Systems",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "6:1--6:26",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464304",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464304",
abstract = "In recommender systems, it is essential to understand
the underlying factors that affect user-item
interaction. Recently, several studies have utilized
disentangled representation learning to discover such
hidden factors from user-item interaction data,
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zang:2022:CCH,
author = "Hongyu Zang and Dongcheng Han and Xin Li and Zhifeng
Wan and Mingzhong Wang",
title = "{CHA}: Categorical Hierarchy-based Attention for Next
{POI} Recommendation",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "7:1--7:22",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464300",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464300",
abstract = "Next Point-of-interest (POI) recommendation is a key
task in improving location-related customer experiences
and business operations, but yet remains challenging
due to the substantial diversity of human activities
and the sparsity of the check-in records \ldots{}",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Tian:2022:WHL,
author = "Yuan Tian and Ke Zhou and Dan Pelleg",
title = "What and How long: Prediction of Mobile App
Engagement",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "8:1--8:38",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464301",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464301",
abstract = "User engagement is crucial to the long-term success of
a mobile app. Several metrics, such as dwell time, have
been used for measuring user engagement. However, how
to effectively predict user engagement in the context
of mobile apps is still an open \ldots{}",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ma:2022:UTE,
author = "Longxuan Ma and Mingda Li and Wei-Nan Zhang and
Jiapeng Li and Ting Liu",
title = "Unstructured Text Enhanced Open-Domain Dialogue
System: a Systematic Survey",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "9:1--9:44",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464377",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464377",
abstract = "Incorporating external knowledge into dialogue
generation has been proven to benefit the performance
of an open-domain Dialogue System (DS), such as
generating informative or stylized responses,
controlling conversation topics. In this article, we
study \ldots{}",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xia:2022:CRA,
author = "Lianghao Xia and Chao Huang and Yong Xu and Huance Xu
and Xiang Li and Weiguo Zhang",
title = "Collaborative Reflection-Augmented Autoencoder Network
for Recommender Systems",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "10:1--10:22",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3467023",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3467023",
abstract = "As the deep learning techniques have expanded to
real-world recommendation tasks, many deep neural
network based Collaborative Filtering (CF) models have
been developed to project user-item interactions into
latent feature space, based on various neural
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2022:IAA,
author = "Siqing Li and Yaliang Li and Wayne Xin Zhao and Bolin
Ding and Ji-Rong Wen",
title = "Interpretable Aspect-Aware Capsule Network for Peer
Review Based Citation Count Prediction",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "11:1--11:29",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3466640",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3466640",
abstract = "Citation count prediction is an important task for
estimating the future impact of research papers. Most
of the existing works utilize the information extracted
from the paper itself. In this article, we focus on how
to utilize another kind of useful data \ldots{}",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:QTG,
author = "Xiao Zhang and Meng Liu and Jianhua Yin and Zhaochun
Ren and Liqiang Nie",
title = "Question Tagging via Graph-guided Ranking",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "12:1--12:23",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3468270",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3468270",
abstract = "With the increasing prevalence of portable devices and
the popularity of community Question Answering (cQA)
sites, users can seamlessly post and answer many
questions. To effectively organize the information for
precise recommendation and easy searching, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mackenzie:2022:ARD,
author = "Joel Mackenzie and Matthias Petri and Alistair
Moffat",
title = "Anytime Ranking on Document-Ordered Indexes",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "13:1--13:32",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3467890",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3467890",
abstract = "Inverted indexes continue to be a mainstay of text
search engines, allowing efficient querying of large
document collections. While there are a number of
possible organizations, document-ordered indexes are
the most common, since they are amenable to various
query types, support index updates, and allow for
efficient dynamic pruning operations. One disadvantage
with document-ordered indexes is that high-scoring
documents can be distributed across the document
identifier space, meaning that index traversal
algorithms that terminate early might put search
effectiveness at risk. The alternative is
impact-ordered indexes, which primarily support
top-disjunctions but also allow for anytime query
processing, where the search can be terminated at any
time, with search quality improving as processing
latency increases. Anytime query processing can be used
to effectively reduce high-percentile tail latency that
is essential for operational scenarios in which a
service level agreement (SLA) imposes response time
requirements. In this work, we show how
document-ordered indexes can be organized such that
they can be queried in an anytime fashion, enabling
strict latency control with effective early
termination. Our experiments show that processing
document-ordered topical segments selected by a simple
score estimator outperforms existing anytime
algorithms, and allows query runtimes to be accurately
limited to comply with SLA requirements.",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:RQG,
author = "Ruqing Zhang and Jiafeng Guo and Lu Chen and Yixing
Fan and Xueqi Cheng",
title = "A Review on Question Generation from Natural Language
Text",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "14:1--14:43",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3468889",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3468889",
abstract = "Question generation is an important yet challenging
problem in Artificial Intelligence (AI), which aims to
generate natural and relevant questions from various
input formats, e.g., natural language text, structure
database, knowledge base, and image. In \ldots{}",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Shen:2022:JRL,
author = "Dazhong Shen and Chuan Qin and Hengshu Zhu and Tong Xu
and Enhong Chen and Hui Xiong",
title = "Joint Representation Learning with Relation-Enhanced
Topic Models for Intelligent Job Interview Assessment",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "15:1--15:36",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3469654",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3469654",
abstract = "The job interview is considered as one of the most
essential tasks in talent recruitment, which forms a
bridge between candidates and employers in fitting the
right person for the right job. While substantial
efforts have been made on improving the job \ldots{}",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wu:2022:KPD,
author = "Hanrui Wu and Qingyao Wu and Michael K. Ng",
title = "Knowledge Preserving and Distribution Alignment for
Heterogeneous Domain Adaptation",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "16:1--16:29",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3469856",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3469856",
abstract = "Domain adaptation aims at improving the performance of
learning tasks in a target domain by leveraging the
knowledge extracted from a source domain. To this end,
one can perform knowledge transfer between these two
domains. However, this problem becomes \ldots{}",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Shen:2022:UPB,
author = "Jiaxing Shen and Jiannong Cao and Oren Lederman and
Shaojie Tang and Alex ``Sandy'' Pentland",
title = "User Profiling Based on Nonlinguistic Audio Data",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "17:1--17:23",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3474826",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3474826",
abstract = "User profiling refers to inferring people's attributes
of interest (AoIs) like gender and occupation, which
enables various applications ranging from personalized
services to collective analyses. Massive nonlinguistic
audio data brings a novel opportunity \ldots{}",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mustar:2022:STQ,
author = "Agn{\`e}s Mustar and Sylvain Lamprier and Benjamin
Piwowarski",
title = "On the Study of Transformers for Query Suggestion",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "18:1--18:27",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3470562",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3470562",
abstract = "When conducting a search task, users may find it
difficult to articulate their need, even more so when
the task is complex. To help them complete their
search, search engine usually provide query
suggestions. A good query suggestion system requires to
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Culpepper:2022:TDC,
author = "J. Shane Culpepper and Guglielmo Faggioli and Nicola
Ferro and Oren Kurland",
title = "Topic Difficulty: Collection and Query Formulation
Effects",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "19:1--19:36",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3470563",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3470563",
abstract = "Several recent studies have explored the interaction
effects between topics, systems, corpora, and
components when measuring retrieval effectiveness.
However, all of these previous studies assume that a
topic or information need is represented by a single
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2022:MID,
author = "Wanyu Chen and Pengjie Ren and Fei Cai and Fei Sun and
Maarten {De Rijke}",
title = "Multi-interest Diversification for End-to-end
Sequential Recommendation",
journal = j-TOIS,
volume = "40",
number = "1",
pages = "20:1--20:30",
month = jan,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3475768",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Jan 5 13:39:59 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3475768",
abstract = "Sequential recommenders capture dynamic aspects of
users' interests by modeling sequential behavior.
Previous studies on sequential recommendations mostly
aim to identify users' main recent interests to
optimize the recommendation accuracy; they often
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{He:2022:GTU,
author = "Xiangnan He and Zhaochun Ren and Emine Yilmaz and Marc
Najork and Tat-Seng Chua",
title = "Graph Technologies for User Modeling and
Recommendation: Introduction to the Special Issue ---
{Part 1}",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "21:1--21:5",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3477596",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3477596",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Gatmiry:2022:NVP,
author = "Khashayar Gatmiry and Manuel Gomez-Rodriguez",
title = "The Network Visibility Problem",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "22:1--22:42",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3460475",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3460475",
abstract = "Social media is an attention economy where
broadcasters are constantly competing for attention in
their followers' feeds. Broadcasters are likely to
elicit greater attention from their followers if their
posts remain visible at the top of their followers'
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Cui:2022:SKA,
author = "Yue Cui and Hao Sun and Yan Zhao and Hongzhi Yin and
Kai Zheng",
title = "Sequential-Knowledge-Aware Next {POI} Recommendation:
a Meta-Learning Approach",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "23:1--23:22",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3460198",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3460198",
abstract = "Accurately recommending the next point of interest
(POI) has become a fundamental problem with the rapid
growth of location-based social networks. However,
sparse, imbalanced check-in data and diverse user
check-in patterns pose severe challenges for POI
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2022:HEH,
author = "Hao Wang and Defu Lian and Hanghang Tong and Qi Liu
and Zhenya Huang and Enhong Chen",
title = "{HyperSoRec}: Exploiting Hyperbolic User and Item
Representations with Multiple Aspects for Social-aware
Recommendation",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "24:1--24:28",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3463913",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3463913",
abstract = "Social recommendation has achieved great success in
many domains including e-commerce and location-based
social networks. Existing methods usually explore the
user-item interactions or user-user connections to
predict users' preference behaviors. However,
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Dai:2022:BRR,
author = "Xinyi Dai and Yunjia Xi and Weinan Zhang and Qing Liu
and Ruiming Tang and Xiuqiang He and Jiawei Hou and Jun
Wang and Yong Yu",
title = "Beyond Relevance Ranking: a General Graph Matching
Framework for Utility-Oriented Learning to Rank",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "25:1--25:29",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464303",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464303",
abstract = "Learning to rank from logged user feedback, such as
clicks or purchases, is a central component of many
real-world information systems. Different from
human-annotated relevance labels, the user feedback is
always noisy and biased. Many existing learning
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:LSC,
author = "Wei Zhang and Zeyuan Chen and Hongyuan Zha and
Jianyong Wang",
title = "Learning from Substitutable and Complementary
Relations for Graph-based Sequential Product
Recommendation",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "26:1--26:28",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464302",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464302",
abstract = "Sequential product recommendation, aiming at
predicting the products that a target user will
interact with soon, has become a hotspot topic. Most of
the sequential recommendation models focus on learning
from users' interacted product sequences in a
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Tian:2022:EGI,
author = "Zhiqiang Tian and Yezheng Liu and Jianshan Sun and
Yuanchun Jiang and Mingyue Zhu",
title = "Exploiting Group Information for Personalized
Recommendation with Graph Neural Networks",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "27:1--27:23",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3464764",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3464764",
abstract = "Personalized recommendation has become more and more
important for users to quickly find relevant items. The
key issue of the recommender system is how to model
user preferences. Previous work mostly employed user
historical data to learn users' \ldots{}",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:MGH,
author = "Chengyuan Zhang and Yang Wang and Lei Zhu and Jiayu
Song and Hongzhi Yin",
title = "Multi-Graph Heterogeneous Interaction Fusion for
Social Recommendation",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "28:1--28:26",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3466641",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3466641",
abstract = "With the rapid development of online social
recommendation system, substantial methods have been
proposed. Unlike traditional recommendation system,
social recommendation performs by integrating social
relationship features, where there are two major
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhou:2022:DAU,
author = "Sheng Zhou and Xin Wang and Martin Ester and Bolang Li
and Chen Ye and Zhen Zhang and Can Wang and Jiajun Bu",
title = "Direction-Aware User Recommendation Based on
Asymmetric Network Embedding",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "29:1--29:23",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3466754",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3466754",
abstract = "User recommendation aims at recommending users with
potential interests in the social network. Previous
works have mainly focused on the undirected social
networks with symmetric relationship such as
friendship, whereas recent advances have been made on
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Huang:2022:LLC,
author = "Xiaowen Huang and Jitao Sang and Jian Yu and
Changsheng Xu",
title = "Learning to Learn a Cold-start Sequential
Recommender",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "30:1--30:25",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3466753",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3466753",
abstract = "The cold-start recommendation is an urgent problem in
contemporary online applications. It aims to provide
users whose behaviors are literally sparse with as
accurate recommendations as possible. Many data-driven
algorithms, such as the widely used matrix \ldots{}",
acknowledgement = ack-nhfb,
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2022:BFG,
author = "Minghao Zhao and Qilin Deng and Kai Wang and Runze Wu
and Jianrong Tao and Changjie Fan and Liang Chen and
Peng Cui",
title = "Bilateral Filtering Graph Convolutional Network for
Multi-relational Social Recommendation in the Power-law
Networks",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "31:1--31:24",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3469799",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3469799",
abstract = "In recent years, advances in Graph Convolutional
Networks (GCNs) have given new insights into the
development of social recommendation. However, many
existing GCN-based social recommendation methods often
directly apply GCN to capture user-item and user-.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "31",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mansoury:2022:GBA,
author = "Masoud Mansoury and Himan Abdollahpouri and Mykola
Pechenizkiy and Bamshad Mobasher and Robin Burke",
title = "A Graph-Based Approach for Mitigating Multi-Sided
Exposure Bias in Recommender Systems",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "32:1--32:31",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3470948",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3470948",
abstract = "Fairness is a critical system-level objective in
recommender systems that has been the subject of
extensive recent research. A specific form of fairness
is supplier exposure fairness, where the objective is
to ensure equitable coverage of items across all
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "32",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yang:2022:LLI,
author = "Jun Yang and Weizhi Ma and Min Zhang and Xin Zhou and
Yiqun Liu and Shaoping Ma",
title = "{LegalGNN}: Legal Information Enhanced Graph Neural
Network for Recommendation",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "33:1--33:29",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3469887",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3469887",
abstract = "Recommendation in legal scenario (Legal-Rec) is a
specialized recommendation task that aims to provide
potential helpful legal documents for users. While
there are mainly three differences compared with
traditional recommendation: (1) Both the structural
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liang:2022:PUQ,
author = "Shangsong Liang and Yupeng Luo and Zaiqiao Meng",
title = "Profiling Users for Question Answering Communities via
Flow-Based Constrained Co-Embedding Model",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "34:1--34:38",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3470565",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3470565",
abstract = "In this article, we study the task of user profiling
in question answering communities (QACs). Previous user
profiling algorithms suffer from a number of defects:
they regard users and words as atomic units, leading to
the mismatch between them; they are \ldots{}",
acknowledgement = ack-nhfb,
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qiu:2022:EPI,
author = "Ruihong Qiu and Zi Huang and Tong Chen and Hongzhi
Yin",
title = "Exploiting Positional Information for Session-Based
Recommendation",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "35:1--35:24",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3473339",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3473339",
abstract = "For present e-commerce platforms, it is important to
accurately predict users' preference for a timely
next-item recommendation. To achieve this goal,
session-based recommender systems are developed, which
are based on a sequence of the most recent user-.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Pan:2022:PSA,
author = "Yaoxin Pan and Shangsong Liang and Jiaxin Ren and
Zaiqiao Meng and Qiang Zhang",
title = "Personalized, Sequential, Attentive, Metric-Aware
Product Search",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "36:1--36:29",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3473337",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3473337",
abstract = "The task of personalized product search aims at
retrieving a ranked list of products given a user's
input query and his/her purchase history. To address
this task, we propose the PSAM model, a Personalized,
Sequential, Attentive and Metric-aware (PSAM)
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2022:SGF,
author = "Hui Li and Lianyun Li and Guipeng Xv and Chen Lin and
Ke Li and Bingchuan Jiang",
title = "{SPEX}: a Generic Framework for Enhancing Neural
Social Recommendation",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "37:1--37:33",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3473338",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3473338",
abstract = "Social Recommender Systems (SRS) have attracted
considerable attention since its accompanying service,
social networks, helps increase user satisfaction and
provides auxiliary information to improve
recommendations. However, most existing SRS focus on
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhu:2022:LHI,
author = "Nengjun Zhu and Jian Cao and Xinjiang Lu and Hui
Xiong",
title = "Learning a Hierarchical Intent Model for Next-Item
Recommendation",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "38:1--38:28",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3473972",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3473972",
abstract = "A session-based recommender system (SBRS) captures
users' evolving behaviors and recommends the next item
by profiling users in terms of items in a session. User
intent and user preference are two factors affecting
his (her) decisions. Specifically, the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Vuong:2022:DMC,
author = "Tung Vuong and Salvatore Andolina and Giulio Jacucci
and Tuukka Ruotsalo",
title = "Does More Context Help? Effects of Context Window and
Application Source on Retrieval Performance",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "39:1--39:40",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3474055",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3474055",
abstract = "We study the effect of contextual information obtained
from a user's digital trace on Web search performance.
Contextual information is modeled using
Dirichlet-Hawkes processes (DHP) and used in augmenting
Web search queries. The context is captured by
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Nardini:2022:FFS,
author = "Franco Maria Nardini and Roberto Trani and Rossano
Venturini",
title = "Fast Filtering of Search Results Sorted by Attribute",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "40:1--40:24",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3477982",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3477982",
abstract = "Modern search services often provide multiple options
to rank the search results, e.g., sort ``by
relevance'', ``by price'' or ``by discount'' in
e-commerce. While the traditional rank by relevance
effectively places the relevant results in the top
positions of \ldots{}",
acknowledgement = ack-nhfb,
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhu:2022:EMM,
author = "Lei Zhu and Chaoqun Zheng and Xu Lu and Zhiyong Cheng
and Liqiang Nie and Huaxiang Zhang",
title = "Efficient Multi-modal Hashing with Online Query
Adaption for Multimedia Retrieval",
journal = j-TOIS,
volume = "40",
number = "2",
pages = "41:1--41:36",
month = apr,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3477180",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Feb 2 08:14:20 MST 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3477180",
abstract = "Multi-modal hashing supports efficient multimedia
retrieval well. However, existing methods still suffer
from two problems: (1) Fixed multi-modal fusion. They
collaborate the multi-modal features with fixed weights
for hash learning, which cannot \ldots{}",
acknowledgement = ack-nhfb,
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{He:2022:ISS,
author = "Xiangnan He and Zhaochun Ren and Emine Yilmaz and Marc
Najork and Tat-Seng Chua",
title = "Introduction to the Special Section on Graph
Technologies for User Modeling and Recommendation,
{Part 2}",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "42:1--42:5",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490180",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490180",
acknowledgement = ack-nhfb,
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yao:2022:CAK,
author = "Jing Yao and Zhicheng Dou and Ji-Rong Wen",
title = "Clarifying Ambiguous Keywords with Personal Word
Embeddings for Personalized Search",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "43:1--43:29",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3470564",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3470564",
abstract = "Personalized search tailors document ranking lists for
each individual user based on her interests and query
intent to better satisfy the user's information need.
Many personalized search models have been proposed.
They first build a user interest profile \ldots{}",
acknowledgement = ack-nhfb,
articleno = "43",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xie:2022:DGG,
author = "Zhiwen Xie and Runjie Zhu and Kunsong Zhao and Jin Liu
and Guangyou Zhou and Jimmy Xiangji Huang",
title = "Dual Gated Graph Attention Networks with Dynamic
Iterative Training for Cross-Lingual Entity Alignment",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "44:1--44:30",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3471165",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3471165",
abstract = "Cross-lingual entity alignment has attracted
considerable attention in recent years. Past studies
using conventional approaches to match entities share
the common problem of missing important structural
information beyond entities in the modeling process.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "44",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Jin:2022:GLI,
author = "Jiarui Jin and Kounianhua Du and Weinan Zhang and
Jiarui Qin and Yuchen Fang and Yong Yu and Zheng Zhang
and Alexander J. Smola",
title = "{GraphHINGE}: Learning Interaction Models of
Structured Neighborhood on Heterogeneous Information
Network",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "45:1--45:35",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3472956",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3472956",
abstract = "Heterogeneous information network (HIN) has been
widely used to characterize entities of various types
and their complex relations. Recent attempts either
rely on explicit path reachability to leverage
path-based semantic relatedness or graph neighborhood
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "45",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2022:DSR,
author = "Lili Wang and Chenghan Huang and Ying Lu and Weicheng
Ma and Ruibo Liu and Soroush Vosoughi",
title = "Dynamic Structural Role Node Embedding for User
Modeling in Evolving Networks",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "46:1--46:21",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3472955",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3472955",
abstract = "Complex user behavior, especially in settings such as
social media, can be organized as time-evolving
networks. Through network embedding, we can extract
general-purpose vector representations of these dynamic
networks which allow us to analyze them \ldots{}",
acknowledgement = ack-nhfb,
articleno = "46",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:ECF,
author = "Ge Zhang and Zhao Li and Jiaming Huang and Jia Wu and
Chuan Zhou and Jian Yang and Jianliang Gao",
title = "{eFraudCom}: an E-commerce Fraud Detection System via
Competitive Graph Neural Networks",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "47:1--47:29",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3474379",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3474379",
abstract = "With the development of e-commerce, fraud behaviors
have been becoming one of the biggest threats to the
e-commerce business. Fraud behaviors seriously damage
the ranking system of e-commerce platforms and
adversely influence the shopping experience of
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "47",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xie:2022:GNC,
author = "Qianqian Xie and Yutao Zhu and Jimin Huang and Pan Du
and Jian-Yun Nie",
title = "Graph Neural Collaborative Topic Model for Citation
Recommendation",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "48:1--48:30",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3473973",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3473973",
abstract = "Due to the overload of published scientific articles,
citation recommendation has long been a critical
research problem for automatically recommending the
most relevant citations of given articles. Relational
topic models (RTMs) have shown promise on \ldots{}",
acknowledgement = ack-nhfb,
articleno = "48",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zeng:2022:MGL,
author = "Xingshan Zeng and Jing Li and Lingzhi Wang and Kam-Fai
Wong",
title = "Modeling Global and Local Interactions for Online
Conversation Recommendation",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "49:1--49:33",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3473970",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3473970",
abstract = "The popularity of social media platforms results in a
huge volume of online conversations produced every day.
To help users better engage in online conversations,
this article presents a novel framework to
automatically recommend conversations to users
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "49",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhu:2022:BHD,
author = "Yadong Zhu and Xiliang Wang and Qing Li and Tianjun
Yao and Shangsong Liang",
title = "{BotSpot++}: a Hierarchical Deep Ensemble Model for
Bots Install Fraud Detection in Mobile Advertising",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "50:1--50:28",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3476107",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3476107",
abstract = "Mobile advertising has undoubtedly become one of the
fastest-growing industries in the world. The influx of
capital attracts increasing fraudsters to defraud money
from advertisers. Fraudsters can leverage many
techniques, where bots install fraud is the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "50",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2022:TIL,
author = "Jiashu Zhao and Jimmy Xiangji Huang and Hongbo Deng
and Yi Chang and Long Xia",
title = "Are Topics Interesting or Not? {An} {LDA}-based
Topic-graph Probabilistic Model for {Web} Search
Personalization",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "51:1--51:24",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3476106",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3476106",
abstract = "In this article, we propose a Latent Dirichlet
Allocation- (LDA) based topic-graph probabilistic
personalization model for Web search. This model
represents a user graph in a latent topic graph and
simultaneously estimates the probabilities that the
user \ldots{}",
acknowledgement = ack-nhfb,
articleno = "51",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2022:SCA,
author = "Dan Li and Tong Xu and Peilun Zhou and Weidong He and
Yanbin Hao and Yi Zheng and Enhong Chen",
title = "Social Context-aware Person Search in Videos via
Multi-modal Cues",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "52:1--52:25",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3480967",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3480967",
abstract = "Person search has long been treated as a crucial and
challenging task to support deeper insight in
personalized summarization and personality discovery.
Traditional methods, e.g., person re-identification and
face recognition techniques, which profile \ldots{}",
acknowledgement = ack-nhfb,
articleno = "52",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sen:2022:KWY,
author = "Procheta Sen and Debasis Ganguly and Gareth J. F.
Jones",
title = "{I} Know What You Need: Investigating Document
Retrieval Effectiveness with Partial Session Contexts",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "53:1--53:30",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3488667",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3488667",
abstract = "Reducing user effort in finding relevant information
is one of the key objectives of search systems.
Existing approaches have been shown to effectively
exploit the context from the current search session of
users for automatically suggesting queries to
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "53",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yan:2022:LTL,
author = "Surong Yan and Kwei-Jay Lin and Xiaolin Zheng and
Haosen Wang",
title = "{LkeRec}: Toward Lightweight End-to-End Joint
Representation Learning for Building Accurate and
Effective Recommendation",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "54:1--54:28",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3486673",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3486673",
abstract = "Explicit and implicit knowledge about users and items
have been used to describe complex and heterogeneous
side information for recommender systems (RSs). Many
existing methods use knowledge graph embedding (KGE) to
learn the representation of a user-item \ldots{}",
acknowledgement = ack-nhfb,
articleno = "54",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Bhoi:2022:PMR,
author = "Suman Bhoi and Mong Li Lee and Wynne Hsu and Hao Sen
Andrew Fang and Ngiap Chuan Tan",
title = "Personalizing Medication Recommendation with a
Graph-Based Approach",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "55:1--55:23",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3488668",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3488668",
abstract = "The broad adoption of electronic health records (EHRs)
has led to vast amounts of data being accumulated on a
patient's history, diagnosis, prescriptions, and lab
tests. Advances in recommender technologies have the
potential to utilize this information \ldots{}",
acknowledgement = ack-nhfb,
articleno = "55",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Paik:2022:TMP,
author = "Jiaul H. Paik and Yash Agrawal and Sahil Rishi and
Vaishal Shah",
title = "Truncated Models for Probabilistic Weighted
Retrieval",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "56:1--56:24",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3476837",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3476837",
abstract = "Existing probabilistic retrieval models do not
restrict the domain of the random variables that they
deal with. In this article, we show that the upper
bound of the normalized term frequency ( tf ) from the
relevant documents is much smaller than the upper
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "56",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2022:EHS,
author = "Meng Chen and Lei Zhu and Ronghui Xu and Yang Liu and
Xiaohui Yu and Yilong Yin",
title = "Embedding Hierarchical Structures for Venue Category
Representation",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "57:1--57:29",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3478285",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3478285",
abstract = "Venue categories used in location-based social
networks often exhibit a hierarchical structure,
together with the category sequences derived from
users' check-ins. The two data modalities provide a
wealth of information for us to capture the semantic
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "57",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Fang:2022:HVC,
author = "Jinyuan Fang and Shangsong Liang and Zaiqiao Meng and
Maarten {De Rijke}",
title = "Hyperspherical Variational Co-embedding for Attributed
Networks",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "58:1--58:36",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3478284",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3478284",
abstract = "Network-based information has been widely explored and
exploited in the information retrieval literature.
Attributed networks, consisting of nodes, edges as well
as attributes describing properties of nodes, are a
basic type of network-based data, and are \ldots{}",
acknowledgement = ack-nhfb,
articleno = "58",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Jayashree:2022:MWP,
author = "Srivatsa Ramesh Jayashree and Ga{\"e}l Dias and Judith
Jeyafreeda Andrew and Sriparna Saha and Fabrice Maurel
and St{\'e}phane Ferrari",
title = "Multimodal {Web} Page Segmentation Using
Self-organized Multi-objective Clustering",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "59:1--59:49",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3480966",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3480966",
abstract = "Web page segmentation (WPS) aims to break a web page
into different segments with coherent intra- and
inter-semantics. By evidencing the morpho-dispositional
semantics of a web page, WPS has traditionally been
used to demarcate informative from non-. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "59",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Moshfeghi:2022:GTA,
author = "Yashar Moshfeghi and Alvaro Francisco Huertas-Rosero",
title = "A Game Theory Approach for Estimating Reliability of
Crowdsourced Relevance Assessments",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "60:1--60:29",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3480965",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3480965",
abstract = "In this article, we propose an approach to improve
quality in crowdsourcing (CS) tasks using Task
Completion Time (TCT) as a source of information about
the reliability of workers in a game-theoretical
competitive scenario. Our approach is based on the
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "60",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Albahem:2022:CBA,
author = "Ameer Albahem and Damiano Spina and Falk Scholer and
Lawrence Cavedon",
title = "Component-based Analysis of Dynamic Search
Performance",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "61:1--61:47",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3483237",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3483237",
abstract = "In many search scenarios, such as exploratory,
comparative, or survey-oriented search, users interact
with dynamic search systems to satisfy multi-aspect
information needs. These systems utilize different
dynamic approaches that exploit various user \ldots{}",
acknowledgement = ack-nhfb,
articleno = "61",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Dang:2022:CBT,
author = "Edward Kai Fung Dang and Robert Wing Pong Luk and
James Allan",
title = "A Comparison between Term-Independence Retrieval
Models for Ad Hoc Retrieval",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "62:1--62:37",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3483612",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3483612",
abstract = "In Information Retrieval, numerous retrieval models or
document ranking functions have been developed in the
quest for better retrieval effectiveness. Apart from
some formal retrieval models formulated on a
theoretical basis, various recent works have \ldots{}",
acknowledgement = ack-nhfb,
articleno = "62",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sun:2022:UAA,
author = "Peijie Sun and Le Wu and Kun Zhang and Yu Su and Meng
Wang",
title = "An Unsupervised Aspect-Aware Recommendation Model with
Explanation Text Generation",
journal = j-TOIS,
volume = "40",
number = "3",
pages = "63:1--63:29",
month = jul,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3483611",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Apr 1 15:26:39 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3483611",
abstract = "Review based recommendation utilizes both users'
rating records and the associated reviews for
recommendation. Recently, with the rapid demand for
explanations of recommendation results, reviews are
used to train the encoder-decoder models for
explanation \ldots{}",
acknowledgement = ack-nhfb,
articleno = "63",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Fang:2022:SRL,
author = "Yang Fang and Xiang Zhao and Peixin Huang and Weidong
Xiao and Maarten de Rijke",
title = "Scalable Representation Learning for Dynamic
Heterogeneous Information Networks via Metagraphs",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "64:1--64:27",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3485189",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3485189",
abstract = "Content representation is a fundamental task in
information retrieval. Representation learning is aimed
at capturing features of an information object in a
low-dimensional space. Most research on representation
learning for heterogeneous information \ldots{}",
acknowledgement = ack-nhfb,
articleno = "64",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ji:2022:SAL,
author = "Weiyu Ji and Xiangwu Meng and Yujie Zhang",
title = "{STARec}: Adaptive Learning with Spatiotemporal and
Activity Influence for {POI} Recommendation",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "65:1--65:40",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3485631",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3485631",
abstract = "POI recommendation has become an essential means to
help people discover attractive places. Intuitively,
activities have an important impact on users'
decision-making, because users select POIs to attend
corresponding activities. However, many existing
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "65",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Guo:2022:SMF,
author = "Jiafeng Guo and Yinqiong Cai and Yixing Fan and Fei
Sun and Ruqing Zhang and Xueqi Cheng",
title = "Semantic Models for the First-Stage Retrieval: a
Comprehensive Review",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "66:1--66:42",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3486250",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3486250",
abstract = "Multi-stage ranking pipelines have been a practical
solution in modern search systems, where the
first-stage retrieval is to return a subset of
candidate documents and latter stages attempt to
re-rank those candidates. Unlike re-ranking stages
going \ldots{}",
acknowledgement = ack-nhfb,
articleno = "66",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Pan:2022:GCA,
author = "Zhiqiang Pan and Fei Cai and Wanyu Chen and Honghui
Chen",
title = "Graph Co-Attentive Session-based Recommendation",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "67:1--67:31",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3486711",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3486711",
abstract = "Session-based recommendation aims to generate
recommendations merely based on the ongoing session,
which is a challenging task. Previous methods mainly
focus on modeling the sequential signals or the
transition relations between items in the current
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "67",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:GTP,
author = "Chuxu Zhang and Julia Kiseleva and Sujay Kumar Jauhar
and Ryen W. White",
title = "Grounded Task Prioritization with Context-Aware
Sequential Ranking",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "68:1--68:28",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3486861",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3486861",
abstract = "People rely on task management applications and
digital assistants to capture and track their tasks,
and help with executing them. The burden of organizing
and scheduling time for tasks continues to reside with
users of these systems, despite the high \ldots{}",
acknowledgement = ack-nhfb,
articleno = "68",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Peng:2022:RNS,
author = "Hao Peng and Ruitong Zhang and Yingtong Dou and Renyu
Yang and Jingyi Zhang and Philip S. Yu",
title = "Reinforced Neighborhood Selection Guided
Multi-Relational Graph Neural Networks",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "69:1--69:46",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490181",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490181",
abstract = "Graph Neural Networks (GNNs) have been widely used for
the representation learning of various structured graph
data, typically through message passing among nodes by
aggregating their neighborhood information via
different operations. While promising, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "69",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2022:PEE,
author = "Chao Wang and Hengshu Zhu and Peng Wang and Chen Zhu
and Xi Zhang and Enhong Chen and Hui Xiong",
title = "Personalized and Explainable Employee Training Course
Recommendations: a {Bayesian} Variational Approach",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "70:1--70:32",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490476",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490476",
abstract = "As a major component of strategic talent management,
learning and development (L\&D) aims at improving the
individual and organization performances through
planning tailored training for employees to increase
and improve their skills and knowledge. While
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "70",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2022:FFM,
author = "Jinze Wang and Yongli Ren and Jie Li and Ke Deng",
title = "The Footprint of Factorization Models and Their
Applications in Collaborative Filtering",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "71:1--71:32",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490475",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490475",
abstract = "Factorization models have been successfully applied to
the recommendation problems and have significant impact
to both academia and industries in the field of
Collaborative Filtering (CF). However, the intermediate
data generated in factorization models' \ldots{}",
acknowledgement = ack-nhfb,
articleno = "71",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Pan:2022:CGL,
author = "Zhiqiang Pan and Fei Cai and Wanyu Chen and Chonghao
Chen and Honghui Chen",
title = "Collaborative Graph Learning for Session-based
Recommendation",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "72:1--72:26",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490479",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490479",
abstract = "Session-based recommendation (SBR), which mainly
relies on a user's limited interactions with items to
generate recommendations, is a widely investigated
task. Existing methods often apply RNNs or GNNs to
model user's sequential behavior or transition
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "72",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2022:CGC,
author = "Hongwei Wang and Jure Leskovec",
title = "Combining Graph Convolutional Neural Networks and
Label Propagation",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "73:1--73:27",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490478",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490478",
abstract = "Label Propagation Algorithm (LPA) and Graph
Convolutional Neural Networks (GCN) are both message
passing algorithms on graphs. Both solve the task of
node classification, but LPA propagates node label
information across the edges of the graph, while GCN
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "73",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xie:2022:LTI,
author = "Zhongwei Xie and Ling Liu and Yanzhao Wu and Luo Zhong
and Lin Li",
title = "Learning Text-image Joint Embedding for Efficient
Cross-modal Retrieval with Deep Feature Engineering",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "74:1--74:27",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490519",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490519",
abstract = "This article introduces a two-phase deep feature
engineering framework for efficient learning of
semantics enhanced joint embedding, which clearly
separates the deep feature engineering in data
preprocessing from training the text-image joint
embedding \ldots{}",
acknowledgement = ack-nhfb,
articleno = "74",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Cheng:2022:FLA,
author = "Zhiyong Cheng and Fan Liu and Shenghan Mei and
Yangyang Guo and Lei Zhu and Liqiang Nie",
title = "Feature-Level Attentive {ICF} for Recommendation",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "75:1--75:24",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3490477",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3490477",
abstract = "Item-based collaborative filtering (ICF) enjoys the
advantages of high recommendation accuracy and ease in
online penalization and thus is favored by the
industrial recommender systems. ICF recommends items to
a target user based on their similarities to \ldots{}",
acknowledgement = ack-nhfb,
articleno = "75",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sakai:2022:RAW,
author = "Tetsuya Sakai and Sijie Tao and Zhaohao Zeng",
title = "Relevance Assessments for {Web} Search Evaluation:
Should We Randomise or Prioritise the Pooled
Documents?",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "76:1--76:35",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3494833",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3494833",
abstract = "In the context of depth-$k$ pooling for constructing
web search test collections, we compare two approaches
to ordering pooled documents for relevance assessors:
The prioritisation strategy (PRI) used widely at NTCIR,
and the simple randomisation strategy \ldots{}",
acknowledgement = ack-nhfb,
articleno = "76",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Urgo:2022:UPT,
author = "Kelsey Urgo and Jaime Arguello",
title = "Understanding the {``Pathway''} Towards a Searcher's
Learning Objective",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "77:1--77:42",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3495222",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3495222",
abstract = "Search systems are often used to support
learning-oriented goals. This trend has given rise to
the ``search-as-learning'' movement, which proposes
that search systems should be designed to support
learning. To this end, an important research question
is: \ldots{}",
acknowledgement = ack-nhfb,
articleno = "77",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yu:2022:SHQ,
author = "Weiren Yu and Julie McCann and Chengyuan Zhang and
Hakan Ferhatosmanoglu",
title = "Scaling High-Quality Pairwise Link-Based Similarity
Retrieval on Billion-Edge Graphs",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "78:1--78:45",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3495209",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3495209",
abstract = "SimRank is an attractive link-based similarity measure
used in fertile fields of Web search and sociometry.
However, the existing deterministic method by Kusumoto
et al. [ 24 ] for retrieving SimRank does not always
produce high-quality similarity results, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "78",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:JPF,
author = "Peng Zhang and Baoxi Liu and Tun Lu and Xianghua Ding
and Hansu Gu and Ning Gu",
title = "Jointly Predicting Future Content in Multiple Social
Media Sites Based on Multi-task Learning",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "79:1--79:28",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3495530",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3495530",
abstract = "User-generated contents (UGC) in social media are the
direct expression of users' interests, preferences, and
opinions. User behavior prediction based on UGC has
increasingly been investigated in recent years.
Compared to learning a person's behavioral \ldots{}",
acknowledgement = ack-nhfb,
articleno = "79",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Tang:2022:RCI,
author = "Zhiwen Tang and Grace Hui Yang",
title = "A Re-classification of Information Seeking Tasks and
Their Computational Solutions",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "80:1--80:32",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3497875",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3497875",
abstract = "This article presents a re-classification of
information seeking (IS) tasks, concepts, and
algorithms. The proposed taxonomy provides new
dimensions to look into information seeking tasks and
methods. The new dimensions include number of search
iterations,. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "80",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Frummet:2022:WCC,
author = "Alexander Frummet and David Elsweiler and Bernd
Ludwig",
title = "{``What Can I Cook with these Ingredients?''} ---
Understanding Cooking-Related Information Needs in
Conversational Search",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "81:1--81:32",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3498330",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3498330",
abstract = "As conversational search becomes more pervasive, it
becomes increasingly important to understand the users'
underlying information needs when they converse with
such systems in diverse domains. We conduct an in situ
study to understand information needs \ldots{}",
acknowledgement = ack-nhfb,
articleno = "81",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2022:DGR,
author = "Yongqi Li and Wenjie Li and Liqiang Nie",
title = "Dynamic Graph Reasoning for Conversational Open-Domain
Question Answering",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "82:1--82:24",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3498557",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3498557",
abstract = "In recent years, conversational agents have provided a
natural and convenient access to useful information in
people's daily life, along with a broad and new
research topic, conversational question answering (QA).
On the shoulders of conversational QA, we \ldots{}",
acknowledgement = ack-nhfb,
articleno = "82",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2022:MSE,
author = "Rui Li and Cheng Yang and Tingwei Li and Sen Su",
title = "{MiDTD}: a Simple and Effective Distillation Framework
for Distantly Supervised Relation Extraction",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "83:1--83:32",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3503917",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3503917",
abstract = "Relation extraction (RE), an important information
extraction task, faced the great challenge brought by
limited annotation data. To this end, distant
supervision was proposed to automatically label RE
data, and thus largely increased the number of
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "83",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2022:CVN,
author = "Peng Zhang and Wenjie Hui and Benyou Wang and Donghao
Zhao and Dawei Song and Christina Lioma and Jakob Grue
Simonsen",
title = "Complex-valued Neural Network-based Quantum Language
Models",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "84:1--84:31",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3505138",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3505138",
abstract = "Language modeling is essential in Natural Language
Processing and Information Retrieval related tasks.
After the statistical language models, Quantum Language
Model (QLM) has been proposed to unify both single
words and compound terms in the same \ldots{}",
acknowledgement = ack-nhfb,
articleno = "84",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2022:SMR,
author = "Zhenduo Wang and Qingyao Ai",
title = "Simulating and Modeling the Risk of Conversational
Search",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "85:1--85:33",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3507357",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3507357",
abstract = "In conversational search, agents can interact with
users by asking clarifying questions to increase their
chance of finding better results. Many recent works and
shared tasks in both natural language processing and
information retrieval communities have \ldots{}",
acknowledgement = ack-nhfb,
articleno = "85",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhu:2022:LNG,
author = "Yutao Zhu and Ruihua Song and Jian-Yun Nie and Pan Du
and Zhicheng Dou and Jin Zhou",
title = "Leveraging Narrative to Generate Movie Script",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "86:1--86:32",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3507356",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3507356",
abstract = "Generating a text based on a predefined guideline is
an interesting but challenging problem. A series of
studies have been carried out in recent years. In
dialogue systems, researchers have explored driving a
dialogue based on a plan, while in story \ldots{}",
acknowledgement = ack-nhfb,
articleno = "86",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Deng:2022:TPA,
author = "Yang Deng and Yaliang Li and Wenxuan Zhang and Bolin
Ding and Wai Lam",
title = "Toward Personalized Answer Generation in E-Commerce
via Multi-perspective Preference Modeling",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "87:1--87:28",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3507782",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3507782",
abstract = "Recently, Product Question Answering (PQA) on
E-Commerce platforms has attracted increasing attention
as it can act as an intelligent online shopping
assistant and improve the customer shopping experience.
Its key function, automatic answer generation for
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "87",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Rahmani:2022:SAI,
author = "Hossein A. Rahmani and Mohammad Aliannejadi and Mitra
Baratchi and Fabio Crestani",
title = "A Systematic Analysis on the Impact of Contextual
Information on Point-of-Interest Recommendation",
journal = j-TOIS,
volume = "40",
number = "4",
pages = "88:1--88:35",
month = oct,
year = "2022",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3508478",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 16 10:23:24 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3508478",
abstract = "As the popularity of Location-based Social Networks
increases, designing accurate models for
Point-of-Interest (POI) recommendation receives more
attention. POI recommendation is often performed by
incorporating contextual information into previously
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "88",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lo:2023:CPR,
author = "Pei-Chi Lo and Ee-Peng Lim",
title = "Contextual Path Retrieval: a Contextual Entity
Relation Embedding-based Approach",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3502720",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3502720",
abstract = "Contextual path retrieval (CPR) refers to the task of
finding contextual path(s) between a pair of entities
in a knowledge graph that explains the connection
between them in a given context. For this novel
retrieval task, we propose the Embedding-based
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ling:2023:GRI,
author = "Yanxiang Ling and Fei Cai and Jun Liu and Honghui Chen
and Maarten de Rijke",
title = "Generating Relevant and Informative Questions for
Open-Domain Conversations",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3510612",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3510612",
abstract = "Recent research has highlighted the importance of
mixed-initiative interactions in conversational search.
To enable mixed-initiative interactions, information
retrieval systems should be able to ask diverse
questions, such as information-seeking, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zheng:2023:IAD,
author = "Zhi Zheng and Chao Wang and Tong Xu and Dazhong Shen
and Penggang Qin and Xiangyu Zhao and Baoxing Huai and
Xian Wu and Enhong Chen",
title = "Interaction-aware Drug Package Recommendation via
Policy Gradient",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3511020",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3511020",
abstract = "Recent years have witnessed the rapid accumulation of
massive electronic medical records, which highly
support intelligent medical services such as drug
recommendation. However, although there are multiple
interaction types between drugs, e.g., synergism
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ma:2023:KGK,
author = "Ting Ma and Longtao Huang and Qianqian Lu and Songlin
Hu",
title = "{KR-GCN}: Knowledge-Aware Reasoning with Graph
Convolution Network for Explainable Recommendation",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3511019",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3511019",
abstract = "Incorporating knowledge graphs (KGs) into recommender
systems to provide explainable recommendation has
attracted much attention recently. The multi-hop paths
in KGs can provide auxiliary facts for improving
recommendation performance as well as \ldots{}",
acknowledgement = ack-nhfb,
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:UBS,
author = "Junqi Zhang and Yiqun Liu and Jiaxin Mao and Weizhi Ma
and Jiazheng Xu and Shaoping Ma and Qi Tian",
title = "User Behavior Simulation for Search Result
Re-ranking",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "5:1--5:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3511469",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3511469",
abstract = "Result ranking is one of the major concerns for Web
search technologies. Most existing methodologies rank
search results in descending order of relevance. To
model the interactions among search results,
reinforcement learning (RL algorithms have been
\ldots{})",
acknowledgement = ack-nhfb,
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Huang:2023:PET,
author = "Liwei Huang and Yutao Ma and Yanbo Liu and Bohong
Danny Du and Shuliang Wang and Deyi Li",
title = "Position-Enhanced and Time-aware Graph Convolutional
Network for Sequential Recommendations",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "6:1--6:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3511700",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3511700",
abstract = "The sequential recommendation (also known as the
next-item recommendation), which aims to predict the
following item to recommend in a session according to
users' historical behavior, plays a critical role in
improving session-based recommender systems. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2023:HSI,
author = "Bing Li and Peng Yang and Hanlin Zhao and Penghui
Zhang and Zijian Liu",
title = "Hierarchical Sliding Inference Generator for
Question-driven Abstractive Answer Summarization",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "7:1--7:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3511891",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3511891",
abstract = "Text summarization on non-factoid question answering
(NQA) aims at identifying the core information of
redundant answer guidance using questions, which can
dramatically improve answer readability and
comprehensibility. Most existing approaches focus on
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Feng:2023:RRP,
author = "Chao Feng and Defu Lian and Xiting Wang and Zheng Liu
and Xing Xie and Enhong Chen",
title = "Reinforcement Routing on Proximity Graph for Efficient
Recommendation",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "8:1--8:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3512767",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3512767",
abstract = "We focus on Maximum Inner Product Search (MIPS), which
is an essential problem in many machine learning
communities. Given a query, MIPS finds the most similar
items with the maximum inner products. Methods for
Nearest Neighbor Search (NNS) which is \ldots{}",
acknowledgement = ack-nhfb,
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2023:FTG,
author = "Xiuying Chen and Mingzhe Li and Shen Gao and Zhangming
Chan and Dongyan Zhao and Xin Gao and Xiangliang Zhang
and Rui Yan",
title = "Follow the Timeline! Generating an Abstractive and
Extractive Timeline Summary in Chronological Order",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "9:1--9:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3517221",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3517221",
abstract = "Today, timestamped web documents related to a general
news query flood the Internet, and timeline
summarization targets this concisely by summarizing the
evolution trajectory of events along the timeline.
Unlike traditional document summarization, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Shang:2023:LRT,
author = "Yu-Ming Shang and Heyan Huang and Xin Sun and Wei Wei
and Xian-Ling Mao",
title = "Learning Relation Ties with a Force-Directed Graph in
Distant Supervised Relation Extraction",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "10:1--10:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3520082",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3520082",
abstract = "Relation ties, defined as the correlation and mutual
exclusion between different relations, are critical for
distant supervised relation extraction. Previous
studies usually obtain this property by greedily
learning the local connections between \ldots{}",
acknowledgement = ack-nhfb,
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2023:SRM,
author = "Chenyang Wang and Weizhi Ma and Chong Chen and Min
Zhang and Yiqun Liu and Shaoping Ma",
title = "Sequential Recommendation with Multiple Contrast
Signals",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "11:1--11:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3522673",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3522673",
abstract = "Sequential recommendation has become a trending
research topic for its capability to capture dynamic
user intents based on historical interaction sequence.
To train a sequential recommendation model, it is a
common practice to optimize the next-item \ldots{}",
acknowledgement = ack-nhfb,
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2023:RNS,
author = "Chong Chen and Weizhi Ma and Min Zhang and Chenyang
Wang and Yiqun Liu and Shaoping Ma",
title = "Revisiting Negative Sampling vs. Non-sampling in
Implicit Recommendation",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "12:1--12:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3522672",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3522672",
abstract = "Recommendation systems play an important role in
alleviating the information overload issue. Generally,
a recommendation model is trained to discern between
positive (liked) and negative (disliked) instances for
each user. However, under the open-world \ldots{}",
acknowledgement = ack-nhfb,
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Tian:2023:CPM,
author = "Yuan Tian and Ke Zhou and Dan Pelleg",
title = "Characterization and Prediction of Mobile Tasks",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "13:1--13:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3522711",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3522711",
abstract = "Mobile devices have become an increasingly ubiquitous
part of our everyday life. We use mobile services to
perform a broad range of tasks (e.g., booking travel or
conducting remote office work), leading to often
lengthy interactions with several distinct \ldots{}",
acknowledgement = ack-nhfb,
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2023:TET,
author = "Xu Chen and Ya Zhang and Ivor W. Tsang and Yuangang
Pan and Jingchao Su",
title = "Toward Equivalent Transformation of User Preferences
in Cross Domain Recommendation",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "14:1--14:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3522762",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3522762",
abstract = "Cross domain recommendation (CDR) is one popular
research topic in recommender systems. This article
focuses on a popular scenario for CDR where different
domains share the same set of users but no overlapping
items. The majority of recent methods have \ldots{}",
acknowledgement = ack-nhfb,
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:SDA,
author = "Weinan Zhang and Yiming Cui and Kaiyan Zhang and Yifa
Wang and Qingfu Zhu and Lingzhi Li and Ting Liu",
title = "A Static and Dynamic Attention Framework for Multi
Turn Dialogue Generation",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "15:1--15:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3522763",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3522763",
abstract = "Recently, research on open domain dialogue systems
have attracted extensive interests of academic and
industrial researchers. The goal of an open domain
dialogue system is to imitate humans in conversations.
Previous works on single turn conversation \ldots{}",
acknowledgement = ack-nhfb,
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zou:2023:UMC,
author = "Jie Zou and Mohammad Aliannejadi and Evangelos
Kanoulas and Maria Soledad Pera and Yiqun Liu",
title = "Users Meet Clarifying Questions: Toward a Better
Understanding of User Interactions for Search
Clarification",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "16:1--16:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3524110",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3524110",
abstract = "The use of clarifying questions (CQs) is a fairly new
and useful technique to aid systems in recognizing the
intent, context, and preferences behind user queries.
Yet, understanding the extent of the effect of CQs on
user behavior and the ability to \ldots{}",
acknowledgement = ack-nhfb,
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:KEA,
author = "Yingying Zhang and Xian Wu and Quan Fang and
Shengsheng Qian and Changsheng Xu",
title = "Knowledge-Enhanced Attributed Multi-Task Learning for
Medicine Recommendation",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "17:1--17:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3527662",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3527662",
abstract = "Medicine recommendation systems target to recommend a
set of medicines given a set of symptoms which play a
crucial role in assisting doctors in their daily
clinics. Existing approaches are either rule-based or
supervised. However, the former heavily \ldots{}",
acknowledgement = ack-nhfb,
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Choi:2023:IKR,
author = "Bogeum Choi and Jaime Arguello and Robert Capra and
Austin R. Ward",
title = "The Influences of a Knowledge Representation Tool on
Searchers with Varying Cognitive Abilities",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "18:1--18:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3527661",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3527661",
abstract = "While current systems are effective in helping
searchers resolve simple information needs (e.g.,
fact-finding), they provide less support for searchers
working on complex information-seeking tasks. Complex
search tasks involve a wide range of (meta). \ldots{}",
acknowledgement = ack-nhfb,
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2023:CPT,
author = "Hui Wang and Kun Zhou and Xin Zhao and Jingyuan Wang
and Ji-Rong Wen",
title = "Curriculum Pre-training Heterogeneous Subgraph
Transformer for Top-{$N$} Recommendation",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "19:1--19:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3528667",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3528667",
abstract = "To characterize complex and heterogeneous side
information in recommender systems, the heterogeneous
information network (HIN) has shown superior
performance and attracted much research attention. In
HIN, the rich entities, relations, and paths can be
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wan:2023:MCH,
author = "Qizhi Wan and Changxuan Wan and Keli Xiao and Rong Hu
and Dexi Liu",
title = "A Multi-channel Hierarchical Graph Attention Network
for Open Event Extraction",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "20:1--20:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3528668",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3528668",
abstract = "Event extraction is an essential task in natural
language processing. Although extensively studied,
existing work shares issues in three aspects, including
(1) the limitations of using original syntactic
dependency structure, (2) insufficient \ldots{}",
acknowledgement = ack-nhfb,
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2023:IRI,
author = "Haonan Chen and Zhicheng Dou and Qiannan Zhu and
Xiaochen Zuo and Ji-Rong Wen",
title = "Integrating Representation and Interaction for
Context-Aware Document Ranking",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "21:1--21:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3529955",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3529955",
abstract = "Recent studies show that historical behaviors (such as
queries and their clicks) contained in a search session
can benefit the ranking performance of subsequent
queries in the session. Existing neural context-aware
ranking models usually rank documents \ldots{}",
acknowledgement = ack-nhfb,
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liang:2023:FSA,
author = "Bin Liang and Xiang Li and Lin Gui and Yonghao Fu and
Yulan He and Min Yang and Ruifeng Xu",
title = "Few-shot Aspect Category Sentiment Analysis via
Meta-learning",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "22:1--22:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3529954",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3529954",
abstract = "Existing aspect-based/category sentiment analysis
methods have shown great success in detecting sentiment
polarity toward a given aspect in a sentence with
supervised learning, where the training and inference
stages share the same pre-defined set of \ldots{}",
acknowledgement = ack-nhfb,
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2023:PGS,
author = "Shiwei Zhao and Runze Wu and Jianrong Tao and Manhu Qu
and Minghao Zhao and Changjie Fan and Hongke Zhao",
title = "{perCLTV}: a General System for Personalized Customer
Lifetime Value Prediction in Online Games",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "23:1--23:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3530012",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3530012",
abstract = "Online games make up the largest segment of the
booming global game market in terms of revenue as well
as players. Unlike games that sell games at one time
for profit, online games make money from in-game
purchases by a large number of engaged players.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wu:2023:PNR,
author = "Chuhan Wu and Fangzhao Wu and Yongfeng Huang and Xing
Xie",
title = "Personalized News Recommendation: Methods and
Challenges",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "24:1--24:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3530257",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3530257",
abstract = "Personalized news recommendation is important for
users to find interesting news information and
alleviate information overload. Although it has been
extensively studied over decades and has achieved
notable success in improving user experience, there are
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Gaeta:2023:RQV,
author = "Rossano Gaeta and Michele Garetto and Giancarlo Ruffo
and Alessandro Flammini",
title = "Reconciling the Quality vs Popularity Dichotomy in
Online Cultural Markets",
journal = j-TOIS,
volume = "41",
number = "1",
pages = "25:1--25:??",
month = jan,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3530790",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3530790",
abstract = "We propose a simple model of an idealized online
cultural market in which N items, endowed with a hidden
quality metric, are recommended to users by a ranking
algorithm possibly biased by the current items'
popularity. Our goal is to better understand the
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2023:TAP,
author = "Yuyue Zhao and Xiang Wang and Jiawei Chen and Yashen
Wang and Wei Tang and Xiangnan He and Haiyong Xie",
title = "Time-aware Path Reasoning on Knowledge Graph for
Recommendation",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "26:1--26:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3531267",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3531267",
abstract = "Reasoning on knowledge graph (KG) has been studied for
explainable recommendation due to its ability of
providing explicit explanations. However, current
KG-based explainable recommendation methods
unfortunately ignore the temporal information (such as
\ldots{})",
acknowledgement = ack-nhfb,
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sun:2023:LIE,
author = "Kai Sun and Richong Zhang and Samuel Mensah and Yongyi
Mao and Xudong Liu",
title = "Learning Implicit and Explicit Multi-task Interactions
for Information Extraction",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "27:1--27:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3533020",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3533020",
abstract = "Information extraction aims at extracting entities,
relations, and so on, in text to support information
retrieval systems. To extract information, researchers
have considered multitask learning (ML) approaches. The
conventional ML approach learns shared \ldots{}",
acknowledgement = ack-nhfb,
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:KBE,
author = "Richong Zhang and Jaein Kim and Jiajie Mei and Yongyi
Mao",
title = "Knowledge Base Embedding for Sampling-Based
Prediction",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "28:1--28:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3533769",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3533769",
abstract = "Each link prediction task requires different degrees
of answer diversity. While a link prediction task may
expect up to a couple of answers, another may expect
nearly a hundred answers. Given this fact, the
performance of a link prediction model can be
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wu:2023:NRM,
author = "Chen Wu and Ruqing Zhang and Jiafeng Guo and Yixing
Fan and Xueqi Cheng",
title = "Are Neural Ranking Models Robust?",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "29:1--29:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3534928",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3534928",
abstract = "Recently, we have witnessed the bloom of neural
ranking models in the information retrieval (IR) field.
So far, much effort has been devoted to developing
effective neural ranking models that can generalize
well on new data. There has been less attention
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2023:MME,
author = "Kang Liu and Feng Xue and Dan Guo and Le Wu and Shujie
Li and Richang Hong",
title = "{MEGCF}: Multimodal Entity Graph Collaborative
Filtering for Personalized Recommendation",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "30:1--30:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3544106",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3544106",
abstract = "In most E-commerce platforms, whether the displayed
items trigger the user's interest largely depends on
their most eye-catching multimodal content.
Consequently, increasing efforts focus on modeling
multimodal user preference, and the pressing paradigm
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Hao:2023:MSB,
author = "Bowen Hao and Hongzhi Yin and Jing Zhang and Cuiping
Li and Hong Chen",
title = "A Multi-strategy-based Pre-training Method for
Cold-start Recommendation",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "31:1--31:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3544107",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3544107",
abstract = "The cold-start issue is a fundamental challenge in
Recommender Systems. The recent self-supervised
learning (SSL) on Graph Neural Networks (GNNs) model,
PT-GNN, pre-trains the GNN model to reconstruct the
cold-start embeddings and has shown great \ldots{}",
acknowledgement = ack-nhfb,
articleno = "31",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2023:RSA,
author = "Wayne Xin Zhao and Zihan Lin and Zhichao Feng and
Pengfei Wang and Ji-Rong Wen",
title = "A Revisiting Study of Appropriate Offline Evaluation
for Top-{$N$} Recommendation Algorithms",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "32:1--32:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3545796",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3545796",
abstract = "In recommender systems, top- N recommendation is an
important task with implicit feedback data. Although
the recent success of deep learning largely pushes
forward the research on top- N recommendation, there
are increasing concerns on appropriate \ldots{}",
acknowledgement = ack-nhfb,
articleno = "32",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wu:2023:AAE,
author = "Hanrui Wu and Jinyi Long and Nuosi Li and Dahai Yu and
Michael K. Ng",
title = "Adversarial Auto-encoder Domain Adaptation for
Cold-start Recommendation with Positive and Negative
Hypergraphs",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "33:1--33:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3544105",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3544105",
abstract = "This article presents a novel model named Adversarial
Auto-encoder Domain Adaptation to handle the
recommendation problem under cold-start settings.
Specifically, we divide the hypergraph into two
hypergraphs, i.e., a positive hypergraph and a negative
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qin:2023:GGD,
author = "Xubo Qin and Zhicheng Dou and Yutao Zhu and Ji-Rong
Wen",
title = "{GDESA}: Greedy Diversity Encoder with Self-attention
for Search Results Diversification",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "34:1--34:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3544103",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3544103",
abstract = "Search result diversification aims to generate
diversified search results so as to meet the various
information needs of users. Most of those existing
diversification methods greedily select the optimal
documents one-by-one comparing with the selected
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:PPP,
author = "Peng-Fei Zhang and Guangdong Bai and Hongzhi Yin and
Zi Huang",
title = "Proactive Privacy-preserving Learning for Cross-modal
Retrieval",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "35:1--35:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3545799",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3545799",
abstract = "Deep cross-modal retrieval techniques have recently
achieved remarkable performance, which also poses
severe threats to data privacy potentially. Nowadays,
enormous user-generated contents that convey personal
information are released and shared on the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Moreo:2023:GFE,
author = "Alejandro Moreo and Andrea Pedrotti and Fabrizio
Sebastiani",
title = "Generalized Funnelling: Ensemble Learning and
Heterogeneous Document Embeddings for Cross-Lingual
Text Classification",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "36:1--36:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3544104",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3544104",
abstract = "Funnelling (Fun) is a recently proposed method for
cross-lingual text classification (CLTC) based on a
two-tier learning ensemble for heterogeneous transfer
learning (HTL). In this ensemble method, 1st-tier
classifiers, each working on a different and \ldots{}",
acknowledgement = ack-nhfb,
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zheng:2023:SAK,
author = "Jianming Zheng and Fei Cai and Yanxiang Ling and
Honghui Chen",
title = "Sequence-aware Knowledge Distillation for a
Lightweight Event Representation",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "37:1--37:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3545798",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3545798",
abstract = "Event representation targets to model the
event-reasoning process as a machine-readable format.
Previous studies on event representation mostly
concentrate on a sole modeling perspective and have not
well investigated the scenario-level knowledge, which
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Datta:2023:RIG,
author = "Suchana Datta and Debasis Ganguly and Mandar Mitra and
Derek Greene",
title = "A Relative Information Gain-based Query Performance
Prediction Framework with Generated Query Variants",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "38:1--38:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3545112",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3545112",
abstract = "Query performance prediction (QPP) methods, which aim
to predict the performance of a query, often rely on
evidences in the form of different characteristic
patterns in the distribution of Retrieval Status Values
(RSVs). However, for neural IR models, it \ldots{}",
acknowledgement = ack-nhfb,
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:MML,
author = "Hang Zhang and Yajun Yang and Xin Wang and Hong Gao
and Qinghua Hu",
title = "{MLI}: a Multi-level Inference Mechanism for User
Attributes in Social Networks",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "39:1--39:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3545797",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3545797",
abstract = "In the social network, each user has attributes for
self-description called user attributes, which are
semantically hierarchical. Attribute inference has
become an essential way for social platforms to realize
user classifications and targeted \ldots{}",
acknowledgement = ack-nhfb,
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lin:2023:GFR,
author = "Zhaohao Lin and Weike Pan and Qiang Yang and Zhong
Ming",
title = "A Generic Federated Recommendation Framework via Fake
Marks and Secret Sharing",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "40:1--40:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3548456",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3548456",
abstract = "With the implementation of privacy protection laws
such as GDPR, it is increasingly difficult for
organizations to legally collect users' data. However,
a typical machine learning-based recommendation
algorithm requires the data to learn users' \ldots{}",
acknowledgement = ack-nhfb,
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Cheng:2023:CSH,
author = "Lizhi Cheng and Weijia Jia and Wenmian Yang",
title = "Capture Salient Historical Information: a Fast and
Accurate Non-autoregressive Model for Multi-turn Spoken
Language Understanding",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "41:1--41:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3545800",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3545800",
abstract = "Spoken Language Understanding (SLU), a core component
of the task-oriented dialogue system, expects a shorter
inference facing the impatience of human users.
Existing work increases inference speed by designing
non-autoregressive models for single-turn \ldots{}",
acknowledgement = ack-nhfb,
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zang:2023:SCD,
author = "Tianzi Zang and Yanmin Zhu and Haobing Liu and Ruohan
Zhang and Jiadi Yu",
title = "A Survey on Cross-domain Recommendation: Taxonomies,
Methods, and Future Directions",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "42:1--42:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3548455",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3548455",
abstract = "Traditional recommendation systems are faced with two
long-standing obstacles, namely data sparsity and
cold-start problems, which promote the emergence and
development of Cross-Domain Recommendation (CDR). The
core idea of CDR is to leverage information \ldots{}",
acknowledgement = ack-nhfb,
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2023:AGP,
author = "Yiqi Wang and Chaozhuo Li and Zheng Liu and Mingzheng
Li and Jiliang Tang and Xing Xie and Lei Chen and
Philip S. Yu",
title = "An Adaptive Graph Pre-training Framework for Localized
Collaborative Filtering",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "43:1--43:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3555372",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3555372",
abstract = "Graph neural networks (GNNs) have been widely applied
in the recommendation tasks and have achieved very
appealing performance. However, most GNN-based
recommendation methods suffer from the problem of data
sparsity in practice. Meanwhile, pre-training
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "43",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Huang:2023:PGH,
author = "Zhenya Huang and Binbin Jin and Hongke Zhao and Qi Liu
and Defu Lian and Bao Tengfei and Enhong Chen",
title = "Personal or General? {A} Hybrid Strategy with
Multi-factors for News Recommendation",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "44:1--44:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3555373",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3555373",
abstract = "News recommender systems have become an effective
manner to help users make decisions by suggesting the
potential news that users may click and read, which has
shown the proliferation nowadays. Many representative
algorithms made great efforts to discover \ldots{}",
acknowledgement = ack-nhfb,
articleno = "44",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zou:2023:LAC,
author = "Jie Zou and Jimmy Huang and Zhaochun Ren and Evangelos
Kanoulas",
title = "Learning to Ask: Conversational Product Search via
Representation Learning",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "45:1--45:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3555371",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3555371",
abstract = "Online shopping platforms, such as Amazon and
AliExpress, are increasingly prevalent in society,
helping customers purchase products conveniently. With
recent progress in natural language processing,
researchers and practitioners shift their focus from
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "45",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2023:FUM,
author = "Qi Liu and Jinze Wu and Zhenya Huang and Hao Wang and
Yuting Ning and Ming Chen and Enhong Chen and Jinfeng
Yi and Bowen Zhou",
title = "Federated User Modeling from Hierarchical
Information",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "46:1--46:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3560485",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3560485",
abstract = "The generation of large amounts of personal data
provides data centers with sufficient resources to mine
idiosyncrasy from private records. User modeling has
long been a fundamental task with the goal of capturing
the latent characteristics of users from \ldots{}",
acknowledgement = ack-nhfb,
articleno = "46",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wu:2023:MOO,
author = "Haolun Wu and Chen Ma and Bhaskar Mitra and Fernando
Diaz and Xue Liu",
title = "A Multi-Objective Optimization Framework for
Multi-Stakeholder Fairness-Aware Recommendation",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "47:1--47:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3564285",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3564285",
abstract = "Nowadays, most online services are hosted on
multi-stakeholder marketplaces, where consumers and
producers may have different objectives. Conventional
recommendation systems, however, mainly focus on
maximizing consumers' satisfaction by recommending the
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "47",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lu:2023:UPR,
author = "Hongyu Lu and Weizhi Ma and Yifan Wang and Min Zhang
and Xiang Wang and Yiqun Liu and Tat-Seng Chua and
Shaoping Ma",
title = "User Perception of Recommendation Explanation: Are
Your Explanations What Users Need?",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "48:1--48:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3565480",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3565480",
abstract = "As recommender systems become increasingly important
in daily human decision-making, users are demanding
convincing explanations to understand why they get the
specific recommendation results. Although a number of
explainable recommender systems have \ldots{}",
acknowledgement = ack-nhfb,
articleno = "48",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Rizzo:2023:RMT,
author = "Stefano Giovanni Rizzo and Matteo Brucato and Danilo
Montesi",
title = "Ranking Models for the Temporal Dimension of Text",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "49:1--49:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3565481",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3565481",
abstract = "Temporal features of text have been shown to improve
clustering and organization of documents, text
classification, visualization, and ranking. Temporal
ranking models consider the temporal expressions found
in text (e.g., ``in 2021'' or ``last year'') as
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "49",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Fei:2023:RAB,
author = "Hao Fei and Tat-Seng Chua and Chenliang Li and
Donghong Ji and Meishan Zhang and Yafeng Ren",
title = "On the Robustness of Aspect-based Sentiment Analysis:
Rethinking Model, Data, and Training",
journal = j-TOIS,
volume = "41",
number = "2",
pages = "50:1--50:??",
month = apr,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3564281",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Mon May 1 07:56:18 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3564281",
abstract = "Aspect-based sentiment analysis (ABSA) aims at
automatically inferring the specific sentiment
polarities toward certain aspects of products or
services behind the social media texts or reviews,
which has been a fundamental application to the
real-world \ldots{}",
acknowledgement = ack-nhfb,
articleno = "50",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yin:2023:TRSa,
author = "Hongzhi Yin and Yizhou Sun and Guandong Xu and
Evangelos Kanoulas",
title = "Trustworthy Recommendation and Search: Introduction to
the Special Issue --- {Part 1}",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "51:1--51:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3579995",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3579995",
acknowledgement = ack-nhfb,
articleno = "51",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2023:SFR,
author = "Yifan Wang and Weizhi Ma and Min Zhang and Yiqun Liu
and Shaoping Ma",
title = "A Survey on the Fairness of Recommender Systems",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "52:1--52:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3547333",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3547333",
abstract = "Recommender systems are an essential tool to relieve
the information overload challenge and play an
important role in people's daily lives. Since
recommendations \ldots{}",
acknowledgement = ack-nhfb,
articleno = "52",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{He:2023:ACF,
author = "Xiangnan He and Yang Zhang and Fuli Feng and Chonggang
Song and Lingling Yi and Guohui Ling and Yongdong
Zhang",
title = "Addressing Confounding Feature Issue for Causal
Recommendation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "53:1--53:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3559757",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3559757",
abstract = "In recommender systems, some features directly affect
whether an interaction would happen, making the
happened interactions not necessarily indicate user
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "53",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhu:2023:EQB,
author = "Lei Zhu and Tianshi Wang and Jingjing Li and Zheng
Zhang and Jialie Shen and Xinhua Wang",
title = "Efficient Query-based Black-box Attack against
Cross-modal Hashing Retrieval",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "54:1--54:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3559758",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3559758",
abstract = "Deep cross-modal hashing retrieval models inherit the
vulnerability of deep neural networks. They are
vulnerable to adversarial attacks, especially for the
form of subtle perturbations to the inputs. Although
many adversarial attack methods have been proposed to
handle the robustness of hashing retrieval models, they
still suffer from two problems: (1) Most of them are
based on the white-box settings, which is usually
unrealistic in practical application. (2) Iterative
optimization for the generation of adversarial examples
in them results in heavy computation. To address these
problems, we propose an Efficient Query-based Black-Box
Attack (EQB$^2$A) against deep cross-modal hashing
retrieval, which can efficiently generate adversarial
examples for the black-box attack. Specifically, by
sending a few query requests to the attacked retrieval
system, the cross-modal retrieval model stealing is
performed based on the neighbor relationship between
the retrieved results and the query, thus obtaining the
knockoffs to substitute the attacked system. A
multi-modal knockoffs-driven adversarial generation is
proposed to achieve efficient adversarial example
generation. While the entire network training
converges, EQB2A can efficiently generate adversarial
examples by forward-propagation with only given benign
images. Experiments show that EQB2A achieves superior
attacking performance under the black-box setting.",
acknowledgement = ack-nhfb,
articleno = "54",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2023:MPB,
author = "Zhongzhou Liu and Yuan Fang and Min Wu",
title = "Mitigating Popularity Bias for Users and Items with
Fairness-centric Adaptive Recommendation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "55:1--55:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3564286",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3564286",
abstract = "Recommendation systems are popular in many domains.
Researchers usually focus on the effectiveness of
recommendation (e.g., precision) but neglect the
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "55",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Dong:2023:DPD,
author = "Xue Dong and Xuemeng Song and Na Zheng and Yinwei Wei
and Zhongzhou Zhao",
title = "Dual Preference Distribution Learning for Item
Recommendation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "56:1--56:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3565798",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3565798",
abstract = "Recommender systems can automatically recommend users
with items that they probably like. The goal of them is
to model the user-item interaction by \ldots{}",
acknowledgement = ack-nhfb,
articleno = "56",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xin:2023:UBL,
author = "Xin Xin and Jiyuan Yang and Hanbing Wang and Jun Ma
and Pengjie Ren and Hengliang Luo and Xinlei Shi and
Zhumin Chen and Zhaochun Ren",
title = "On the User Behavior Leakage from Recommender System
Exposure",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "57:1--57:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3568954",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3568954",
abstract = "Modern recommender systems are trained to predict
users' potential future interactions from users'
historical behavior data. During the interaction
process, despite \ldots{}",
acknowledgement = ack-nhfb,
articleno = "57",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Thanh:2023:PGB,
author = "Toan Nguyen Thanh and Nguyen Duc Khang Quach and Thanh
Tam Nguyen and Thanh Trung Huynh and Viet Hung Vu and
Phi Le Nguyen and Jun Jo and Quoc Viet Hung Nguyen",
title = "Poisoning {GNN}-based Recommender Systems with
Generative Surrogate-based Attacks",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "58:1--58:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3567420",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3567420",
abstract = "With recent advancements in graph neural networks
(GNN), GNN-based recommender systems (gRS) have
achieved remarkable success in the past few years.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "58",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ye:2023:TRN,
author = "Haibo Ye and Xinjie Li and Yuan Yao and Hanghang
Tong",
title = "Towards Robust Neural Graph Collaborative Filtering
via Structure Denoising and Embedding Perturbation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "59:1--59:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3568396",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3568396",
abstract = "Neural graph collaborative filtering has received
great recent attention due to its power of encoding the
high-order neighborhood via the backbone \ldots{}",
acknowledgement = ack-nhfb,
articleno = "59",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2023:SID,
author = "Ziqian Chen and Fei Sun and Yifan Tang and Haokun Chen
and Jinyang Gao and Bolin Ding",
title = "Studying the Impact of Data Disclosure Mechanism in
Recommender Systems via Simulation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "60:1--60:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3569452",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3569452",
abstract = "Recently, privacy issues in web services that rely on
users' personal data have raised great attention.
Despite that recent regulations force companies to
offer choices \ldots{}",
acknowledgement = ack-nhfb,
articleno = "60",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Oosterhuis:2023:DRE,
author = "Harrie Oosterhuis",
title = "Doubly Robust Estimation for Correcting Position Bias
in Click Feedback for Unbiased Learning to Rank",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "61:1--61:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3569453",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3569453",
abstract = "Clicks on rankings suffer from position bias:
generally items on lower ranks are less likely to be
examined-and thus clicked-by users, in spite of their
actual preferences \ldots{}",
acknowledgement = ack-nhfb,
articleno = "61",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2023:PRF,
author = "Hang Li and Ahmed Mourad and Shengyao Zhuang and Bevan
Koopman and Guido Zuccon",
title = "Pseudo Relevance Feedback with Deep Language Models
and Dense Retrievers: Successes and Pitfalls",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "62:1--62:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3570724",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3570724",
abstract = "Pseudo Relevance Feedback (PRF) is known to improve
the effectiveness of bag-of-words retrievers. At the
same time, deep language models have been shown
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "62",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Guo:2023:PHG,
author = "Naicheng Guo and Xiaolei Liu and Shaoshuai Li and
Qiongxu Ma and Kaixin Gao and Bing Han and Lin Zheng
and Sheng Guo and Xiaobo Guo",
title = "{Poincar{\'e}} Heterogeneous Graph Neural Networks for
Sequential Recommendation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "63:1--63:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3568395",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3568395",
abstract = "Sequential recommendation (SR) learns users'
preferences by capturing the sequential patterns from
users' behaviors evolution. As discussed in many
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "63",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Cai:2023:UCS,
author = "Desheng Cai and Shengsheng Qian and Quan Fang and Jun
Hu and Changsheng Xu",
title = "User Cold-Start Recommendation via Inductive
Heterogeneous Graph Neural Network",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "64:1--64:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3560487",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3560487",
abstract = "Recently, user cold-start recommendations have
attracted a lot of attention from industry and
academia. In user cold-start recommendation systems,
the user \ldots{}",
acknowledgement = ack-nhfb,
articleno = "64",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Imran:2023:RRE,
author = "Mubashir Imran and Hongzhi Yin and Tong Chen and Quoc
Viet Hung Nguyen and Alexander Zhou and Kai Zheng",
title = "{ReFRS}: Resource-efficient Federated Recommender
System for Dynamic and Diversified User Preferences",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "65:1--65:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3560486",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3560486",
abstract = "Owing to its nature of scalability and privacy by
design, federated learning (FL) has received increasing
interest in decentralized deep learning. FL has also
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "65",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Long:2023:DCL,
author = "Jing Long and Tong Chen and Quoc Viet Hung Nguyen and
Hongzhi Yin",
title = "Decentralized Collaborative Learning Framework for
Next {POI} Recommendation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "66:1--66:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3555374",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3555374",
abstract = "Next Point-of-Interest (POI) recommendation has become
an indispensable functionality in Location-based Social
Networks (LBSNs) due \ldots{}",
acknowledgement = ack-nhfb,
articleno = "66",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2023:BDR,
author = "Jiawei Chen and Hande Dong and Xiang Wang and Fuli
Feng and Meng Wang and Xiangnan He",
title = "Bias and Debias in Recommender System: a Survey and
Future Directions",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "67:1--67:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3564284",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3564284",
abstract = "While recent years have witnessed a rapid growth of
research papers on recommender system (RS), most of the
papers focus on inventing machine learning \ldots{}",
acknowledgement = ack-nhfb,
articleno = "67",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Song:2023:SPF,
author = "Haoyu Song and Wei-Nan Zhang and Kaiyan Zhang and Ting
Liu",
title = "A Stack-Propagation Framework for Low-Resource
Personalized Dialogue Generation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "68:1--68:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3563389",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3563389",
abstract = "With the resurgent interest in building open-domain
dialogue systems, the dialogue generation task has
attracted increasing attention over the past few years.
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "68",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Shen:2023:RWC,
author = "Yanyan Shen and Lifan Zhao and Weiyu Cheng and Zibin
Zhang and Wenwen Zhou and Lin Kangyi",
title = "{RESUS}: Warm-up Cold Users via Meta-learning Residual
User Preferences in {CTR} Prediction",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "69:1--69:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3564283",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3564283",
abstract = "Click-through Rate (CTR) prediction on cold users is a
challenging task in recommender systems. Recent
researches have resorted to meta-learning to tackle the
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "69",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liang:2023:ETA,
author = "Bi Liang and Xiangwu Meng and Yujie Zhang",
title = "Exploring Time-aware Multi-pattern Group Venue
Recommendation in {LBSNs}",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "70:1--70:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3564280",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3564280",
abstract = "Location-based social networks (LBSNs) have become a
popular platform for users to share their activities
with friends and families, which provide abundant
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "70",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ma:2023:ITB,
author = "Muyang Ma and Pengjie Ren and Zhumin Chen and Zhaochun
Ren and Huasheng Liang and Jun Ma and Maarten {De
Rijke}",
title = "Improving Transformer-based Sequential Recommenders
through Preference Editing",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "71:1--71:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3564282",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3564282",
abstract = "One of the key challenges in sequential recommendation
is how to extract and represent user preferences.
Traditional methods rely solely on predicting
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "71",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Han:2023:DDA,
author = "Lei Han and Tianwa Chen and Gianluca Demartini and
Marta Indulska and Shazia Sadiq",
title = "A Data-Driven Analysis of Behaviors in Data Curation
Processes",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "72:1--72:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3567419",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3567419",
abstract = "Understanding how data workers interact with data, and
various pieces of information related to data
preparation, is key to designing systems that can
better \ldots{}",
acknowledgement = ack-nhfb,
articleno = "72",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2023:PSK,
author = "Minghan Li and Diana Nicoleta Popa and Johan Chagnon
and Yagmur Gizem Cinar and Eric Gaussier",
title = "The Power of Selecting Key Blocks with Local
Pre-ranking for Long Document Information Retrieval",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "73:1--73:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3568394",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3568394",
abstract = "On a wide range of natural language processing and
information retrieval tasks, transformer-based models,
particularly pre-trained language models like
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "73",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2023:GNP,
author = "Siwei Liu and Zaiqiao Meng and Craig Macdonald and
Iadh Ounis",
title = "Graph Neural Pre-training for Recommendation with Side
Information",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "74:1--74:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3568953",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3568953",
abstract = "Leveraging the side information associated with
entities (i.e., users and items) to enhance
recommendation systems has been widely recognized as an
essential \ldots{}",
acknowledgement = ack-nhfb,
articleno = "74",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ji:2023:CSD,
author = "Yitong Ji and Aixin Sun and Jie Zhang and Chenliang
Li",
title = "A Critical Study on Data Leakage in Recommender System
Offline Evaluation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "75:1--75:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3569930",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3569930",
abstract = "Recommender models are hard to evaluate, particularly
under offline setting. In this article, we provide a
comprehensive and critical analysis of the data leakage
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "75",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Shao:2023:URJ,
author = "Yunqiu Shao and Yueyue Wu and Yiqun Liu and Jiaxin Mao
and Shaoping Ma",
title = "Understanding Relevance Judgments in Legal Case
Retrieval",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "76:1--76:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3569929",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3569929",
abstract = "Legal case retrieval, which aims to retrieve relevant
cases given a query case, has drawn increasing research
attention in recent years. While much research has
worked \ldots{}",
acknowledgement = ack-nhfb,
articleno = "76",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Deng:2023:UMT,
author = "Yang Deng and Wenxuan Zhang and Weiwen Xu and Wenqiang
Lei and Tat-Seng Chua and Wai Lam",
title = "A Unified Multi-task Learning Framework for Multi-goal
Conversational Recommender Systems",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "77:1--77:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3570640",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3570640",
abstract = "Recent years witnessed several advances in developing
multi-goal conversational recommender systems (MG-CRS)
that can proactively attract users' interests
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "77",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2023:MUR,
author = "Yu Zhao and Qiang Xu and Ying Zou and Wei Li",
title = "Modeling User Reviews through {Bayesian} Graph
Attention Networks for Recommendation",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "78:1--78:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3570500",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3570500",
abstract = "Recommender systems relieve users from cognitive
overloading by predicting preferred items for users.
Due to the complexity of interactions between users and
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "78",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yan:2023:AHP,
author = "Ming Yan and Haiyang Xu and Chenliang Li and Junfeng
Tian and Bin Bi and Wei Wang and Xianzhe Xu and Ji
Zhang and Songfang Huang and Fei Huang and Luo Si and
Rong Jin",
title = "Achieving Human Parity on Visual Question Answering",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "79:1--79:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3572833",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3572833",
abstract = "The Visual Question Answering (VQA) task utilizes both
visual image and language analysis to answer a textual
question with respect to an image. It has been a
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "79",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2023:PAG,
author = "Yakun Li and Lei Hou and Juanzi Li",
title = "Preference-aware Graph Attention Networks for
Cross-Domain Recommendations with Collaborative
Knowledge Graph",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "80:1--80:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3576921",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3576921",
abstract = "Knowledge graphs (KGs) can provide users with semantic
information and relations among numerous entities and
nodes, which can greatly facilitate the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "80",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:RGB,
author = "Yi Zhang and Yiwen Zhang and Dengcheng Yan and
Shuiguang Deng and Yun Yang",
title = "Revisiting Graph-based Recommender Systems from the
Perspective of Variational Auto-Encoder",
journal = j-TOIS,
volume = "41",
number = "3",
pages = "81:1--81:??",
month = jul,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3573385",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Tue May 9 08:43:56 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3573385",
abstract = "Graph-based recommender system has attracted
widespread attention and produced a series of research
results. Because of the powerful high-order connection
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "81",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yin:2023:TRSb,
author = "Hongzhi Yin and Yizhou Sun and Guandong Xu and
Evangelos Kanoulas",
title = "Trustworthy Recommendation and Search: Introduction to
the Special Section --- {Part 2}",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "82:1--82:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3604776",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3604776",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "82",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhou:2023:EHT,
author = "Yuchen Zhou and Yanan Cao and Yanmin Shang and Chuan
Zhou and Shirui Pan and Zheng Lin and Qian Li",
title = "Explainable Hyperbolic Temporal Point Process for
User-Item Interaction Sequence Generation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "83:1--83:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3570501",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3570501",
abstract = "Recommender systems which captures dynamic user
interest based on time-ordered user-item interactions
plays a critical role in the real-world. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "83",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Deffayet:2023:ERC,
author = "Romain Deffayet and Jean-Michel Renders and Maarten de
Rijke",
title = "Evaluating the Robustness of Click Models to Policy
Distributional Shift",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "84:1--84:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3569086",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3569086",
abstract = "Many click models have been proposed to interpret logs
of natural interactions with search engines and extract
unbiased information for evaluation or \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "84",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Guo:2023:DRL,
author = "Xiaobo Guo and Shaoshuai Li and Naicheng Guo and
Jiangxia Cao and Xiaolei Liu and Qiongxu Ma and
Runsheng Gan and Yunan Zhao",
title = "Disentangled Representations Learning for Multi-target
Cross-domain Recommendation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "85:1--85:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3572835",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3572835",
abstract = "Data sparsity has been a long-standing issue for
accurate and trustworthy recommendation systems (RS).
To alleviate the problem, many researchers pay
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "85",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xue:2023:LDV,
author = "Lyuxin Xue and Deqing Yang and Shuoyao Zhai and Yuxin
Li and Yanghua Xiao",
title = "Learning Dual-view User Representations for Enhanced
Sequential Recommendation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "86:1--86:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3572028",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3572028",
abstract = "Sequential recommendation (SR) aims to predict a
user's next interacted item given his/her historical
interactions. Most existing sequential recommendation
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "86",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2023:VGL,
author = "Senrong Xu and Liangyue Li and Zenan Li and Yuan Yao
and Feng Xu and Zulong Chen and Quan Lu and Hanghang
Tong",
title = "On the Vulnerability of Graph Learning-based
Collaborative Filtering",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "87:1--87:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3572834",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3572834",
abstract = "Graph learning-based collaborative filtering (GLCF),
which is built upon the message-passing mechanism of
graph neural networks (GNNs), has received great recent
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "87",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Leonhardt:2023:EEI,
author = "Jurek Leonhardt and Koustav Rudra and Avishek Anand",
title = "Extractive Explanations for Interpretable Text
Ranking",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "88:1--88:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3576924",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3576924",
abstract = "Neural document ranking models perform impressively
well due to superior language understanding gained from
pre-training tasks. However, due to their \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "88",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wu:2023:PPB,
author = "Chen Wu and Ruqing Zhang and Jiafeng Guo and Maarten
{De Rijke} and Yixing Fan and Xueqi Cheng",
title = "{PRADA}: Practical Black-box Adversarial Attacks
against Neural Ranking Models",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "89:1--89:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3576923",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3576923",
abstract = "Neural ranking models (NRMs) have shown remarkable
success in recent years, especially with pre-trained
language models. However, deep neural models are
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "89",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:LLF,
author = "Honglei Zhang and Fangyuan Luo and Jun Wu and Xiangnan
He and Yidong Li",
title = "{LightFR}: Lightweight Federated Recommendation with
Privacy-preserving Matrix Factorization",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "90:1--90:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3578361",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3578361",
abstract = "Federated recommender system (FRS), which enables many
local devices to train a shared model jointly without
transmitting local raw data, has become a prevalent
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "90",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{He:2023:ERS,
author = "Liyang He and Zhenya Huang and Enhong Chen and Qi Liu
and Shiwei Tong and Hao Wang and Defu Lian and Shijin
Wang",
title = "An Efficient and Robust Semantic Hashing Framework for
Similar Text Search",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "91:1--91:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3570725",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3570725",
abstract = "Similar text search aims to find texts relevant to a
given query from a database, which is fundamental in
many information retrieval applications, such as
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "91",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2023:TAI,
author = "Qiming Li and Zhao Zhang and Fuzhen Zhuang and Yongjun
Xu and Chao Li",
title = "Topic-aware Intention Network for Explainable
Recommendation with Knowledge Enhancement",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "92:1--92:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3579993",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3579993",
abstract = "Recently, recommender systems based on knowledge
graphs (KGs) have become a popular research direction.
Graph neural network (GNN) is the key \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "92",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Meng:2023:RNT,
author = "Qing Meng and Hui Yan and Bo Liu and Xiangguo Sun and
Mingrui Hu and Jiuxin Cao",
title = "Recognize News Transition from Collective Behavior for
News Recommendation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "93:1--93:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3578362",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3578362",
abstract = "In the news recommendation, users are overwhelmed by
thousands of news daily, which makes the users'
behavior data have high sparsity. Therefore, only
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "93",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2023:QRM,
author = "Lingzhi Wang and Xingshan Zeng and Kam-Fai Wong",
title = "Quotation Recommendation for Multi-party Online
Conversations Based on Semantic and Topic Fusion",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "94:1--94:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3594633",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3594633",
abstract = "Quotations are crucial for successful explanations and
persuasions in interpersonal communications. However,
finding what to quote in a \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "94",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhao:2023:AAT,
author = "Yan Zhao and Liwei Deng and Kai Zheng",
title = "{AdaTaskRec}: an Adaptive Task Recommendation
Framework in Spatial Crowdsourcing",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "95:1--95:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3593582",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3593582",
abstract = "Spatial crowdsourcing is one of the prime movers for
the orchestration of location-based tasks, and task
recommendation is a crucial means to help workers
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "95",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Mackenzie:2023:EDT,
author = "Joel Mackenzie and Andrew Trotman and Jimmy Lin",
title = "Efficient Document-at-a-time and Score-at-a-time Query
Evaluation for Learned Sparse Representations",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "96:1--96:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3576922",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3576922",
abstract = "Researchers have had much recent success with ranking
models based on so-called learned sparse
representations generated by transformers. One crucial
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "96",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:MLA,
author = "Xinyue Zhang and Jingjing Li and Hongzu Su and Lei Zhu
and Heng Tao Shen",
title = "Multi-level Attention-based Domain Disentanglement for
{BCDR}",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "97:1--97:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3576925",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3576925",
abstract = "Cross-domain recommendation aims to exploit
heterogeneous information from a data-sufficient domain
(source domain) to transfer knowledge to a \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "97",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qin:2023:LRU,
author = "Jiarui Qin and Weinan Zhang and Rong Su and Zhirong
Liu and Weiwen Liu and Guangpeng Zhao and Hao Li and
Ruiming Tang and Xiuqiang He and Yong Yu",
title = "Learning to Retrieve User Behaviors for Click-through
Rate Estimation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "98:1--98:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3579354",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3579354",
abstract = "Click-through rate (CTR) estimation plays a crucial
role in modern online personalization services. It is
essential to capture users' drifting interests by
modeling \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "98",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yao:2023:OAP,
author = "Zijun Yao and Bin Liu and Fei Wang and Daby Sow and
Ying Li",
title = "Ontology-aware Prescription Recommendation in
Treatment Pathways Using Multi-evidence Healthcare
Data",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "99:1--99:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3579994",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3579994",
abstract = "For care of chronic diseases (e.g., depression,
diabetes, hypertension), it is critical to identify
effective treatment pathways that aim to promptly
update the \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "99",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Somanchi:2023:EUH,
author = "Sriram Somanchi and Ahmed Abbasi and Ken Kelley and
David Dobolyi and Ted Tao Yuan",
title = "Examining User Heterogeneity in Digital Experiments",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "100:1--100:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3578931",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3578931",
abstract = "Digital experiments are routinely used to test the
value of a treatment relative to a status-quo control
setting-for instance, a new search relevance algorithm
for \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "100",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zheng:2023:ADR,
author = "Ruiqi Zheng and Liang Qu and Bin Cui and Yuhui Shi and
Hongzhi Yin",
title = "{AutoML} for Deep Recommender Systems: a Survey",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "101:1--101:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3579355",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3579355",
abstract = "Recommender systems play a significant role in
information filtering and have been utilized in
different scenarios, such as e-commerce and social
media. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "101",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xia:2023:EDS,
author = "Xin Xia and Junliang Yu and Qinyong Wang and Chaoqun
Yang and Nguyen Quoc Viet Hung and Hongzhi Yin",
title = "Efficient On-Device Session-Based Recommendation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "102:1--102:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3580364",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3580364",
abstract = "On-device session-based recommendation systems have
been achieving increasing attention on account of the
low energy/resource consumption and \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "102",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2023:PPL,
author = "Lei Li and Yongfeng Zhang and Li Chen",
title = "Personalized Prompt Learning for Explainable
Recommendation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "103:1--103:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3580488",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3580488",
abstract = "Providing user-understandable explanations to justify
recommendations could help users better understand the
recommended items, increase the system's ease of use,
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "103",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Cui:2023:FGI,
author = "Jiajun Cui and Zeyuan Chen and Aimin Zhou and Jianyong
Wang and Wei Zhang",
title = "Fine-Grained Interaction Modeling with
Multi-Relational Transformer for Knowledge Tracing",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "104:1--104:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3580595",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3580595",
abstract = "Knowledge tracing, the goal of which is predicting
students' future performance given their past question
response sequences to trace their knowledge states, is
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "104",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Cheng:2023:CDM,
author = "Zifeng Cheng and Zhiwei Jiang and Yafeng Yin and Cong
Wang and Shiping Ge and Qing Gu",
title = "A Consistent Dual-{MRC} Framework for Emotion-cause
Pair Extraction",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "105:1--105:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3558548",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3558548",
abstract = "Emotion-cause pair extraction (ECPE) is a recently
proposed task that aims to extract the potential clause
pairs of emotions and its corresponding causes in a
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "105",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yi:2023:MAA,
author = "Jing Yi and Xubin Ren and Zhenzhong Chen",
title = "Multi-auxiliary Augmented Collaborative Variational
Auto-encoder for Tag Recommendation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "106:1--106:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3578932",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3578932",
abstract = "Recommending appropriate tags to items can facilitate
content organization, retrieval, consumption, and other
applications, where hybrid tag recommender systems
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "106",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhou:2023:EMV,
author = "Kun Zhou and Hui Wang and Ji-rong Wen and Wayne Xin
Zhao",
title = "Enhancing Multi-View Smoothness for Sequential
Recommendation Models",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "107:1--107:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3582495",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3582495",
abstract = "Sequential recommendation models aim to predict the
interested items to a user based on his historical
behaviors. To train sequential recommenders, implicit
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "107",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2023:BSI,
author = "Dugang Liu and Pengxiang Cheng and Zinan Lin and
Xiaolian Zhang and Zhenhua Dong and Rui Zhang and
Xiuqiang He and Weike Pan and Zhong Ming",
title = "Bounding System-Induced Biases in Recommender Systems
with a Randomized Dataset",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "108:1--108:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3582002",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3582002",
abstract = "Debiased recommendation with a randomized dataset has
shown very promising results in mitigating
system-induced biases. However, it still \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "108",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Dusart:2023:THS,
author = "Alexis Dusart and Karen Pinel-Sauvagnat and Gilles
Hubert",
title = "{TSSuBERT}: How to Sum Up Multiple Years of Reading in
a Few Tweets",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "109:1--109:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3581786",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3581786",
abstract = "The development of deep neural networks and the
emergence of pre-trained language models such as BERT
allow to increase performance on many NLP tasks.
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "109",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lin:2023:DRF,
author = "Sheng-Chieh Lin and Jimmy Lin",
title = "A Dense Representation Framework for Lexical and
Semantic Matching",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "110:1--110:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3582426",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3582426",
abstract = "Lexical and semantic matching capture different
successful approaches to text retrieval and the fusion
of their results has proven to be more effective and
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "110",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Si:2023:ERS,
author = "Zihua Si and Zhongxiang Sun and Xiao Zhang and Jun Xu
and Yang Song and Xiaoxue Zang and Ji-Rong Wen",
title = "Enhancing Recommendation with Search Data in a Causal
Learning Manner",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "111:1--111:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3582425",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3582425",
abstract = "Recommender systems are currently widely used in
various applications helping people filter information.
Existing models always embed the rich information for
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "111",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2023:TTG,
author = "Ronghui Xu and Meng Chen and Yongshun Gong and Yang
Liu and Xiaohui Yu and Liqiang Nie",
title = "{TME}: Tree-guided Multi-task Embedding Learning
towards Semantic Venue Annotation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "112:1--112:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3582553",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3582553",
abstract = "The prevalence of location-based services has
generated a deluge of check-ins, enabling the task of
human mobility understanding. Among the various
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "112",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2023:CLL,
author = "Han Zhang and Zhicheng Dou and Yutao Zhu and Ji-Rong
Wen",
title = "Contrastive Learning for Legal Judgment Prediction",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "113:1--113:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3580489",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3580489",
abstract = "Legal judgment prediction (LJP) is a fundamental task
of legal artificial intelligence. It aims to
automatically predict the judgment results of legal
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "113",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yang:2023:DRU,
author = "Mengyue Yang and Guohao Cai and Furui Liu and Jiarui
Jin and Zhenhua Dong and Xiuqiang He and Jianye Hao and
Weiqi Shao and Jun Wang and Xu Chen",
title = "Debiased Recommendation with User Feature Balancing",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "114:1--114:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3580594",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3580594",
abstract = "Debiased recommendation has recently attracted
increasing attention from both industry and academic
communities. Traditional models mostly rely on
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "114",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Feng:2023:LMT,
author = "Jiazhan Feng and Chongyang Tao and Xueliang Zhao and
Dongyan Zhao",
title = "Learning Multi-turn Response Selection in Grounded
Dialogues with Reinforced Knowledge and Context
Distillation",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "115:1--115:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3584701",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3584701",
abstract = "Recently, knowledge-grounded dialogue systems have
gained increasing attention. Great efforts have been
made to build response matching models where \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "115",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2023:NBR,
author = "Ming Li and Sami Jullien and Mozhdeh Ariannezhad and
Maarten de Rijke",
title = "A Next Basket Recommendation Reality Check",
journal = j-TOIS,
volume = "41",
number = "4",
pages = "116:1--116:??",
month = oct,
year = "2023",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3587153",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Wed Sep 20 08:21:57 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3587153",
abstract = "The goal of a next basket recommendation (NBR) system
is to recommend items for the next basket for a user,
based on the sequence of their prior baskets. We
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "116",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wei:2024:NAS,
author = "Lanning Wei and Huan Zhao and Zhiqiang He and Quanming
Yao",
title = "Neural Architecture Search for {GNN}-Based Graph
Classification",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3584945",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3584945",
abstract = "Graph classification is an important problem with
applications across many domains, for which graph
neural networks (GNNs) have been state-of-the-art
(SOTA) methods. In the literature, to adopt GNNs for
the graph classification task, there are two groups
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "1",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{McGregor:2024:SRC,
author = "Molly McGregor and Leif Azzopardi and Martin Halvey",
title = "A Systematic Review of Cost, Effort, and Load Research
in Information Search and Retrieval, 1972--2020",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3583069",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3583069",
abstract = "During the information search and retrieval (ISR)
process, user-system interactions such as submitting
queries, examining results, and engaging with
information impose some degree of demand on the user's
resources. Within ISR, these demands are well
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "2",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2024:GBP,
author = "Hongyan Xu and Qiyao Peng and Hongtao Liu and Yueheng
Sun and Wenjun Wang",
title = "Group-Based Personalized News Recommendation with
Long- and Short-Term Fine-Grained Matching",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3584946",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3584946",
abstract = "Personalized news recommendation aims to help users
find news content they prefer, which has attracted
increasing attention recently. There are two core
issues in news recommendation: learning news
representation and matching candidate news with user
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "3",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2024:RSM,
author = "Jin Zhang and Xinrui Li and Liye Wang",
title = "A Review Selection Method Based on Consumer Decision
Phases in E-commerce",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3587265",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3587265",
abstract = "A valuable small subset strategically selected from
massive online reviews is beneficial to improve
consumers' decision-making efficiency in e-commerce.
Existing review selection methods primarily concentrate
on the informativeness of reviews and aim to \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "4",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wu:2024:FDF,
author = "Yao Wu and Jian Cao and Guandong Xu",
title = "{FASTER}: a Dynamic Fairness-assurance Strategy for
Session-based Recommender Systems",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "5:1--5:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3586993",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3586993",
abstract = "When only users' preferences and interests are
considered by a recommendation algorithm, it will lead
to the severe long-tail problem over items. Therefore,
the unfair exposure phenomenon of recommended items
caused by this problem has attracted \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "5",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2024:CCP,
author = "Xinhang Li and Zhaopeng Qiu and Jiacheng Jiang and
Yong Zhang and Chunxiao Xing and Xian Wu",
title = "Conditional Cross-Platform User Engagement
Prediction",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "6:1--6:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3589226",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3589226",
abstract = "The bursting of media sharing platforms like TikTok,
YouTube, and Kwai enables normal users to create and
share content with worldwide audiences. The most
popular YouTuber can attract up to 100 million
followers. Since there are multiple popular platforms,.
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "6",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Rad:2024:VNA,
author = "Radin Hamidi Rad and Hossein Fani and Ebrahim Bagheri
and Mehdi Kargar and Divesh Srivastava and Jaroslaw
Szlichta",
title = "A Variational Neural Architecture for Skill-based Team
Formation",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "7:1--7:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3589762",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3589762",
abstract = "Team formation is concerned with the identification of
a group of experts who have a high likelihood of
effectively collaborating with each other to satisfy a
collection of input skills. Solutions to this task have
mainly adopted graph operations and at \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "7",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{He:2024:MMA,
author = "Liangliang He and Xiao Li and Pancheng Wang and Jintao
Tang and Ting Wang",
title = "{MAN}: Memory-augmented Attentive Networks for Deep
Learning-based Knowledge Tracing",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "8:1--8:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3589340",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3589340",
abstract = "Knowledge Tracing (KT) is the task of modeling a
learner's knowledge state to predict future performance
in e-learning systems based on past performance. Deep
learning-based methods, such as recurrent neural
networks, memory-augmented neural networks, and
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "8",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2024:TRD,
author = "Hai Chen and Fulan Qian and Chang Liu and Yanping
Zhang and Hang Su and Shu Zhao",
title = "Training Robust Deep Collaborative Filtering Models
via Adversarial Noise Propagation",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "9:1--9:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3589000",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3589000",
abstract = "The recommendation performance of deep collaborative
filtering models drops sharply under imperceptible
adversarial perturbations. Some methods promote the
robustness of recommendation systems by adversarial
training. However, these methods only study \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "9",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yan:2024:CRG,
author = "Mingshi Yan and Zhiyong Cheng and Chen Gao and Jing
Sun and Fan Liu and Fuming Sun and Haojie Li",
title = "Cascading Residual Graph Convolutional Network for
Multi-Behavior Recommendation",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "10:1--10:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3587693",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3587693",
abstract = "Multi-behavior recommendation exploits multiple types
of user-item interactions, such as view and cart, to
learn user preferences and has demonstrated to be an
effective solution to alleviate the data sparsity
problem faced by the traditional models that \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "10",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sakai:2024:VFE,
author = "Tetsuya Sakai and Jin Young Kim and Inho Kang",
title = "A Versatile Framework for Evaluating Ranked Lists in
Terms of Group Fairness and Relevance",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "11:1--11:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3589763",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3589763",
abstract = "We present a simple and versatile framework for
evaluating ranked lists in terms of Group Fairness and
Relevance, in which the groups (i.e., possible
attribute values) can be either nominal or ordinal in
nature. First, we demonstrate that when our \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "11",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2024:CDR,
author = "Wenjie Wang and Xinyu Lin and Liuhui Wang and Fuli
Feng and Yunshan Ma and Tat-Seng Chua",
title = "Causal Disentangled Recommendation against User
Preference Shifts",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "12:1--12:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3593022",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3593022",
abstract = "Recommender systems easily face the issue of user
preference shifts. User representations will become
out-of-date and lead to inappropriate recommendations
if user preference has shifted over time. To solve the
issue, existing work focuses on learning \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "12",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2024:MMM,
author = "Yazhou Zhang and Ao Jia and Bo Wang and Peng Zhang and
Dongming Zhao and Pu Li and Yuexian Hou and Xiaojia Jin
and Dawei Song and Jing Qin",
title = "{M3GAT}: a Multi-modal, Multi-task Interactive Graph
Attention Network for Conversational Sentiment Analysis
and Emotion Recognition",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "13:1--13:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3593583",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3593583",
abstract = "Sentiment and emotion, which correspond to long-term
and short-lived human feelings, are closely linked to
each other, leading to the fact that sentiment analysis
and emotion recognition are also two interdependent
tasks in natural language processing \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "13",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Gao:2024:CBF,
author = "Chongming Gao and Shiqi Wang and Shijun Li and Jiawei
Chen and Xiangnan He and Wenqiang Lei and Biao Li and
Yuan Zhang and Peng Jiang",
title = "{CIRS}: Bursting Filter Bubbles by Counterfactual
Interactive Recommender System",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "14:1--14:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3594871",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3594871",
abstract = "While personalization increases the utility of
recommender systems, it also brings the issue of filter
bubbles. e.g., if the system keeps exposing and
recommending the items that the user is interested in,
it may also make the user feel bored and less
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "14",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sun:2024:MCN,
author = "Zhu Sun and Yu Lei and Lu Zhang and Chen Li and
Yew-Soon Ong and Jie Zhang",
title = "A Multi-channel Next {POI} Recommendation Framework
with Multi-granularity Check-in Signals",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "15:1--15:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3592789",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3592789",
abstract = "Current study on next point-of-interest (POI)
recommendation mainly explores user sequential
transitions with the fine-grained individual-user POI
check-in trajectories only, which suffers from the
severe check-in data sparsity issue. In fact, coarse-.
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "15",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2024:MVE,
author = "Dongjing Wang and Xin Zhang and Yuyu Yin and Dongjin
Yu and Guandong Xu and Shuiguang Deng",
title = "Multi-View Enhanced Graph Attention Network for
Session-Based Music Recommendation",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "16:1--16:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3592853",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3592853",
abstract = "Traditional music recommender systems are mainly based
on users' interactions, which limit their performance.
Particularly, various kinds of content information,
such as metadata and description can be used to improve
music recommendation. However, it \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "16",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sun:2024:MUS,
author = "Weiwei Sun and Shuyu Guo and Shuo Zhang and Pengjie
Ren and Zhumin Chen and Maarten de Rijke and Zhaochun
Ren",
title = "Metaphorical User Simulators for Evaluating
Task-oriented Dialogue Systems",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "17:1--17:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3596510",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3596510",
abstract = "Task-oriented dialogue systems (TDSs) are assessed
mainly in an offline setting or through human
evaluation. The evaluation is often limited to
single-turn or is very time-intensive. As an
alternative, user simulators that mimic user behavior
allow us to \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "17",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qin:2024:LHS,
author = "Yingrong Qin and Chen Gao and Shuangqing Wei and Yue
Wang and Depeng Jin and Jian Yuan and Lin Zhang and
Dong Li and Jianye Hao and Yong Li",
title = "Learning from Hierarchical Structure of Knowledge
Graph for Recommendation",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "18:1--18:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3595632",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3595632",
abstract = "Knowledge graphs (KGs) can help enhance
recommendations, especially for the data-sparsity
scenarios with limited user-item interaction data. Due
to the strong power of representation learning of graph
neural networks (GNNs), recent works of KG-based
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "18",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Rashidi:2024:IJV,
author = "Lida Rashidi and Justin Zobel and Alistair Moffat",
title = "The Impact of Judgment Variability on the Consistency
of Offline Effectiveness Measures",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "19:1--19:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3596511",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3596511",
abstract = "Measurement of the effectiveness of search engines is
often based on use of relevance judgments. It is well
known that judgments can be inconsistent between
judges, leading to discrepancies that potentially
affect not only scores but also system \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "19",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Bruch:2024:AFF,
author = "Sebastian Bruch and Siyu Gai and Amir Ingber",
title = "An Analysis of Fusion Functions for Hybrid Retrieval",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "20:1--20:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3596512",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3596512",
abstract = "We study hybrid search in text retrieval where lexical
and semantic search are fused together with the
intuition that the two are complementary in how they
model relevance. In particular, we examine fusion by a
convex combination of lexical and semantic \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "20",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Roitero:2024:HMC,
author = "Kevin Roitero and David {La Barbera} and Michael
Soprano and Gianluca Demartini and Stefano Mizzaro and
Tetsuya Sakai",
title = "How Many Crowd Workers Do {I} Need? {On} Statistical
Power when Crowdsourcing Relevance Judgments",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "21:1--21:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3597201",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3597201",
abstract = "To scale the size of Information Retrieval
collections, crowdsourcing has become a common way to
collect relevance judgments at scale. Crowdsourcing
experiments usually employ 100-10,000 workers, but such
a number is often decided in a heuristic way. The
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "21",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Huang:2024:DLR,
author = "Heyan Huang and Changsen Yuan and Qian Liu and Yixin
Cao",
title = "Document-level Relation Extraction via Separate
Relation Representation and Logical Reasoning",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "22:1--22:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3597610",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3597610",
abstract = "Document-level relation extraction (RE) extends the
identification of entity/mentions' relation from the
single sentence to the long document. It is more
realistic and poses new challenges to relation
representation and reasoning skills. In this article,
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "22",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sakai:2024:OPW,
author = "Tetsuya Sakai and Sijie Tao and Nuo Chen and Yujing Li
and Maria Maistro and Zhumin Chu and Nicola Ferro",
title = "On the Ordering of Pooled {Web} Pages, Gold
Assessments, and Bronze Assessments",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "23:1--23:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3600227",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3600227",
abstract = "The present study leverages a recent opportunity we
had to create a new English web search test collection
for the NTCIR-16 We Want Web (WWW-4) task, which
concluded in June 2022. More specifically, through the
test collection construction effort, we \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "23",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yin:2024:UDS,
author = "Qing Yin and Hui Fang and Zhu Sun and Yew-Soon Ong",
title = "Understanding Diversity in Session-based
Recommendation",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "24:1--24:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3600226",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3600226",
abstract = "Current session-based recommender systems (SBRSs)
mainly focus on maximizing recommendation accuracy,
while few studies have been devoted to improve
diversity beyond accuracy. Meanwhile, it is unclear how
the accuracy-oriented SBRSs perform in terms of
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "24",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Jing:2024:SDT,
author = "Liqiang Jing and Xuemeng Song and Xuming Lin and
Zhongzhou Zhao and Wei Zhou and Liqiang Nie",
title = "Stylized Data-to-text Generation: a Case Study in the
E-Commerce Domain",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "25:1--25:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3603374",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3603374",
abstract = "Existing data-to-text generation efforts mainly focus
on generating a coherent text from non-linguistic input
data, such as tables and attribute-value pairs, but
overlook that different application scenarios may
require texts of different styles. Inspired \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "25",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2024:INR,
author = "Haoyang Li and Ziwei Zhang and Xin Wang and Wenwu
Zhu",
title = "Invariant Node Representation Learning under
Distribution Shifts with Multiple Latent Environments",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "26:1--26:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3604427",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3604427",
abstract = "Node representation learning methods, such as graph
neural networks, show promising results when testing
and training graph data come from the same
distribution. However, the existing approaches fail to
generalize under distribution shifts when the nodes
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "26",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qin:2024:ASO,
author = "Chuan Qin and Hengshu Zhu and Dazhong Shen and Ying
Sun and Kaichun Yao and Peng Wang and Hui Xiong",
title = "Automatic Skill-Oriented Question Generation and
Recommendation for Intelligent Job Interviews",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "27:1--27:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3604552",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3604552",
abstract = "Job interviews are the most widely accepted method for
companies to select suitable candidates, and a critical
challenge is finding the right questions to ask job
candidates. Moreover, there is a lack of integrated
tools for automatically generating \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "27",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ni:2024:MCD,
author = "Yuxin Ni and Yunwen Xia and Hui Fang and Chong Long
and Xinyu Kong and Daqian Li and Dong Yang and Jie
Zhang",
title = "{Meta-CRS}: a Dynamic Meta-Learning Approach for
Effective Conversational Recommender System",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "28:1--28:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3604804",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3604804",
abstract = "Conversational recommender system (CRS) enhances the
recommender system by acquiring the latest user
preference through dialogues, where an agent needs to
decide ``whether to ask or recommend'', ``which
attributes to ask'', and ``which items to recommend''
in \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "28",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2024:RMA,
author = "Zhichao Xu and Hansi Zeng and Juntao Tan and Zuohui Fu
and Yongfeng Zhang and Qingyao Ai",
title = "A Reusable Model-agnostic Framework for Faithfully
Explainable Recommendation and System Scrutability",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "29:1--29:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3605357",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3605357",
abstract = "State-of-the-art industrial-level recommender system
applications mostly adopt complicated model structures
such as deep neural networks. While this helps with the
model performance, the lack of system explainability
caused by these nearly blackbox models \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "29",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Meng:2024:CFK,
author = "Chang Meng and Ziqi Zhao and Wei Guo and Yingxue Zhang
and Haolun Wu and Chen Gao and Dong Li and Xiu Li and
Ruiming Tang",
title = "Coarse-to-Fine Knowledge-Enhanced Multi-Interest
Learning Framework for Multi-Behavior Recommendation",
journal = j-TOIS,
volume = "42",
number = "1",
pages = "30:1--30:??",
month = jan,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3606369",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Fri Nov 3 14:26:23 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3606369",
abstract = "Multi-types of behaviors (e.g., clicking, carting,
purchasing, etc.) widely exist in most real-world
recommendation scenarios, which are beneficial to learn
users' multi-faceted preferences. As dependencies are
explicitly exhibited by the multiple types \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "30",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yang:2024:CKG,
author = "Yang Yang and Chubing Zhang and Xin Song and Zheng
Dong and Hengshu Zhu and Wenjie Li",
title = "Contextualized Knowledge Graph Embedding for
Explainable Talent Training Course Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "33:1--33:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3597022",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3597022",
abstract = "Learning and development, or L\&D, plays an important
role in talent management, which aims to improve the
knowledge and capabilities of employees through a
variety of performance-oriented training activities.
Recently, with the rapid development of \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "33",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yao:2024:DBL,
author = "Yitong Yao and Jing Zhang and Peng Zhang and Yueheng
Sun",
title = "A Dual-branch Learning Model with Gradient-balanced
Loss for Long-tailed Multi-label Text Classification",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "34:1--34:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3597416",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3597416",
abstract = "Multi-label text classification has a wide range of
applications in the real world. However, the data
distribution in the real world is often imbalanced,
which leads to serious long-tailed problems. For
multi-label classification, due to the vast scale of
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "34",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Lan:2024:TEC,
author = "Tian Lan and Xian-Ling Mao and Wei Wei and Xiaoyan Gao
and Heyan Huang",
title = "Towards Efficient Coarse-grained Dialogue Response
Selection",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "35:1--35:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3597609",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3597609",
abstract = "Coarse-grained response selection is a fundamental and
essential subsystem for the widely used retrieval-based
chatbots, aiming to recall a coarse-grained candidate
set from a large-scale dataset. The dense retrieval
technique has recently been proven \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "35",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Li:2024:PPR,
author = "Canjia Li and Andrew Yates and Sean MacAvaney and Ben
He and Yingfei Sun",
title = "{PARADE}: Passage Representation Aggregation for
Document Reranking",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "36:1--36:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3600088",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3600088",
abstract = "Pre-trained transformer models, such as BERT and T5,
have shown to be highly effective at ad hoc passage and
document ranking. Due to the inherent sequence length
limits of these models, they need to process document
passages one at a time rather than \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "36",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xie:2024:HTS,
author = "Jiayi Xie and Zhenzhong Chen",
title = "Hierarchical Transformer with Spatio-temporal Context
Aggregation for Next Point-of-interest Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "37:1--37:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3597930",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3597930",
abstract = "Next point-of-interest (POI) recommendation is a
critical task in location-based social networks, yet
remains challenging due to a high degree of variation
and personalization exhibited in user movements. In
this work, we explore the latent hierarchical
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "37",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2024:SIG,
author = "Chen Xu and Jun Xu and Zhenhua Dong and Ji-Rong Wen",
title = "Syntactic-Informed Graph Networks for Sentence
Matching",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "38:1--38:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3609795",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3609795",
abstract = "Matching two natural language sentences is a
fundamental problem in both natural language processing
and information retrieval. Preliminary studies have
shown that the syntactic structures help improve the
matching accuracy, and different syntactic \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "38",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2024:TBP,
author = "Xinyu Zhang and Kelechi Ogueji and Xueguang Ma and
Jimmy Lin",
title = "Toward Best Practices for Training Multilingual Dense
Retrieval Models",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "39:1--39:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3613447",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3613447",
abstract = "Dense retrieval models using a transformer-based
bi-encoder architecture have emerged as an active area
of research. In this article, we focus on the task of
monolingual retrieval in a variety of typologically
diverse languages using such an architecture.
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "39",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ma:2024:ISI,
author = "Yixiao Ma and Yueyue Wu and Qingyao Ai and Yiqun Liu
and Yunqiu Shao and Min Zhang and Shaoping Ma",
title = "Incorporating Structural Information into Legal Case
Retrieval",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "40:1--40:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3609796",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3609796",
abstract = "Legal case retrieval has received increasing attention
in recent years. However, compared to ad hoc retrieval
tasks, legal case retrieval has its unique challenges.
First, case documents are rather lengthy and contain
complex legal structures. Therefore, \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "40",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Sun:2024:BGS,
author = "Yatong Sun and Xiaochun Yang and Zhu Sun and Bin
Wang",
title = "{BERD+}: a Generic Sequential Recommendation Framework
by Eliminating Unreliable Data with Item- and
Attribute-level Signals",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "41:1--41:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3611008",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3611008",
abstract = "Most sequential recommendation systems (SRSs) predict
the next item as the target for users given its
preceding items as input, assuming the target is
definitely related to its input. However, users may
unintentionally click items that are inconsistent
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "41",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Bruch:2024:AAM,
author = "Sebastian Bruch and Franco Maria Nardini and Amir
Ingber and Edo Liberty",
title = "An Approximate Algorithm for Maximum Inner Product
Search over Streaming Sparse Vectors",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "42:1--42:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3609797",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3609797",
abstract = "Maximum Inner Product Search or top- k retrieval on
sparse vectors is well understood in information
retrieval, with a number of mature algorithms that
solve it exactly. However, all existing algorithms are
tailored to text and frequency-based similarity
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "42",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Zhang:2024:SSL,
author = "Shengyu Zhang and Tan Jiang and Kun Kuang and Fuli
Feng and Jin Yu and Jianxin Ma and Zhou Zhao and Jianke
Zhu and Hongxia Yang and Tat-Seng Chua and Fei Wu",
title = "{SLED}: Structure Learning based Denoising for
Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "43:1--43:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3611385",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3611385",
abstract = "In recommender systems, click behaviors play a
fundamental role in mining users' interests and
training models (clicked items as positive samples).
Such signals are implicit feedback and are arguably
less representative of users' inherent interests. Most
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "43",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Quan:2024:AVL,
author = "Yuhan Quan and Jingtao Ding and Chen Gao and Nian Li
and Lingling Yi and Depeng Jin and Yong Li",
title = "Alleviating Video-length Effect for Micro-video
Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "44:1--44:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3617826",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3617826",
abstract = "Micro-video platforms such as TikTok are extremely
popular nowadays. One important feature is that users
no longer select interested videos from a set; instead,
they either watch the recommended video or skip to the
next one. As a result, the time length \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "44",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2024:HEN,
author = "Sannyuya Liu and Shengyingjie Liu and Zongkai Yang and
Jianwen Sun and Xiaoxuan Shen and Qing Li and Rui Zou
and Shangheng Du",
title = "Heterogeneous Evolution Network Embedding with
Temporal Extension for Intelligent Tutoring Systems",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "45:1--45:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3617828",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3617828",
abstract = "Graph embedding (GE) aims to acquire low-dimensional
node representations while maintaining the graph's
structural and semantic attributes. Intelligent
tutoring systems (ITS) signify a noteworthy achievement
in the fusion of AI and education. Utilizing GE
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "45",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Niu:2024:PAI,
author = "Yanrui Niu and Chao Liang and Ankang Lu and Baojin
Huang and Zhongyuan Wang and Jiahao Guo",
title = "Person-action Instance Search in Story Videos: an
Experimental Study",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "46:1--46:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3617892",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3617892",
abstract = "Person-Action instance search (P-A INS) aims to
retrieve the instances of a specific person doing a
specific action, which appears in the 2019-2021 INS
tasks of the world-famous TREC Video Retrieval
Evaluation (TRECVID). Most of the top-ranking solutions
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "46",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Liu:2024:DMF,
author = "Han Liu and Yinwei Wei and Fan Liu and Wenjie Wang and
Liqiang Nie and Tat-Seng Chua",
title = "Dynamic Multimodal Fusion via Meta-Learning Towards
Micro-Video Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "47:1--47:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3617827",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3617827",
abstract = "Multimodal information (e.g., visual, acoustic, and
textual) has been widely used to enhance representation
learning for micro-video recommendation. For
integrating multimodal information into a joint
representation of micro-video, multimodal fusion plays
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "47",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Guo:2024:DDA,
author = "Lei Guo and Hao Liu and Lei Zhu and Weili Guan and
Zhiyong Cheng",
title = "{DA-DAN}: a Dual Adversarial Domain Adaption Network
for Unsupervised Non-overlapping Cross-domain
Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "48:1--48:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3617825",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3617825",
abstract = "Unsupervised Non-overlapping Cross-domain
Recommendation (UNCR) is the task that recommends
source domain items to the target domain users, which
is more challenging as the users are non-overlapped,
and its learning process is unsupervised. Unsupervised
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "48",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Ma:2024:PDK,
author = "Longxuan Ma and Jiapeng Li and Mingda Li and Wei-Nan
Zhang and Ting Liu",
title = "Policy-driven Knowledge Selection and Response
Generation for Document-grounded Dialogue",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "49:1--49:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3617829",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3617829",
abstract = "Document-grounded dialogue (DGD) uses documents as
external knowledge for dialogue generation. Correctly
understanding the dialogue context is crucial for
selecting knowledge from the document and generating
proper responses. In this article, we propose
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "49",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Hu:2024:SCL,
author = "Yupeng Hu and Kun Wang and Meng Liu and Haoyu Tang and
Liqiang Nie",
title = "Semantic Collaborative Learning for Cross-Modal Moment
Localization",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "50:1--50:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3620669",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3620669",
abstract = "Localizing a desired moment within an untrimmed video
via a given natural language query, i.e., cross-modal
moment localization, has attracted widespread research
attention recently. However, it is a challenging task
because it requires not only \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "50",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2024:MAG,
author = "Ke Wang and Yanmin Zhu and Tianzi Zang and Chunyang
Wang and Kuan Liu and Peibo Ma",
title = "Multi-aspect Graph Contrastive Learning for
Review-enhanced Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "51:1--51:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3618106",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3618106",
abstract = "Review-based recommender systems explore semantic
aspects of users' preferences by incorporating
user-generated reviews into rating-based models. Recent
works have demonstrated the potential of review
information to improve the recommendation capacity.
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "51",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Shi:2024:RPB,
author = "Xiaoyu Shi and Quanliang Liu and Hong Xie and Di Wu
and Bo Peng and MingSheng Shang and Defu Lian",
title = "Relieving Popularity Bias in Interactive
Recommendation: a Diversity-Novelty-Aware Reinforcement
Learning Approach",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "52:1--52:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3618107",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3618107",
abstract = "While personalization increases the utility of item
recommendation, it also suffers from the issue of
popularity bias. However, previous methods emphasize
adopting supervised learning models to relieve
popularity bias in the static recommendation,
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "52",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Chen:2024:MDS,
author = "Xiaolin Chen and Xuemeng Song and Liqiang Jing and
Shuo Li and Linmei Hu and Liqiang Nie",
title = "Multimodal Dialog Systems with Dual Knowledge-enhanced
Generative Pretrained Language Model",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "53:1--53:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3606368",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3606368",
abstract = "Text response generation for multimodal task-oriented
dialog systems, which aims to generate the proper text
response given the multimodal context, is an essential
yet challenging task. Although existing efforts have
achieved compelling success, they \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "53",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Qin:2024:DMP,
author = "Yifang Qin and Hongjun Wu and Wei Ju and Xiao Luo and
Ming Zhang",
title = "A Diffusion Model for {POI} Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "54:1--54:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3624475",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3624475",
abstract = "Next Point-of-Interest (POI) recommendation is a
critical task in location-based services that aim to
provide personalized suggestions for the user's next
destination. Previous works on POI recommendation have
laid focus on modeling the user's spatial \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "54",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Siro:2024:UPU,
author = "Clemencia Siro and Mohammad Aliannejadi and Maarten
{De Rijke}",
title = "Understanding and Predicting User Satisfaction with
Conversational Recommender Systems",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "55:1--55:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3624989",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3624989",
abstract = "User satisfaction depicts the effectiveness of a
system from the user's perspective. Understanding and
predicting user satisfaction is vital for the design of
user-oriented evaluation methods for conversational
recommender systems (CRSs). Current \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "55",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wang:2024:SSB,
author = "Chao Wang and Hengshu Zhu and Chen Zhu and Chuan Qin
and Enhong Chen and Hui Xiong",
title = "{SetRank}: a Setwise {Bayesian} Approach for
Collaborative Ranking in Recommender System",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "56:1--56:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3626194",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3626194",
abstract = "The recent development of recommender systems has a
focus on collaborative ranking, which provides users
with a sorted list rather than rating prediction. The
sorted item lists can more directly reflect the
preferences for users and usually perform better
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "56",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Xu:2024:NPM,
author = "Shicheng Xu and Liang Pang and Huawei Shen and Xueqi
Cheng",
title = "{NIR-Prompt}: a Multi-task Generalized Neural
Information Retrieval Training Framework",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "57:1--57:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3626092",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3626092",
abstract = "Information retrieval aims to find information that
meets users' needs from the corpus. Different needs
correspond to different IR tasks such as document
retrieval, open-domain question answering,
retrieval-based dialogue, and so on, while they share
the \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "57",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Wan:2024:STC,
author = "Zhongwei Wan and Xin Liu and Benyou Wang and Jiezhong
Qiu and Boyu Li and Ting Guo and Guangyong Chen and
Yang Wang",
title = "Spatio-temporal Contrastive Learning-enhanced {GNNs}
for Session-based Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "58:1--58:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3626091",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3626091",
abstract = "Session-based recommendation (SBR) systems aim to
utilize the user's short-term behavior sequence to
predict the next item without the detailed user
profile. Most recent works try to model the user
preference by treating the sessions as between-item
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "58",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Jing:2024:CSS,
author = "Mengyuan Jing and Yanmin Zhu and Tianzi Zang and Ke
Wang",
title = "Contrastive Self-supervised Learning in Recommender
Systems: a Survey",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "59:1--59:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3627158",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3627158",
abstract = "Deep learning-based recommender systems have achieved
remarkable success in recent years. However, these
methods usually heavily rely on labeled data (i.e.,
user-item interactions), suffering from problems such
as data sparsity and cold-start. Self-. \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "59",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Yi:2024:CGP,
author = "Zixuan Yi and Iadh Ounis and Craig MacDonald",
title = "Contrastive Graph Prompt-tuning for Cross-domain
Recommendation",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "60:1--60:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3618298",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3618298",
abstract = "Recommender systems commonly suffer from the
long-standing data sparsity problem where insufficient
user-item interaction data limits the systems' ability
to make accurate recommendations. This problem can be
alleviated using cross-domain recommendation \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "60",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Bassani:2024:PQE,
author = "Elias Bassani and Nicola Tonellotto and Gabriella
Pasi",
title = "Personalized Query Expansion with Contextual Word
Embeddings",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "61:1--61:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3624988",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3624988",
abstract = "Personalized Query Expansion, the task of expanding
queries with additional terms extracted from the
user-related vocabulary, is a well-known solution to
improve the retrieval performance of a system w.r.t.
short queries. Recent approaches rely on word
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "61",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Article{Shao:2024:ITL,
author = "Yunqiu Shao and Haitao Li and Yueyue Wu and Yiqun Liu
and Qingyao Ai and Jiaxin Mao and Yixiao Ma and
Shaoping Ma",
title = "An Intent Taxonomy of Legal Case Retrieval",
journal = j-TOIS,
volume = "42",
number = "2",
pages = "62:1--62:??",
month = mar,
year = "2024",
CODEN = "ATISET",
DOI = "https://doi.org/10.1145/3626093",
ISSN = "1046-8188",
ISSN-L = "1046-8188",
bibdate = "Thu Dec 28 06:52:28 MST 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tois.bib",
URL = "https://dl.acm.org/doi/10.1145/3626093",
abstract = "Legal case retrieval is a special Information
Retrieval (IR) task focusing on legal case documents.
Depending on the downstream tasks of the retrieved case
documents, users' information needs in legal case
retrieval could be significantly different from
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Inf. Sys.",
articleno = "62",
fjournal = "ACM Transactions on Information Systems (TOIS)",
journal-URL = "https://dl.acm.org/loi/tois",
}
@Proceedings{Croft:1989:SCR,
editor = "W. Bruce Croft",
booktitle = "{SIGIR Conference on Research and Development in
Information Retrieval}",
title = "{SIGIR Conference on Research and Development in
Information Retrieval}",
volume = "7(3)",
publisher = pub-ACM,
address = pub-ACM:adr,
pages = "183--316",
month = jul,
year = "1989",
CODEN = "ATISET",
ISSN = "1046-8188",
bibdate = "Sat Jan 16 19:04:41 MST 1999",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tois.bib",
series = j-TOIS,
abstract = "The conference materials contain 6 papers. The areas
covered include formal models, search strategies,
hypermedia, storage structures, natural language
processing, and knowledge-based architectures, storage
on optical disks, hypertext, based help systems,
probabilistic retrieval model, information retrieval
from an artificial intelligence perspective, document
and query texts parsing are the main topics covered.
All papers are abstracted and indexed separately.",
acknowledgement = ack-nhfb,
classification = "723; 903; 922",
conference = "SIGIR Conference on Research and Development in
Information Retrieval",
conferenceyear = "1989",
editoraddress = "Amherst, MA, USA",
editoraffiliation = "Univ of Massachusetts",
journalabr = "ACM Trans Inf Syst",
keywords = "Artificial Intelligence; cd-rom Full Text Storage;
Computer Interfaces --- Human Factors; Data Storage;
Database Systems; Information Retrieval Systems;
Knowledge Based Search; Natural Language Processing;
Optical; Probabilistic Retrieval Model; Probability;
String Text Retrieval",
meetingaddress = "Cambridge, MA, USA",
meetingdate = "Jun 1989",
meetingdate2 = "06/89",
}
