@INPROCEEDINGS{Anh2004,
AUTHOR = {Vo Ngoc Anh and Alistair Moffat},
TITLE = {{M}elbourne {U}niversity 2004: {T}erabyte and {W}eb tracks},
BOOKTITLE = {Proceedings of the Thirteenths {T}ext {RE}trieval {C}onference ({TREC} 2004)},
YEAR = {2004},
CROSSREF = {TREC2004},
URL = {http://trec.nist.gov/pubs/trec13/papers/umelbourne.tera.web.pdf}
}
@INPROCEEDINGS{Craswell2004,
AUTHOR = {Nick Craswell and David Hawking},
TITLE = {Overview of the {TREC}-2004 {W}eb track},
BOOKTITLE = {Proceedings of the Thirteenths {T}ext {RE}trieval {C}onference ({TREC} 2004)},
YEAR = {2004},
CROSSREF = {TREC2004},
URL = {http://trec.nist.gov/pubs/trec13/papers/WEB.OVERVIEW.pdf}
}
@INCOLLECTION{Woods1975,
AUTHOR = {William A. Woods},
TITLE = {What's in a link: Foundations for Semantic Networks},
BOOKTITLE = {Representation and Understanding},
PUBLISHER = {Academic Press},
YEAR = {1975},
EDITOR = {Daniel G. Bobrow and Allan Collins},
CROSSREF = {Bobrow1975}
}
@INPROCEEDINGS{Zaragoza2004,
AUTHOR = {Hugo Zaragoza and Nick
Craswell and Michael Taylor and Suchi Saria and Stephen Robertson},
TITLE = {{M}icrosoft {C}ambridge and {TREC}-13: {Web} and {HARD} tracks},
BOOKTITLE = {Proceedings of the Thirteenths {T}ext {RE}trieval {C}onference ({TREC} 2004)},
YEAR = {2004},
CROSSREF = {TREC2004},
URL = {http://trec.nist.gov/pubs/trec13/papers/microsoft-cambridge.web.hard.pdf}
}
@ARTICLE{Adamic2005,
AUTHOR = {Lada A. Adamic and Eytan Adar},
TITLE = {How To Search a Social Network},
JOURNAL = {Social Networks},
YEAR = {2005},
VOLUME = {27},
PAGES = {187--203},
NUMBER = {3},
MONTH = JUL,
URL = {http://www.hpl.hp.com/research/idl/papers/socsearch/index.html}
}
@ARTICLE{Albert1999,
AUTHOR = {Albert, Reka and Jeong, Hawoong and Barabasi, Albert-Laszlo},
TITLE = {Internet: Diameter of the World-Wide Web},
JOURNAL = {Nature},
YEAR = {1999},
VOLUME = {401},
PAGES = {130--131},
NUMBER = {6749},
MONTH = SEP,
ISSN = {0028-0836},
URL = {http://dx.doi.org/10.1038/43601}
}
@BOOK{Anderson1983,
TITLE = {The Architecture of Cognition},
PUBLISHER = {Harvard University Press},
YEAR = {1983},
AUTHOR = {John R. Anderson},
SERIES = {Cognitive Science Series},
ISBN = {0-674-04425-8},
KEYWORDS = {spreading activation},
OWNER = {skirsch}
}
@BOOK{Baeza-Yates1999,
TITLE = {Modern Information Retrieval},
PUBLISHER = {Addison-Wesley},
YEAR = {1999},
AUTHOR = {Ricardo Baeza-Yates and Berthier Ribeiro-Neto},
KEYWORDS = {information retrieval},
OWNER = {skirsch}
}
@BOOK{Barabasi2003,
TITLE = {Linked},
PUBLISHER = {Plume Books},
YEAR = {2003},
AUTHOR = {Albert-L{\'a}szl{\'o} Barab{\'a}si}
}
@ARTICLE{Barabasi1999,
AUTHOR = {Albert-L{\'a}szl{\'o} Barab{\'a}si and R{\'e}ka Albert},
TITLE = {Emergence of Scaling in Random Networks},
JOURNAL = {Science},
YEAR = {1999},
VOLUME = {286},
PAGES = {509--512},
MONTH = OCT,
DOI = {http://dx.doi.org/10.1126/science.286.5439.509}
}
@INPROCEEDINGS{Beitzel2003,
AUTHOR = {Steven M. Beitzel and Ophir Frieder and Eric C.
Jensen and David Grossman and Abdur Chowdhury and Nazli Goharian},
TITLE = {Disproving the fusion hypothesis: an
analysis of data fusion via effective information retrieval strategies},
BOOKTITLE = {SAC '03: Proceedings of the 2003 ACM symposium on Applied computing},
YEAR = {2003},
PAGES = {823--827},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/952532.952695},
ISBN = {1-58113-624-2},
KEYWORDS = {data fusion},
LOCATION = {Melbourne, Florida}
}
@INPROCEEDINGS{Belew1989,
AUTHOR = {R. K. Belew},
TITLE = {Adaptive information retrieval: using a
connectionist representation to retrieve and learn about documents},
BOOKTITLE = {SIGIR '89: Proceedings of the 12th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1989},
PAGES = {11--20},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
ABSTRACT = {AIR represents a connectionist approach to the task
of information retrieval. The system uses relevance feedback from
its users to change its representation of authors, index terms and
documents so that, over time, AIR improves at its task. The result is a
representation of the consensual meaning of keywords and documents shared
by some group of users. The central focus goal of this paper is to
use our experience with AIR to highlight those characteristics of
connectionist representations that make them particularly appropriate
for IR applications. We argue that this associative representation
is a natural generalization of traditional IR techniques, and that
connectionist learning techniques are effective in this setting.},
DOI = {http://doi.acm.org/10.1145/75334.75337},
ISBN = {0-89791-321-3},
KEYWORDS = {spreading activation, information retrieval},
LOCATION = {Cambridge, Massachusetts, United States}
}
@INPROCEEDINGS{Belkin1993a,
AUTHOR = {N. J. Belkin and P. Kantor and C. Cool and R. Quatrain},
TITLE = {Combining Evidence for Information Retrieval},
BOOKTITLE = {Proceceedings of the Second {T}ext {RE}trieval {C}onference ({TREC}-2)},
YEAR = {1994},
EDITOR = {D. K. Harman},
NUMBER = {500-215},
SERIES = {{NIST} Special Publications},
PAGES = {35--44},
ORGANIZATION = {U.S. National Institute of Standards and Technology (NIST)},
KEYWORDS = {data fusion},
LOCATION = {Washington, D.C., United States},
URL = {http://trec.nist.gov/pubs/trec2/papers/txt/03.txt}
}
@ARTICLE{Belkin1995,
AUTHOR = {N. J. Belkin and P. Kantor and E. A. Fox and J. A. Shaw},
TITLE = {Combining the evidence of multiple query representations for information retrieval},
JOURNAL = {Information Processing and Management},
YEAR = {1995},
VOLUME = {31},
PAGES = {431--448},
NUMBER = {3},
NOTE = {Based on \cite{Belkin1993} and \cite{Fox1993}},
ADDRESS = {Tarrytown, NY, USA},
DOI = {http://dx.doi.org/10.1016/0306-4573(94)00057-A},
ISSN = {0306-4573},
KEYWORDS = {data fusion},
PUBLISHER = {Pergamon Press, Inc.}
}
@INPROCEEDINGS{Belkin1993,
AUTHOR = {Nicholas J. Belkin and C. Cool and W. Bruce Croft and James P. Callan},
TITLE = {The effect multiple query representations on information retrieval system performance},
BOOKTITLE = {SIGIR '93: Proceedings of the 16th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1993},
PAGES = {339--346},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/160688.160760},
ISBN = {0-89791-605-0},
KEYWORDS = {data fusion},
LOCATION = {Pittsburgh, Pennsylvania, United States}
}
@ARTICLE{Belkin1992,
AUTHOR = {Nicholas J. Belkin and W. Bruce Croft},
TITLE = {Information filtering and information retrieval: two sides of the same coin?},
JOURNAL = {Commun. ACM},
YEAR = {1992},
VOLUME = {35},
PAGES = {29--38},
NUMBER = {12},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/138859.138861},
ISSN = {0001-0782},
KEYWORDS = {information filtering, information retrieval},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{Berger1999,
AUTHOR = {Adam Berger and John Lafferty},
TITLE = {Information retrieval as statistical translation},
BOOKTITLE = {SIGIR '99: Proceedings of the 22nd annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1999},
PAGES = {222--229},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/312624.312681},
ISBN = {1-58113-096-1},
LOCATION = {Berkeley, California, United States}
}
@ARTICLE{Berners-Lee1994,
AUTHOR = {Tim Berners-Lee and Robert
Cailliau and Ari Luotonen and Henrik Frystyk Nielsen and Arthur Secret},
TITLE = {The {W}orld-{W}ide {W}eb},
JOURNAL = {Communications of the ACM},
YEAR = {1994},
VOLUME = {37},
PAGES = {76--82},
NUMBER = {8},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/179606.179671},
ISSN = {0001-0782},
KEYWORDS = {www},
PUBLISHER = {ACM Press}
}
@ARTICLE{Berners-Lee2001,
AUTHOR = {Tim Berners-Lee and James Hendler and Ora Lassila},
TITLE = {The Semantic Web},
JOURNAL = {Scientific American},
YEAR = {2001},
VOLUME = {284},
PAGES = {34--43},
NUMBER = {5},
MONTH = MAY,
ABSTRACT = {A new form of Web content that is
meaningful to computers will unleash a revolution of new possibilities},
URL = {http://www.scientificamerican.com/article.cfm?articleID=00048144-10D2-1C70-84A9809EC588EF21&catID=2}
}
@TECHREPORT{berry94using,
AUTHOR = {Michael W. Berry and Susan T. Dumais and Gavin W. O'Brien},
TITLE = {Using Linear Algebra for Intelligent Information Retrieval},
INSTITUTION = {University of Tennessee, Knoxville},
YEAR = {1994},
NUMBER = {UT-CS-94-270},
ABSTRACT = {Currently, most approaches
to retrieving textual materials from scientific databases depend
on a lexical match between words in users' requests and those in
or assigned to documents in a database. Because of the tremendous
diversity in the words people use to describe the same document, lexical
methods are necessarily incomplete and imprecise. Using the singular
value decomposition (SVD), one can take advantage of the implicit
higher-order structure in the association of terms with documents...},
KEYWORDS = {information retrieval, latent semantic indexing},
URL = {http://citeseer.ist.psu.edu/berry95using.html}
}
@ARTICLE{Bharat2000,
AUTHOR = {Krishna Bharat},
TITLE = {{S}earch{P}ad: explicit capture of search context to support {W}eb search},
JOURNAL = {Computer Networks},
YEAR = {2000},
VOLUME = {33},
PAGES = {493--501},
NUMBER = {1-6},
ADDRESS = {New York, NY, USA},
DOI = {http://dx.doi.org/10.1016/S1389-1286(00)00047-5},
ISSN = {1389-1286},
KEYWORDS = {information retrieval, personalization},
PUBLISHER = {Elsevier North-Holland, Inc.}
}
@ARTICLE{Blei2003,
AUTHOR = {David M. Blei and Andrew Y. Ng and Michael I. Jordan},
TITLE = {Latent Dirichlet Allocation},
JOURNAL = {Journal of Machine Learning Research},
YEAR = {2003},
VOLUME = {3},
PAGES = {993--1022},
URL = {http://www.cs.berkeley.edu/~blei/papers/blei03a.pdf}
}
@INPROCEEDINGS{Brachman1988,
AUTHOR = {Ronald J. Brachman and Deborah L. McGuinness},
TITLE = {Knowledge representation, connectionism and conceptual retrieval},
BOOKTITLE = {SIGIR '88: Proceedings of the 11th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1988},
PAGES = {161--174},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/62437.62448},
ISBN = {2-7061-0309-4},
LOCATION = {Grenoble, France}
}
@ARTICLE{Brachman1980,
AUTHOR = {Ronald J. Brachman and Brian C. Smith},
TITLE = {Special issue on knowledge representation},
JOURNAL = {SIGART Bulletin},
YEAR = {1980},
NUMBER = {70},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/1056751.1056752},
ISSN = {0163-5719},
PUBLISHER = {ACM Press}
}
@TECHREPORT{Breese1998,
AUTHOR = {John S. Breese and David Heckerman and Carl Kadie},
TITLE = {Empirical Analysis of Predictive Algorithms for Collaborative Filtering},
INSTITUTION = {Microsoft Research},
YEAR = {1998},
TYPE = {Techical Report},
NUMBER = {MSR-TR-98-12},
ADDRESS = {Microsoft Corporation, One Microsoft Way, Redmond, WA~98052},
MONTH = MAY,
ABSTRACT = {Collaborative ltering or recommender systems use a database about
user preferences to predict additional topics or products a new user
might like. In this paper we describe several algorithms designed for
this task, including techniques based on correlation coe cients,
vector-based sim- ilarity calculations, and statistical Bayesian
methods. We compare the predictive accuracy of the various methods in a
set of representative problem domains. We use two basic classes of
evaluation metrics. The rst characterizes accuracy over a set of
individual predictions in terms of average absolute deviation. The
second estimates the utility of a ranked list of suggested items. This
metric uses an estimate of the probability that a user will see a
recommendation in an ordered list. Experiments were run for datasets
associated with 3 application areas, 4 experimental pro- tocols, and the 2
evaluation metrics for the various algorithms. Results indicate that for a
wide range of conditions, Bayesian networks with decision trees at
each node and correlation methods outperform Bayesian-clustering and
vector-similarity methods. Between correlation and Bayesian networks, the
preferred method depends on the nature of the dataset, nature of
the application (ranked versus one-by-one presentation), and the
availability of votes with which to make predictions. Other considerations
include the size of database, speed of predictions, and learning time.},
URL = {http://research.microsoft.com/research/pubs/view.aspx?msr_tr_id=MSR-TR-98-12}
}
@MISC{FOAF,
AUTHOR = {Dan Brickley and Libby Miller},
TITLE = {{FOAF} Vocabulary Specification},
HOWPUBLISHED = {\url{http://xmlns.com/foaf/0.1/}},
YEAR = {2005}
}
@ARTICLE{brin98anatomy,
AUTHOR = {Sergey Brin and Lawrence Page},
TITLE = {The anatomy of a large-scale hypertextual {Web} search engine},
JOURNAL = {Computer Networks and ISDN Systems},
YEAR = {1998},
VOLUME = {30},
PAGES = {107--117},
NUMBER = {1--7},
CITESEERURL = {citeseer.ist.psu.edu/brin98anatomy.html},
KEYWORDS = {information retrieval, web retrieval},
URL = {ftp://db.stanford.edu/pub/papers/google.pdf}
}
@INPROCEEDINGS{Broder2000,
AUTHOR = {Andrei Broder and Ravi Kumar and Farzin Maghoul and Prabhakar Raghavan and Sridhar
Rajagopalan and Raymie Stata and Andrew Tomkins and Janet Wiener},
TITLE = {Graph structure in the Web},
BOOKTITLE = {Proceedings of the 9th
international World Wide Web conference on Computer networks: the
international journal of computer and telecommunications networking},
YEAR = {2000},
PAGES = {309--320},
ADDRESS = {Amsterdam, The Netherlands, The Netherlands},
PUBLISHER = {North-Holland Publishing Co.},
DOI = {http://dx.doi.org/10.1016/S1389-1286(00)00083-9},
LOCATION = {Amsterdam, The Netherlands},
URL = {http://www.almaden.ibm.com/webfountain/resources/GraphStructureintheWeb.pdf}
}
@ARTICLE{Broder2000a,
AUTHOR = {Andrei Broder and Ravi Kumar and Farzin Maghoul and Prabhakar Raghavan and Sridhar
Rajagopalan and Raymie Stata and Andrew Tomkins and Janet Wiener},
TITLE = {Graph structure in the Web},
JOURNAL = {Computer Networks},
YEAR = {2000},
VOLUME = {33},
PAGES = {309--320},
URL = {http://www.people.cornell.edu/pages/dc288/Paper1.pdf}
}
@ARTICLE{Bush1996,
AUTHOR = {Vannevar Bush},
TITLE = {As We May Think},
JOURNAL = {interactions},
YEAR = {1996},
VOLUME = {3},
PAGES = {35--46},
NUMBER = {2},
NOTE = {Reprint of \cite{Bush1945}.},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/227181.227186},
ISSN = {1072-5520},
PUBLISHER = {ACM Press}
}
@ARTICLE{Bush1945,
AUTHOR = {Vannevar Bush},
TITLE = {As We May Think},
JOURNAL = {The Atlantic Monthly},
YEAR = {1945},
VOLUME = {176},
PAGES = {101--108},
NUMBER = {1},
MONTH = JUL,
NOTE = {Reprinted as \cite{Bush1996}.},
URL = {http://www.theatlantic.com/doc/prem/194507/bush}
}
@PHDTHESIS{Campbell2000,
AUTHOR = {Iain Campbell},
TITLE = {The ostensive model of developing information-needs},
SCHOOL = {University of Glasgow},
YEAR = {2000},
ABSTRACT = {From intuitions and informal observations of searching behaviour, a
formal model is developed of cognition during a searching session.
The model is of the iterative updating of an information-need by
exposure of a user to information during a session. The model is
path-based £ using trends within the content of objects on a path
to predict the current information-need. This provides contextual
interpretation of objects based upon the path taken to an object.
The model is ostensive in nature; however, instead of the active
communicated evidence of traditional conceptions of ostension, it
uses passive observational evidence. It produces a new notion of
relevance: Ostensive Relevance £ profiles of which are the key to the
effective use of path information. The integration of the Ostensive
Model and the Binary Probabilistic Model is achieved by weakening
of a conventional assumption in the estimation of a probabilistic
parameter. This integration effects a novel combination of objective and
subjective probabilities £ commonly regarded as incompatible. The
Ostensive Model is instantiated in a combination of a networked IR
server and a novel graphical user-interface. The interface presents a
fish-eyed view of a growing multi-path browsing surface that hides
internal representations and obviates querying. The hiding of internals,
combined with the ability of the Ostensive Model to follow a developing
information-need, makes the interface a truly media-neutral searching
environment. A new test collection of general interest images with four
binary relevance assessments is constructed and used for an evaluation
of three Ostensive Relevance Profiles. The results are analysed in
the light of different interpretations of the multiple assessments
of the test-collection. The evaluation method is itself analysed
and concrete proposals made for its development. The results of the
evaluation provide strong encouragement for the Ostensive approach.},
KEYWORDS = {information retrieval, ostensive retrieval},
URL = {http://www.dcs.gla.ac.uk/~iain/papers/phd.pdf}
}
@INPROCEEDINGS{Campbell1996,
AUTHOR = {Iain Campbell and Cornelis J. {van Rijsbergen}},
TITLE = {The ostensive model of developing information needs},
BOOKTITLE = {Proceedings of {COLIS}-96, 2nd International Conference on Conceptions of Library Science},
YEAR = {1996},
PAGES = {251--268},
ADDRESS = {Kobenhavn, DK},
ABSTRACT = {We present a model of the progressive development of information needs. It is a
model that recognises the changing uncertainty inherent in a user?s
cognition of his information need. The approach centres around the
collection and combination of ostensive evidence. We present uncertainty
profiles associated with the discounting of ostensive evidence with
respect to its age, and relate that to a new notion of relevance -
Ostensive Relevance. This notion recognises the transient, inaccessible,
spatio-temporal nature of relevance. We describe how these components
come together to allow the Ostensive Model to be integrated with the
traditional Binary Probabilistic Model. We describe the integration
and show that it reveals an implicit assumption in the conventional
estimation procedure for a particular conditional probability. The
temporal aspects of the Ostensive Model allow a weakening of that
assumption. The integration allows direct implementation of the Ostensive
Model. Finally, we present an example that demonstrates the intuitive
appeal of the approach over existing approaches to Relevance Feedback.},
KEYWORDS = {information retrieval, ostensive retrieval},
URL = {citeseer.ist.psu.edu/campbell00ostensive.html}
}
@MISC{Ceglowski2003,
AUTHOR = {Maciej Ceglowski and Aaron Coburn and John Cuadrado},
TITLE = {Semantic Search of Unstructured Data using Contextual Network Graphs},
YEAR = {2003},
KEYWORDS = {spreading activation, information retrieval},
OWNER = {skirsch},
URL = {http://research.nitle.org/papers/Contextual_Network_Graphs.pdf}
}
@ARTICLE{Chung2002,
AUTHOR = {Fan Chung and Linyuan Lu},
TITLE = {The average distances in random graphs with given expected degrees.},
JOURNAL = {Proceedings of the National Academy of Sciences of the United States of America},
YEAR = {2002},
VOLUME = {99},
PAGES = {15879--15882},
NUMBER = {25},
MONTH = DEC,
ABSTRACT = {Random graph theory is used to examine the
"small-world phenomenon"; any two strangers are connected through a
short chain of mutual acquaintances. We will show that for certain
families of random graphs with given expected degrees the average
distance is almost surely of order log nlog d, where d is the weighted
average of the sum of squares of the expected degrees. Of particular
interest are power law random graphs in which the number of vertices of
degree k is proportional to 1kbeta for some fixed exponent beta.
For the case of beta> 3, we prove that the average distance of the
power law graphs is almost surely of order log nlog d. However, many
Internet, social, and citation networks are power law graphs with
exponents in the range 2 < beta < 3 for which the power law random graphs
have average distance almost surely of order log log n, but have
diameter of order log n (provided having some mild constraints for the
average distance and maximum degree). In particular, these graphs
contain a dense subgraph, which we call the core, having n(clog log n)
vertices. Almost all vertices are within distance log log n of the
core although there are vertices at distance log n from the core.},
DOI = {10.1073/pnas.252631999},
PII = {252631999},
URL = {http://dx.doi.org/10.1073/pnas.252631999}
}
@ARTICLE{Church1990,
AUTHOR = {Kenneth Ward Church and Patrick Hanks},
TITLE = {Word association norms, mutual information, and lexicography},
JOURNAL = {Comput. Linguist.},
YEAR = {1990},
VOLUME = {16},
PAGES = {22--29},
NUMBER = {1},
ABSTRACT = {The term word assaciation is used in a very particular sense in the psycholinguistic
literature. (Generally speaking, subjects respond quicker than normal
to the word "nurse" if it follows a highly associated word such as
"doctor.") We wilt extend the term to provide the basis for a statistical
description of a variety of interesting linguistic phenomena, ranging from
semantic relations of the doctor/nurse type (content word/content
word) to lexico-syntactic co-occurrence constraints between verbs and
prepositions (content word/function word). This paper will propose a new
objective measure based on the information theoretic notion of mutual
information, for estimating word association norms from computer
readable corpora. (The standard method of obtaining word association
norms, testing a few thousand subjects on a few hundred words, is both
costly and unreliable.) The , proposed measure, the association ratio,
estimates word association norms directly from computer readable corpora,
waki,~g it possible to estimate norms for tens of thousands of words.},
ADDRESS = {Cambridge, MA, USA},
ISSN = {0891-2017},
KEYWORDS = {computational linguistics, statistics},
PUBLISHER = {MIT Press},
URL = {http://www.aclweb.org/anthology/P89-1010}
}
@ARTICLE{30967,
AUTHOR = {Paul R. Cohen and Rick Kjeldsen},
TITLE = {Information retrieval by constrained spreading activation in semantic networks},
JOURNAL = {Inf. Process. Manage.},
YEAR = {1987},
VOLUME = {23},
PAGES = {255--268},
NUMBER = {4},
ADDRESS = {Tarrytown, NY, USA},
DOI = {http://dx.doi.org/10.1016/0306-4573(87)90017-3},
ISSN = {0306-4573},
KEYWORDS = {information retrieval, spreading activation, GRANT},
PUBLISHER = {Pergamon Press, Inc.}
}
@INPROCEEDINGS{Craswell2005,
AUTHOR = {Nick Craswell and Stephen Robertson and Hugo Zaragoza and Michael Taylor},
TITLE = {Relevance weighting for query independent evidence},
BOOKTITLE = {SIGIR '05: Proceedings of the 28th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {2005},
PAGES = {416--423},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/1076034.1076106},
ISBN = {1-59593-034-5},
LOCATION = {Salvador, Brazil},
URL = {http://research.microsoft.com/users/cambridge/hugoz/pubs/pdf/craswell_sigir05.pdf}
}
@ARTICLE{Crestani1997a,
AUTHOR = {F. Crestani},
TITLE = {Application of Spreading Activation Techniques in Information Retrieval},
JOURNAL = {Artificial Intelligence Review},
YEAR = {1997},
VOLUME = {11},
PAGES = {453--482},
NUMBER = {6},
ABSTRACT = {This paper surveys the use of Spreading Activation techniques on
Semantic Networks in Associative Information Retrieval. The major
Spreading Activation models are presented and their applications to IR is
surveyed. A number of works in this area are critically analyzed in order
to study the relevance of Spreading Activation for associative IR.},
ADDRESS = {Norwell, MA, USA},
DOI = {http://dx.doi.org/10.1023/A:1006569829653},
ISSN = {0269-2821},
KEYWORDS = {spreading activation,
information storage and retrieval, semantic networks, associative
information retrieval, information processing, knowledge representation},
PUBLISHER = {Kluwer Academic Publishers}
}
@ARTICLE{Crestani2000,
AUTHOR = {Fabio Crestani and Puay Leng Lee},
TITLE = {Searching the Web by constrained spreading activation},
JOURNAL = {Information Processing and Management},
YEAR = {2000},
VOLUME = {36},
PAGES = {585--605},
NUMBER = {4},
ADDRESS = {Tarrytown, NY, USA},
DOI = {http://dx.doi.org/10.1016/S0306-4573(99)00073-4},
ISSN = {0306-4573},
PUBLISHER = {Pergamon Press, Inc.}
}
@INPROCEEDINGS{Crestani1999,
AUTHOR = {Fabio Crestani and Puay Leng Lee},
TITLE = {{W}eb{SCSA}: Web Search by Constrained Spreading Activation},
BOOKTITLE = {{ADL} '99: Proceedings of the
{IEEE} Forum on Research and Technology Advances in Digital Libraries},
YEAR = {1999},
PAGES = {163},
ADDRESS = {Washington, DC, USA},
PUBLISHER = {IEEE Computer Society},
ISBN = {0-7695-0219-9},
KEYWORDS = {information retrieval, web retrieval, spreading activation}
}
@ARTICLE{Crestani1997,
AUTHOR = {Fabio Crestani and Cornelis J. {v}an Rijsbergen},
TITLE = {A Model for Adaptive Information Retrieval},
JOURNAL = {Journal of Intelligent Information Systems},
YEAR = {1997},
VOLUME = {8},
PAGES = {29--56},
ABSTRACT = {The paper presents a network model that can be used to produce conceptual and
logical schemas for Information Retrieval applications. The model has
interesting adaptability characteristics and can be instantiated in various
effective ways. The paper also reports the results of an experimental
investigation into the effectiveness of implementing associative and adaptive
retrieval on the proposed model by means of Neural Networks. The
implementationmakes use of the learning and generalisation capabilities of the
Backpropagation learning algorithm to build up and use application domain
knowledge in a sub-symbolic form. The knowledge is acquired from
examples of queries and relevant documents. Three different learning
strategies are introduced, their performance is analysed and compared
with the performance of a traditional Information Retrieval system.},
DOI = {http://dx.doi.org/10.1023/A:1008601616486},
KEYWORDS = {information retrieval, adaptive retrieval, model},
OWNER = {skirsch},
URL = {http://portal.acm.org/citation.cfm?id=251408.251009}
}
@INPROCEEDINGS{62491,
AUTHOR = {W. B. Croft and T. J. Lucia and P. R. Cohen},
TITLE = {Retrieving documents by plausible inference: a preliminary study},
BOOKTITLE = {SIGIR '88: Proceedings of the 11th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1988},
PAGES = {481--494},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/62437.62491},
ISBN = {2-7061-0309-4},
KEYWORDS = {information retrieval, associative retrieval},
LOCATION = {Grenoble, France}
}
@INPROCEEDINGS{Cuenca-Acuna2002,
AUTHOR = {Francisco Matias Cuenca-Acuna and Thu D. Nguyen},
TITLE = {Text-Based Content Search and Retrieval in ad hoc P2P Communities},
BOOKTITLE = {International Workshop on Peer-to-Peer Computing (co-located with Networking 2002)},
YEAR = {2002},
VOLUME = {2376},
SERIES = {Lecture Notes in Computer Science},
MONTH = MAY,
PUBLISHER = {Springer-Verlag},
ISBN = {3-540-44177-8},
URL = {www.cs.rutgers.edu/~mcuenca}
}
@INPROCEEDINGS{DAmore2004,
AUTHOR = {Raymond D'Amore},
TITLE = {Expertise community detection},
BOOKTITLE = {SIGIR '04: Proceedings of the 27th annual international
conference on Research and development in information retrieval},
YEAR = {2004},
PAGES = {498--499},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/1008992.1009089},
ISBN = {1-58113-881-4},
KEYWORDS = {expert finding, expert location},
LOCATION = {Sheffield, United Kingdom}
}
@ARTICLE{deerwester90indexing,
AUTHOR = {Scott C. Deerwester and Susan T. Dumais and
Thomas K. Landauer and George W. Furnas and Richard A. Harshman},
TITLE = {Indexing by Latent Semantic Analysis},
JOURNAL = {Journal of the American Society of Information Science},
YEAR = {1990},
VOLUME = {41},
PAGES = {391-407},
NUMBER = {6},
URL = {http://citeseer.ist.psu.edu/deerwester90indexing.html}
}
@INPROCEEDINGS{Dittrich2005,
AUTHOR = {Jens-Peter Dittrich and
Marcos Antonio Vaz Salles and Donald Kossmann and Lukas Blunschi},
TITLE = {{iMeMex}: Escapes from the Personal Information Jungle},
BOOKTITLE = {Proceedings of the 31st VLDB Conference},
YEAR = {2005},
ADDRESS = {Trondheim, Norway}
}
@ARTICLE{Dodds2003,
AUTHOR = {Peter Sheridan Dodds and Roby Muhamad and Duncan J. Watts},
TITLE = {An Experimental Study of Search in Global Social Networks},
JOURNAL = {Science},
YEAR = {2003},
VOLUME = {301},
PAGES = {827--829},
MONTH = AUG,
ABSTRACT = {We report on a global social-search experiment in which more than 60,000 e-mail
users attempted to reach one of 18 target persons in 13 countries by
forwarding messages to acquaintances. We find that successful social
search is conducted primarily through intermediate to weak strength
ties, does not require highly connected ?hubs? to succeed, and, in
contrast to unsuccessful social search, disproportionately relies on
professional relationships. By accounting for the attrition of message
chains, we estimate that social searches can reach their targets
in a median of five to seven steps, depending on the separation of
source and target, although small variations in chain lengths and
participation rates generate large differences in target reachability. We
conclude that although global social networks are, in principle,
searchable, actual success depends sensitively on individual incentives.}
}
@ARTICLE{Donato2004,
AUTHOR = {D. Donato and L. Laura and S. Leonardi and S. Millozzi},
TITLE = {Large scale properties of the Webgraph},
JOURNAL = {European Physical Journal B},
YEAR = {2004},
VOLUME = {38},
PAGES = {239-243},
DOI = {10.1140/epjb/e2004-00056-6}
}
@ARTICLE{Doray2002,
AUTHOR = {Louis G. Doray and Michel Arsenault},
TITLE = {Estimators of the regression parameters of the zeta distribution},
JOURNAL = {Insurance: Mathematics and Economics},
YEAR = {2002},
VOLUME = {30},
PAGES = {439--450},
NUMBER = {3},
MONTH = JUN,
ABSTRACT = {The zeta distribution with regression parameters has been rarely used in statistics
because of the difficulty of estimating the parameters by traditional
maximum likelihood. We propose an alternative method for estimating the
parameters based on an iteratively reweighted least-squares algorithm. The
quadratic distance estimator (QDE) obtained is consistent, asymptotically
unbiased and normally distributed; the estimate can also serve as the
initial value required by an algorithm to maximize the likelihood
function. We illustrate the method with a numerical example from the
insurance literature; we compare the values of the estimates obtained
by the quadratic distance and maximum likelihood methods and their
approximate variance?covariance matrix. Finally, we calculate the bias,
variance and the asymptotic efficiency of the QDE compared to the
maximum likelihood estimator (MLE) for some values of the parameters.},
DOI = {http://dx.doi.org/10.1016/S0167-6687(02)00130-0},
KEYWORDS = {Zeta distribution; Covariates; Maximum likelihood; Quadratic distance
estimator; Iteratively reweighted least-squares; Aymptotic efficiency}
}
@ARTICLE{Doreian1994,
AUTHOR = {Patrick Doreian},
TITLE = {A measure of standing for citation networks within a wider environment},
JOURNAL = {Information Processing \& Management},
YEAR = {1994},
VOLUME = {30},
PAGES = {21-31},
NUMBER = {1},
COMMENT = {cited in PageRank patent}
}
@INPROCEEDINGS{Dwork2001,
AUTHOR = {Cynthia Dwork and Ravi Kumar and Moni Naor and D. Sivakumar},
TITLE = {Rank aggregation methods for the Web},
BOOKTITLE = {WWW '01: Proceedings of the 10th international conference on World Wide Web},
YEAR = {2001},
PAGES = {613--622},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/371920.372165},
ISBN = {1-58113-348-0},
LOCATION = {Hong Kong, Hong Kong},
URL = {http://www.www10.org/cdrom/papers/pdf/p577.pdf}
}
@ARTICLE{Erdos1959,
AUTHOR = {Paul Erd\H{o}s and Alfr{\'e}d R{\'e}nyi},
TITLE = {On Random Graphs},
JOURNAL = {Publicationes Mathematicae},
YEAR = {1959},
VOLUME = {6},
PAGES = {290--297}
}
@INPROCEEDINGS{Fagan1987,
AUTHOR = {J. Fagan},
TITLE = {Automatic phrase indexing for document retrieval},
BOOKTITLE = {SIGIR '87: Proceedings of the 10th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1987},
PAGES = {91--101},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/42005.42016},
ISBN = {0-89791-232-2},
LOCATION = {New Orleans, Louisiana, United States}
}
@INPROCEEDINGS{Fagin2003,
AUTHOR = {Ronald Fagin and Ravi Kumar and Kevin S. McCurley and Jasmine
Novak and D. Sivakumar and John A. Tomlin and David P. Williamson},
TITLE = {Searching the workplace web},
BOOKTITLE = {WWW '03: Proceedings of the 12th international conference on World Wide Web},
YEAR = {2003},
PAGES = {366--375},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/775152.775204},
ISBN = {1-58113-680-3},
LOCATION = {Budapest, Hungary}
}
@ARTICLE{Farahat2005,
AUTHOR = {Ayman Farahat and Thomas LoFaro and Joel C. Miller and Gergory Rae and Leslie A. Ward},
TITLE = {Authority Rankings from {HITS}, {P}age{R}ank
and {SALSA}: Existence, Uniqueness and Effect of Initializations},
JOURNAL = {SIAM Journal of Scientific Computing},
YEAR = {2005},
VOLUME = {27},
PAGES = {1181--1201},
NUMBER = {4},
ABSTRACT = {Algorithms such as Kleinberg's HITS algorithm,
the PageRank algorithm of Brin and Page, and the SALSA algorithm of
Lempel and Moran use the link structure of a network of web pages to
assign weights to each page in the network. The weights can then be
used to rank the pages as authoritative sources. These algorithms
share a common underpinning; they find a dominant eigenvector of a
nonnegative matrix that describes the link structure of the given
network and use the entries of this eigenvector as the page weights.
We use this commonality to give a unified treatment, proving the
existence of the required eigenvector for the PageRank, HITS, and
SALSA algorithms, the uniqueness of the PageRank eigenvector, and the
convergence of the algorithms to these eigenvectors. However, we
show that the HITS and SALSA eigenvectors need not be unique. We
examine how the initialization of the algorithms affects the final
weightings produced. We give examples of networks that lead the HITS and
SALSA algorithms to return nonunique or nonintuitive rankings. We
characterize all such networks in terms of the connectivity of the related
HITS authority graph. We propose a modification, Exponentiated Input
to HITS, to the adjacency matrix input to the HITS algorithm. We
prove that Exponentiated Input to HITS returns a unique ranking,
provided that the network is weakly connected. Our examples also show
that SALSA can give inconsistent hub and authority weights, due to
nonuniqueness. We also mention a small modification to the SALSA
initialization which makes the hub and authority weights consistent.},
DOI = {10.1137/S1064827502412875},
URL = {http://epubs.siam.org/fulltext/SISC/volume-27/41287.pdf}
}
@BOOK{Feynman1989,
TITLE = {What do you care what other people think?},
PUBLISHER = {Bantam},
YEAR = {1989},
AUTHOR = {Richard P. Feynman}
}
@INPROCEEDINGS{Fitzpatrick1997,
AUTHOR = {Larry Fitzpatrick and Mei Dent},
TITLE = {Automatic feedback using past queries: social searching?},
BOOKTITLE = {SIGIR '97: Proceedings of the 20th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1997},
PAGES = {306--313},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/258525.258597},
ISBN = {0-89791-836-3},
LOCATION = {Philadelphia, Pennsylvania, United States}
}
@INPROCEEDINGS{Flake2000,
AUTHOR = {Gary William Flake and Steve Lawrence and C. Lee Giles},
TITLE = {Efficient identification of Web communities},
BOOKTITLE = {KDD '00: Proceedings of the sixth ACM SIGKDD
international conference on Knowledge discovery and data mining},
YEAR = {2000},
PAGES = {150--160},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/347090.347121},
ISBN = {1-58113-233-6},
LOCATION = {Boston, Massachusetts, United States}
}
@ARTICLE{Flake2002,
AUTHOR = {Gary William Flake and Steve Lawrence and C. Lee Giles and Frans M. Coetzee},
TITLE = {Self-Organization and Identification of Web Communities},
JOURNAL = {Computer},
YEAR = {2002},
VOLUME = {35},
PAGES = {66--71},
NUMBER = {3},
DOI = {http://dx.doi.org/10.1109/2.989932},
ISSN = {0018-9162},
PUBLISHER = {IEEE Computer Society Press}
}
@INCOLLECTION{Flake2004,
AUTHOR = {Gary William Flake and Kostas Tsioutsiouliklis and Leonid Zhukov},
TITLE = {Methods for Mining Web Communities: Bibliometric, Spectral, and Flow},
BOOKTITLE = {Web Dynamics},
PUBLISHER = {Springer Verlag},
YEAR = {2004},
EDITOR = {Alexandra Poulovassilis and Mark Levene},
CHAPTER = {4},
PAGES = {45--68},
ABSTRACT = {In this chapter, we examine the problem
of Web community identification expressed in terms of the graph or
network structure induced by the Web. While the task of community
identification is obviously related to the more fundamental problems of graph
partitioning and clustering, the basic task is differentiated from other
problems by being within the Web domain. This single difference has many
implications for how effective methods work, both in theory and in
practice. In order of presentation, we will examine bibliometric
similarity measures, bipartite community cores, the HITS algorithm,
PageRank, and maximum flow-based Web communities. Interestingly,
each of these topics relate to one-another in a non-trivial manner.},
ISBN = {3-540-40676-X},
OWNER = {skirsch},
URL = {http://research.yahoo.com/publications/4.pdf}
}
@TECHREPORT{Flake2003TR,
AUTHOR = {Gary William Flake and Kostas Tsioutsiouliklis and Leonid Zhukov},
TITLE = {Methods for Mining Web Communities: Bibliometric, Spectral, and Flow},
INSTITUTION = {Overture Research},
YEAR = {2003},
NUMBER = {OR-2003-004},
ABSTRACT = {In this chapter, we examine the problem
of Web community identification expressed in terms of the graph or
network structure induced by the Web. While the task of community
identification is obviously related to the more fundamental problems of graph
partitioning and clustering, the basic task is differentiated from other
problems by being within the Web domain. This single difference has many
implications for how effective methods work, both in theory and in
practice. In order of presentation, we will examine bibliometric
similarity measures, bipartite community cores, the HITS algorithm,
PageRank, and maximum flow-based Web communities. Interestingly,
each of these topics relate to one-another in a non-trivial manner.},
OWNER = {skirsch},
URL = {http://research.yahoo.com/publications/4.pdf}
}
@TECHREPORT{Fortunato2005,
AUTHOR = {Santo Fortunato and Alessandro Flammini and Filippo Menczer and Alessandro Vespignani},
TITLE = {The egalitarian effect of search engines},
INSTITUTION = {arXiv.org},
YEAR = {2005},
NUMBER = {cs.CY/0511005},
NOTE = {Preprint.},
URL = {http://arxiv.org/pdf/cs.CY/0511005}
}
@INPROCEEDINGS{Fox1993,
AUTHOR = {Edward A. Fox and Joseph A. Shaw},
TITLE = {Combination of Multiple Searches},
BOOKTITLE = {Proceedings of the Second {T}ext {RE}trieval {C}onference ({TREC}-2)},
YEAR = {1994},
EDITOR = {D. K. Harman},
NUMBER = {500-215},
SERIES = {NIST Special Publications},
ORGANIZATION = {U.S. National Institute of Standards and Technology (NIST)},
KEYWORDS = {data fusion},
URL = {http://trec.nist.gov/pubs/trec2/papers/ps/vpi.ps.gz}
}
@ARTICLE{Freeman1979,
AUTHOR = {Linton C. Freeman},
TITLE = {Centrality in Social Networks. Conceptual Clarification},
JOURNAL = {Social Networks},
YEAR = {1979},
VOLUME = {1},
PAGES = {215--239}
}
@ARTICLE{Frei1995,
AUTHOR = {H. P. Frei and D. Stieger},
TITLE = {The use of semantic links in hypertext information retrieval},
JOURNAL = {Information Processing and Management},
YEAR = {1995},
VOLUME = {31},
PAGES = {1--13},
NUMBER = {1},
ADDRESS = {Tarrytown, NY, USA},
DOI = {http://dx.doi.org/10.1016/0306-4573(94)E0005-M},
ISSN = {0306-4573},
PUBLISHER = {Pergamon Press, Inc.}
}
@INCOLLECTION{Freyne2004,
AUTHOR = {Jill Freyne and Barry Smyth},
TITLE = {An Experiment in Social Search},
BOOKTITLE = {Adaptive Hypermedia and Adaptive Web-Based Systems, Third International Conference, AH
2004, Eindhoven, The Netherlands, August 23-26, 2004, Proceedings},
PUBLISHER = {Springer},
YEAR = {2004},
EDITOR = {Wolfgang Nejdl and De Bra, Paul},
VOLUME = {3137},
SERIES = {Lecture Notes in Computer Science},
PAGES = {95--103},
ISBN = {3-540-22895-0},
OWNER = {skirsch}
}
@INPROCEEDINGS{Furnkranz2003,
AUTHOR = {J. F{\"u}rnkranz and P. A. Flach},
TITLE = {An analysis of rule evaluation metrics},
BOOKTITLE = {Proceedings of the 20th International Conference on Machine Learning (ICML'03)},
YEAR = {2003},
PAGES = {202--209},
MONTH = {January},
PUBLISHER = {AAAI Press},
ABSTRACT = {In this paper we analyze the most popular evaluation metrics for separate-and-conquer
rule learning algorithms. Our results show that all commonly used
heuristics, including accuracy, weighted relative accuracy, entropy, Gini
index and information gain, are equivalent to one of two fundamental
prototypes: precision, which tries to optimize the area under the ROC curve
for unknown costs, and a cost-weighted difference between covered
positive and negative examples, which tries to find the optimal point
under known or assumed costs. We also show that a straight-forward
generalization of the m-estimate trades off these two prototypes.},
ABSTRACT-URL = {http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000705},
ISBN = {1-57735-189-4},
PUBTYPE = {102},
URL = {http://www.cs.bris.ac.uk/Publications/Papers/1000705.pdf}
}
@INPROCEEDINGS{Garofolo1997,
AUTHOR = {John S. Garofolo and
Ellen M. Voorhees and Vincent M. Stanford and Karen Sp{\"a}rck Jones},
TITLE = {{TREC}-6 1997 Spoken Document Retrieval Track Overview and Results},
BOOKTITLE = {Proceedings of the Sixth {T}ext {RE}trieval {C}onference {TREC}-6},
YEAR = {1997},
EDITOR = {E. M. Voorhees and D. K. Harman},
NUMBER = {500-240},
SERIES = {NIST Special Publications},
ORGANIZATION = {U.S. National Institute of Standards and Technology (NIST)},
URL = {http://trec.nist.gov/pubs/trec6/papers/sdr97.ps.gz}
}
@INPROCEEDINGS{Gevrey2001,
AUTHOR = {Julien Gevrey and Stefan M. R{\"u}ger},
TITLE = {Link-based Approaches for Text Retrieval},
BOOKTITLE = {Proceedings of the Tenth {T}ext {RE}trieval {C}onference {TREC}-10},
YEAR = {2001},
EDITOR = {E. M. Voorhees and D. K. Harman},
NUMBER = {500-250},
SERIES = {NIST Special Publications},
PAGES = {279--285},
ORGANIZATION = {U.S. National Institute of Standards and Technology (NIST)},
URL = {http://trec.nist.gov/pubs/trec10/papers/web-gevrey-rueger.pdf}
}
@INPROCEEDINGS{Gibson1998,
AUTHOR = {David Gibson and Jon Kleinberg and Prabhakar Raghavan},
TITLE = {Inferring Web communities from link topology},
BOOKTITLE = {HYPERTEXT '98: Proceedings of the ninth ACM conference on Hypertext and hypermedia :
links, objects, time and space---structure in hypermedia systems},
YEAR = {1998},
PAGES = {225--234},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/276627.276652},
ISBN = {0-89791-972-6},
LOCATION = {Pittsburgh, Pennsylvania, United States}
}
@ARTICLE{Girvan2002,
AUTHOR = {M. Girvan and M. E. J. Newman},
TITLE = {Community structure in social and biological networks.},
JOURNAL = {Proc Natl Acad Sci U S A},
YEAR = {2002},
VOLUME = {99},
PAGES = {7821-6},
NUMBER = {12},
MONTH = {Jun},
ABSTRACT = {A number of recent studies have focused on the statistical properties of networked
systems such as social networks and the Worldwide Web. Researchers
have concentrated particularly on a few properties that seem to be
common to many networks: the small-world property, power-law degree
distributions, and network transitivity. In this article, we highlight another
property that is found in many networks, the property of community
structure, in which network nodes are joined together in tightly
knit groups, between which there are only looser connections. We
propose a method for detecting such communities, built around the
idea of using centrality indices to find community boundaries. We
test our method on computer-generated and real-world graphs whose
community structure is already known and find that the method detects
this known structure with high sensitivity and reliability. We also
apply the method to two networks whose community structure is not
well known--a collaboration network and a food web--and find that it
detects significant and informative community divisions in both cases.},
DOI = {10.1073/pnas.122653799},
KEYWORDS = {Algorithms, Animals, Community Networks, Computer Simulation,
Humans, Models, Nerve Net, Neural Networks (Computer), Non-P.H.S.,
Research Support, Social Behavior, Theoretical, U.S. Gov't, 12060727},
PII = {99/12/7821},
URL = {http://dx.doi.org/10.1073/pnas.122653799}
}
@MISC{Gladwell1999,
AUTHOR = {Malcolm Gladwell},
TITLE = {Six Degrees of Lois Weisberg},
HOWPUBLISHED = {The New Yorker},
MONTH = {jan},
YEAR = {1999},
URL = {http://www.gladwell.com/1999/1999_01_11_a_weisberg.htm}
}
@INPROCEEDINGS{Glance2001,
AUTHOR = {Natalie S. Glance},
TITLE = {Community search assistant},
BOOKTITLE = {IUI '01: Proceedings of
the 6th international conference on Intelligent user interfaces},
YEAR = {2001},
PAGES = {91--96},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/359784.360293},
ISBN = {1-58113-325-1},
LOCATION = {Santa Fe, New Mexico, United States}
}
@INCOLLECTION{Gnasa2003,
AUTHOR = {Gnasa, Melanie and Alda, Sascha and Grigull, Jasmin and Cremers, Armin B.},
TITLE = {Towards Virtual Knowledge Communities in Peer-to-Peer Networks},
BOOKTITLE = {Distributed Multimedia Information Retrieval},
PUBLISHER = {Springer},
YEAR = {2003},
EDITOR = {Jamie Callan and Fabio Crestani and Mark Sanderson},
VOLUME = {2924},
SERIES = {Lecture Notes in Computer Science},
PAGES = {143--155},
ABSTRACT = {As a result of the anonymity in todays Web search, it
is not possible to receive a personalized search result. Neither
prior search results nor search results from other users are taken
into consideration. In order to resolve this anonymity towards the
search engine, a system is created which locally stores the search
results in the scope of a peerto- peer network. Using the Peer Search
Memory (PeerSy) all approved bookmarks are stored and associated
with the corresponding queries. By this means, repeated access is
facilitated. Furthermore, sharing of bookmarks in the peer-to-peer
network allows grouping of Virtual Knowledge Communities (VKC) in
order to obtain a surplus value in knowledge sharing on the Web.},
KEYWORDS = {ISKODOR},
OWNER = {skirsch},
URL = {http://www.springerlink.com/index/NUR92TH9821N5TPJ}
}
@INPROCEEDINGS{Gnasa2004a,
AUTHOR = {Melanie Gnasa and Sascha Alda and Nadir G{\"u}l and Jasmin Grigull and Armin B. Cremers},
TITLE = {Cooperative Pull-Push Cycle for Searching a Hybrid P2P Network},
BOOKTITLE = {4th International Conference on Peer-to-Peer Computing (P2P 2004)},
YEAR = {2004},
PAGES = {192--199},
ADDRESS = {Z{\"u}rich, Switzerland},
ABSTRACT = {Information acquisition is a great challenge in the context of
a continually growing Web. Nowadays, large Web search engines are
primarily designed to assist an information pull by the user. On
this platform, only actual information needs are handled without
assistance of long-term needs. To overcome these shortcomings we propose a
cooperative system for information pull and push on a peerto- peer
architecture. In this paper we present a hybrid network for a collaborative
search environment, based on a local personalization strategy on each
peer, and a highlyavailable Web search service (e.g. Google). Each
peer participates in the Pull-Push Cycle, and has the function of an
information consumer as well as an information provider. Hence, long-term
information needs can be identified without any context restrictions, and
recommendations are computed based on Virtual Knowledge Communities.},
KEYWORDS = {ISKODOR},
OWNER = {skirsch},
URL = {http://ir.iai.uni-bonn.de/research/downloads/p2p-Gnasa-2004.pdf}
}
@ARTICLE{Gnasa2004,
AUTHOR = {Melanie Gnasa and Markus Won and Armin B. Cremers},
TITLE = {Three Pillars for Congenial Web
Search. {C}ontinuous Evaluation for enhancing Web Search Effectiveness},
JOURNAL = {Journal of Web Engineering},
YEAR = {2004},
VOLUME = {3},
PAGES = {252--280},
NUMBER = {3\&4},
ADDRESS = {Princeton},
ISSN = {1540-9589},
KEYWORDS = {ISKODOR},
OWNER = {skirsch},
PUBLISHER = {Rinton Press},
URL = {http://www.informatik.uni-bonn.de/~won/Download/wwwjournal2004.pdf}
}
@ARTICLE{Goldstein2004,
AUTHOR = {Goldstein, M. L. and Morris, S. A. and Yen, G. G.},
TITLE = {Problems with fitting to the power-law distribution},
JOURNAL = {The European Physical Journal B},
YEAR = {2004},
VOLUME = {41},
PAGES = {255--258},
NUMBER = {2},
MONTH = SEP,
URL = {http://dx.doi.org/10.1140/epjb/e2004-00316-5}
}
@BOOK{Gospodnetic2005,
TITLE = {Lucene in Action},
PUBLISHER = {Manning},
YEAR = {2005},
AUTHOR = {Otis Gospodneti{\'c} and Erik Hatcher},
URL = {http://www.lucenebook.com/}
}
@ARTICLE{Granovetter1973,
AUTHOR = {Mark S. Granovetter},
TITLE = {The Strength of Weak Ties},
JOURNAL = {American Journal of Sociology},
YEAR = {1973},
VOLUME = {78},
PAGES = {1360--1380},
NUMBER = {6},
MONTH = MAY,
URL = {http://www.stanford.edu/dept/soc/people/faculty/granovetter/documents/TheStrengthofWeakTies.pdf}
}
@INPROCEEDINGS{Guha2004,
AUTHOR = {R. Guha and Ravi Kumar and Prabhakar Raghavan and Andrew Tomkins},
TITLE = {Propagation of trust and distrust},
BOOKTITLE = {WWW '04: Proceedings of the 13th international conference on World Wide Web},
YEAR = {2004},
PAGES = {403--412},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/988672.988727},
ISBN = {1-58113-844-X},
LOCATION = {New York, NY, USA}
}
@MASTERSTHESIS{Gul2004,
AUTHOR = {Nadir G{\"u}l},
TITLE = {{MyPush -- Ein kollaborativer Push Dienst f{\"u}r die
automatische Informationsbeschaffung in einem Peer-to-Peer Netzwerk}},
SCHOOL = {Rheinische Friedrich-Wilhelms-Universit{\"a}t Bonn},
YEAR = {2004},
TYPE = {Diploma thesis},
MONTH = MAR
}
@BOOK{Hamming1980,
TITLE = {Coding and information theory},
PUBLISHER = {Prentice-Hall},
YEAR = {1980},
AUTHOR = {Richard W. Hamming},
ADDRESS = {Englewood Cliffs},
ISBN = {0-13-139139-9}
}
@ARTICLE{Hanley1982,
AUTHOR = {J. A. Hanley and B. J. McNeil},
TITLE = {The meaning and use of
the area under a receiver operating characteristic ({ROC}) curve.},
JOURNAL = {Radiology},
YEAR = {1982},
VOLUME = {143},
PAGES = {29-36},
NUMBER = {1},
MONTH = APR,
ABSTRACT = {A representation and interpretation of the area
under a receiver operating characteristic (ROC) curve obtained by the
"rating" method, or by mathematical predictions based on patient
characteristics, is presented. It is shown that in such a setting
the area represents the probability that a randomly chosen diseased
subject is (correctly) rated or ranked with greater suspicion than a
randomly chosen non-diseased subject. Moreover, this probability
of a correct ranking is the same quantity that is estimated by the
already well-studied nonparametric Wilcoxon statistic. These two
relationships are exploited to (a) provide rapid closed-form expressions
for the approximate magnitude of the sampling variability, i.e.,
standard error that one uses to accompany the area under a smoothed
ROC curve, (b) guide in determining the size of the sample required
to provide a sufficiently reliable estimate of this area, and (c)
determine how large sample sizes should be to ensure that one can
statistically detect differences in the accuracy of diagnostic techniques.},
KEYWORDS = {Evaluation Studies, Humans, Mathematics, Models, Theoretical, Research
Support, Non-U.S. Gov't, Statistics, Technology, Radiologic, 7063747},
OWNER = {skirsch},
URL = {http://www.med.mcgill.ca/epidemiology/hanley/software/Hanley_McNeil_Radiology_82.pdf}
}
@INPROCEEDINGS{Harman1988,
AUTHOR = {D. Harman},
TITLE = {Towards interactive query expansion},
BOOKTITLE = {SIGIR '88: Proceedings of the 11th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1988},
PAGES = {321--331},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/62437.62469},
ISBN = {2-7061-0309-4},
LOCATION = {Grenoble, France}
}
@INPROCEEDINGS{Harman1992,
AUTHOR = {Donna Harman},
TITLE = {Relevance feedback revisited},
BOOKTITLE = {SIGIR '92: Proceedings of the 15th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1992},
PAGES = {1--10},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/133160.133167},
ISBN = {0-89791-523-2},
LOCATION = {Copenhagen, Denmark}
}
@TECHREPORT{Haveliwala1999,
AUTHOR = {Taher Haveliwala},
TITLE = {Efficient Computation of {P}age{R}ank},
INSTITUTION = {Stanford University},
YEAR = {1999},
MONTH = OCT,
ABSTRACT = {This paper discusses e cient techniques for computing PageRank, a ranking met- ric for
hypertext documents. We show that PageRank can be computed for very
large subgraphs of the web (up to hundreds of millions of nodes) on
machines with limited main memory. Running-time measurements on various
memory con gurations are presented for PageRank computation over the
24-million-page Stanford WebBase archive. We discuss several methods
for analyzing the con- vergence of PageRank based on the induced
ordering of the pages. We present convergence results helpful for
determining the number of iterations necessary to achieve a useful
PageRank assignment, both in the absence and presence of search queries.},
KEYWORDS = {PageRank, search engine, link structure},
URL = {http://dbpubs.stanford.edu/pub/1999-31}
}
@INPROCEEDINGS{Haveliwala2002,
AUTHOR = {Taher H. Haveliwala},
TITLE = {Topic-sensitive {P}age{R}ank},
BOOKTITLE = {WWW '02: Proceedings of the eleventh international conference on World Wide Web},
YEAR = {2002},
PAGES = {517--526},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/511446.511513},
ISBN = {1-58113-449-5},
LOCATION = {Honolulu, Hawaii, USA}
}
@INPROCEEDINGS{Haveliwala2002a,
AUTHOR = {Taher H. Haveliwala and Aristides Gionis and Dan Klein and Piotr Indyk},
TITLE = {Evaluating strategies for similarity search on the web},
BOOKTITLE = {WWW '02: Proceedings of the 11th international conference on World Wide Web},
YEAR = {2002},
PAGES = {432--442},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/511446.511502},
ISBN = {1-58113-449-5},
LOCATION = {Honolulu, Hawaii, USA}
}
@ARTICLE{Hayes2003,
AUTHOR = {Brian Hayes},
TITLE = {A Lucid Interval},
JOURNAL = {American Scientist},
YEAR = {2003},
VOLUME = {91},
PAGES = {484--488},
NUMBER = {6},
MONTH = NOV # {--} # DEC,
URL = {http://www.cs.utep.edu/interval-comp/hayes.pdf}
}
@INPROCEEDINGS{Hearst1996,
AUTHOR = {Marti A. Hearst and Jan O. Pedersen},
TITLE = {Reexamining the cluster hypothesis: scatter/gather on retrieval results},
BOOKTITLE = {SIGIR '96: Proceedings of the 19th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1996},
PAGES = {76--84},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/243199.243216},
ISBN = {0-89791-792-8},
LOCATION = {Zurich, Switzerland}
}
@INPROCEEDINGS{Herlocker2000,
AUTHOR = {Jonathan L. Herlocker and Joseph A. Konstan and John Riedl},
TITLE = {Explaining collaborative filtering recommendations},
BOOKTITLE = {CSCW '00: Proceedings
of the 2000 ACM conference on Computer supported cooperative work},
YEAR = {2000},
PAGES = {241--250},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/358916.358995},
ISBN = {1-58113-222-0},
LOCATION = {Philadelphia, Pennsylvania, United States}
}
@INPROCEEDINGS{142751,
AUTHOR = {William C. Hill and James D. Hollan and Dave Wroblewski and Tim McCandless},
TITLE = {Edit wear and read wear},
BOOKTITLE = {CHI '92: Proceedings of the SIGCHI conference on Human factors in computing systems},
YEAR = {1992},
PAGES = {3--9},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/142750.142751},
ISBN = {0-89791-513-5},
LOCATION = {Monterey, California, United States}
}
@ARTICLE{Holland1970,
AUTHOR = {Paul W. Holland and Samuel Leinhardt},
TITLE = {A Method for Detecting Structure in Sociometric Data},
JOURNAL = {American Journal of Sociology},
YEAR = {1970},
VOLUME = {76},
PAGES = {492--513},
NUMBER = {3},
MONTH = NOV
}
@INCOLLECTION{Huberman2004,
AUTHOR = {Bernardo A. Huberman and Lada A. Adamic},
TITLE = {Information Dynamics in the Networked World},
BOOKTITLE = {Complex Networks},
PUBLISHER = {Springer},
YEAR = {2004},
EDITOR = {Eli Ben-Naim and Hans Frauenfelder and Zoltan Toroczkai},
VOLUME = {650},
SERIES = {Lecture Notes in Physics},
PAGES = {371--398},
ISBN = {3-540-22354-1},
URL = {http://www.hpl.hp.com/research/idl/papers/infodynamics/index.html}
}
@ARTICLE{Huberman1998,
AUTHOR = {Bernardo A. Huberman
and Peter L. T. Pirolli and James E. Pitkow and Rajan M. Lukose},
TITLE = {Strong Regularities in World Wide Web Surfing},
JOURNAL = {Science},
YEAR = {1998},
VOLUME = {280},
PAGES = {95--97},
NUMBER = {5360},
MONTH = APR,
ABSTRACT = {One of the most common modes of accessing information in the World
Wide Web is surfing from one document to another along hyperlinks.
Several large empirical studies have revealed common patterns of
surfing behavior. A model that assumes that users make a sequence of
decisions to proceed to another page, continuing as long as the value
of the current page exceeds some threshold, yields the probability
distribution for the number of pages that a user visits within a given
Web site. This model was verified by comparing its predictions with
detailed measurements of surfing patterns. The model also explains the
observed Zipf-like distributions in page hits observed at Web sites.},
DOI = {10.1126/science.280.5360.95},
URL = {http://www.sciencemag.org/cgi/reprint/280/5360/95.pdf}
}
@ARTICLE{Janson1993,
AUTHOR = {Svante Janson and Donald E. Knuth and Tomasz {\L}uczak and Boris Pittel},
TITLE = {The Birth of the Giant Component},
JOURNAL = {Random Structures \& Algorithms},
YEAR = {1993},
VOLUME = {4},
PAGES = {233--358},
NUMBER = {3},
URL = {http://arxiv.org/pdf/math.PR/9310236}
}
@ARTICLE{Jones2000,
AUTHOR = {K. Spärck Jones and S. Walker and S. E. Robertson},
TITLE = {A probabilistic model of information retrieval, Part 1},
JOURNAL = {Information Processing and Management},
YEAR = {2000},
VOLUME = {36},
PAGES = {779--808},
URL = {http://www.soi.city.ac.uk/~ser/blockbuster/pmir-pt1-reprint.pdf}
}
@ARTICLE{Jones2000a,
AUTHOR = {K. Spärck Jones and S. Walker and S. E. Robertson},
TITLE = {A probabilistic model of information retrieval, Part 2},
JOURNAL = {Information Processing and Management},
YEAR = {2000},
VOLUME = {36},
PAGES = {809--840},
URL = {http://www.soi.city.ac.uk/~ser/blockbuster/pmir-pt2-reprint.pdf}
}
@INPROCEEDINGS{Kamvar2003,
AUTHOR = {Sepandar D. Kamvar and Mario T. Schlosser and Hector Garcia-Molina},
TITLE = {The Eigentrust algorithm for reputation management in P2P networks},
BOOKTITLE = {WWW '03: Proceedings of the 12th international conference on World Wide Web},
YEAR = {2003},
PAGES = {640--651},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/775152.775242},
ISBN = {1-58113-680-3},
LOCATION = {Budapest, Hungary},
URL = {http://www.stanford.edu/~sdkamvar/papers/eigentrust.pdf}
}
@INPROCEEDINGS{Kantor1996,
AUTHOR = {Paul B. Kantor and Ellen M. Voorhees},
TITLE = {Report on the {TREC}-5 Confusion Track},
BOOKTITLE = {Proceedings of the Fifth {T}ext {RE}trieval {C}onference {TREC}-5},
YEAR = {1996},
EDITOR = {E. M. Voorhees and D. K. Harman},
NUMBER = {500-238},
SERIES = {NIST Special Publications},
ORGANIZATION = {U.S. National Institute of Standards and Technology (NIST)},
URL = {http://trec.nist.gov/pubs/trec5/papers/confusion_track.ps.gz}
}
@ARTICLE{Kautz1997,
AUTHOR = {Henry Kautz and Bart Selman and Mehul Shah},
TITLE = {Referral Web: combining social networks and collaborative filtering},
JOURNAL = {Commununications of the ACM},
YEAR = {1997},
VOLUME = {40},
PAGES = {63--65},
NUMBER = {3},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/245108.245123},
ISSN = {0001-0782},
KEYWORDS = {expert finding, expert location, world wide web, referrals},
PUBLISHER = {ACM Press}
}
@ARTICLE{Kautz1997a,
AUTHOR = {Henry Kautz and Bart Selman and Mehul Shah},
TITLE = {The Hidden Web},
JOURNAL = {{AI} Magazine},
YEAR = {1997},
VOLUME = {18},
PAGES = {27--36},
NUMBER = {2},
KEYWORDS = {expert finding, expert location, world wide web, referrals},
URL = {http://www.cs.washington.edu/homes/kautz/referralweb/doc/aimag.pdf}
}
@INPROCEEDINGS{Kleinberg2000,
AUTHOR = {Jon Kleinberg},
TITLE = {The small-world phenomenon: an algorithm perspective},
BOOKTITLE = {STOC '00: Proceedings
of the thirty-second annual ACM symposium on Theory of computing},
YEAR = {2000},
PAGES = {163--170},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/335305.335325},
ISBN = {1-58113-184-4},
LOCATION = {Portland, Oregon, United States}
}
@INPROCEEDINGS{Kleinberg1999a,
AUTHOR = {Jon Kleinberg and Andrew Tomkins},
TITLE = {Applications of linear algebra in information retrieval and hypertext analysis},
BOOKTITLE = {PODS '99: Proceedings of the eighteenth ACM
SIGMOD-SIGACT-SIGART symposium on Principles of database systems},
YEAR = {1999},
PAGES = {185--193},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/303976.303995},
ISBN = {1-58113-062-7},
LOCATION = {Philadelphia, Pennsylvania, United States}
}
@ARTICLE{Kleinberg2000a,
AUTHOR = {Jon M. Kleinberg},
TITLE = {Navigation in a small world},
JOURNAL = {Nature},
YEAR = {2000},
VOLUME = {406},
PAGES = {845},
MONTH = AUG,
DOI = {http://dx.doi.org/10.1038/35022643},
URL = {http://www.nature.com/nature/journal/v406/n6798/abs/406845a0_fs.html}
}
@ARTICLE{Kleinberg1999,
AUTHOR = {Jon M. Kleinberg},
TITLE = {Authoritative sources in a hyperlinked environment},
JOURNAL = {Journal of the ACM},
YEAR = {1999},
VOLUME = {46},
PAGES = {604--632},
NUMBER = {5},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/324133.324140},
ISSN = {0004-5411},
PUBLISHER = {ACM Press}
}
@ARTICLE{Knuth1974,
AUTHOR = {Donald E. Knuth},
TITLE = {Computer programming as an art},
JOURNAL = {Commun. ACM},
YEAR = {1974},
VOLUME = {17},
PAGES = {667--673},
NUMBER = {12},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/361604.361612},
ISSN = {0001-0782},
PUBLISHER = {ACM Press}
}
@MISC{Kong2005,
AUTHOR = {Joseph S. Kong and P. Oscar Boykin
and Behnam A. Rezaei and Nima Sarshar and Vwani P. Roychowdhury},
TITLE = {Let Your {C}yber{A}lter Ego Share Information and Manage Spam},
HOWPUBLISHED = {Preprint},
YEAR = {2005},
ABSTRACT = {Almost all of us have
multiple cyberspace identities, and these {\em cyber}alter egos are
networked together to form a vast cyberspace social network. This network
is distinct from the world-wide-web (WWW), which is being queried
and mined to the tune of billions of dollars everyday, and until
recently, has gone largely unexplored. Empirically, the cyberspace social
networks have been found to possess many of the same complex features
that characterize its real counterparts, including scale-free degree
distributions, low diameter, and extensive connectivity. We show that
these topological features make the latent networks particularly
suitable for explorations and management via local-only messaging
protocols. {\em Cyber}alter egos can communicate via their direct
links (i.e., using only their own address books) and set up a highly
decentralized and scalable message passing network that can allow large-scale
sharing of information and data. As one particular example of such
collaborative systems, we provide a design of a spam filtering system, and
our large-scale simulations show that the system achieves a spam
detection rate close to 100%, while the false positive rate is kept
around zero. This system has several advantages over other recent
proposals (i) It uses an already existing network, created by the
same social dynamics that govern our daily lives, and no dedicated
peer-to-peer (P2P) systems or centralized server-based systems need be
constructed; (ii) It utilizes a percolation search algorithm that makes the
query-generated traffic scalable; (iii) The network has a built in
trust system (just as in social networks) that can be used to thwart
malicious attacks; iv) It can be implemented right now as a plugin to
popular email programs, such as MS Outlook, Eudora, and Sendmail.},
KEYWORDS = {Physics and Society; Disordered Systems and Neural
Networks; Computers and Society; Networking and Internet Architecture},
URL = {http://xxx.lanl.gov/abs/physics/0504026}
}
@ARTICLE{Konstan1997,
AUTHOR = {Joseph A. Konstan and Bradley N. Miller and David
Maltz and Jonathan L. Herlocker and Lee R. Gordon and John Riedl},
TITLE = {{G}roup{L}ens: applying collaborative filtering to {U}senet news},
JOURNAL = {Communications of the ACM},
YEAR = {1997},
VOLUME = {40},
PAGES = {77--87},
NUMBER = {3},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/245108.245126},
ISSN = {0001-0782},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{Kraaij2002,
AUTHOR = {Wessel Kraaij and Thijs Westerveld and Djoerd Hiemstra},
TITLE = {The Importance of Prior Probabilities for Entry Page Search},
BOOKTITLE = {SIGIR '02: Proceedings of the 25th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {2002},
PAGES = {27--34},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/564376.564383},
ISBN = {1-58113-561-0},
LOCATION = {Tampere, Finland},
URL = {http://db.cs.utwente.nl/Publications/PaperStore/db-utwente-0000003211.pdf}
}
@INPROCEEDINGS{Kumar1999,
AUTHOR = {Ravi Kumar and Prabhakar Raghavan and Sridhar Rajagopalan and Andrew Tomkins},
TITLE = {Trawling the Web for emerging cyber-communities},
BOOKTITLE = {WWW '99: Proceeding of the eighth international conference on World Wide Web},
YEAR = {1999},
PAGES = {1481--1493},
ADDRESS = {New York, NY, USA},
PUBLISHER = {Elsevier North-Holland, Inc.},
DOI = {http://dx.doi.org/10.1016/S1389-1286(99)00040-7},
LOCATION = {Toronto, Canada},
URL = {http://scholar.google.com/url?sa=U&q=http://www8.org/w8-papers/4a-search-mining/trawling/trawling.html}
}
@BOOK{Lancaster1968,
TITLE = {Information Retrieval Systems: Characteristics, Testing, and Evaluation},
PUBLISHER = {Wiley},
YEAR = {1968},
AUTHOR = {F. W. Lancaster},
ADDRESS = {New York}
}
@ARTICLE{Langville2005,
AUTHOR = {Amy N. Langville and Carl D. Meyer},
TITLE = {A Survey of Eigenvector Methods for Web Information Retrieval},
JOURNAL = {SIAM Review},
YEAR = {2005},
VOLUME = {47},
PAGES = {135--161},
NUMBER = {1},
MONTH = FEB,
URL = {http://epubs.siam.org/sam-bin/getfile/SIREV/articles/42478.pdf}
}
@MISC{Lawson2005,
AUTHOR = {Mark Lawson},
TITLE = {{B}erners-{L}ee on the read/write web},
HOWPUBLISHED = {broadcast by Newsnight on BBC Two},
MONTH = AUG,
YEAR = {2005},
NOTE = {Interview with Tim Berners-Lee},
URL = {http://news.bbc.co.uk/1/hi/technology/4132752.stm}
}
@ARTICLE{Lee1997,
AUTHOR = {Joon Ho Lee},
TITLE = {Analyses of multiple evidence combination},
JOURNAL = {SIGIR Forum},
YEAR = {1997},
VOLUME = {31},
PAGES = {267--276},
NUMBER = {SI},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/278459.258587},
ISBN = {0-89791-836-3},
ISSN = {0163-5840},
KEYWORDS = {data fusion},
PUBLISHER = {ACM Press}
}
@ARTICLE{Lehmann2003,
AUTHOR = {S. Lehmann and B. Lautrup and A. D. Jackson},
TITLE = {Citation networks in high energy physics.},
JOURNAL = {Physical Review E},
YEAR = {2003},
VOLUME = {68},
PAGES = {026113},
NUMBER = {2 Partt 2},
MONTH = AUG,
ABSTRACT = {The citation network constituted by the SPIRES
database is investigated empirically. The probability that a given paper
in the SPIRES database has k citations is well described by simple
power laws, P(k) proportional to k(-alpha), with alpha approximately
1.2 for k less than 50 citations and alpha approximately 2.3 for
50 or more citations. A consideration of citation distribution by
subfield shows that the citation patterns of high energy physics form a
remarkably homogeneous network. Further, we utilize the knowledge of
the citation distributions to demonstrate the extreme improbability
that the citation records of selected individuals and institutions
have been obtained by a random draw on the resulting distribution.},
DOI = {http://dx.doi.org/10.1103/PhysRevE.68.026113},
URL = {http://link.aps.org/abstract/PRE/v68/e026113}
}
@ARTICLE{Malone1987,
AUTHOR = {Thomas W. Malone and Kenneth R. Grant
and Franklyn A. Turbak and Stephen A. Brobst and Michael D. Cohen},
TITLE = {Intelligent information-sharing systems},
JOURNAL = {Commununications of the ACM},
YEAR = {1987},
VOLUME = {30},
PAGES = {390--402},
NUMBER = {5},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/22899.22903},
ISSN = {0001-0782},
PUBLISHER = {ACM Press}
}
@INCOLLECTION{Manber1992,
AUTHOR = {Udi Manber},
TITLE = {Foreword},
BOOKTITLE = {Information Retrieval. Data Structures \& Algorithms},
PUBLISHER = {Prentice Hall},
YEAR = {1992},
EDITOR = {William B. Frakes and Ricardo Baeza-Yates},
PAGES = {v--vi}
}
@INPROCEEDINGS{Masinter1993,
AUTHOR = {Larry Masinter and Erik Ostrom},
TITLE = {Collaborative Information Retrieval: {G}opher from {MOO}},
BOOKTITLE = {Proceedings of {INET} '93},
YEAR = {1993},
ABSTRACT = {There are two visions of how use
of the global network will evolve in the future First individuals
will use the network as a resource providing access to material from
libraries and other suppliers of information and entertainment Second
in addition to communicating with these data sources people will
communicate with each other using a variety of interactive text audio and
video conferencing methods This paper is about a system that combines
the two uses adding an information retrieval tool Gopher to a text
based virtual reality environment MOO The combination allows informal
collaboration using information retrieval to happen across the network},
CITESEERURL = {http://citeseer.ist.psu.edu/masinter93collaborative.html},
OWNER = {skirsch},
URL = {http://larry.masinter.net/MOOGopher.pdf}
}
@INPROCEEDINGS{Mattox1999,
AUTHOR = {David Mattox and Mark T. Maybury and Daryl Morey},
TITLE = {Enterprise expert and knowledge discovery},
BOOKTITLE = {Proceedings of the HCI International '99
(the 8th International Conference on Human-Computer Interaction)},
YEAR = {1999},
PAGES = {303--307},
ADDRESS = {Mahwah, NJ, USA},
PUBLISHER = {Lawrence Erlbaum Associates, Inc.},
ISBN = {0-8058-3392-7},
KEYWORDS = {expert location, expert finding},
URL = {http://www.mitre.org/work/tech_papers/tech_papers_00/maybury_enterprise/maybury_enterprise.pdf}
}
@ARTICLE{Maybury2001,
AUTHOR = {Mark Maybury and Ray D'Amore and David House},
TITLE = {Expert Finding for Collaborative Virtual Environments},
JOURNAL = {Commun. ACM},
YEAR = {2001},
VOLUME = {44},
PAGES = {55--56},
NUMBER = {12},
ADDRESS = {New York, NY, USA},
DOI = {http://dx.doi.org/10.1145/501338.501343},
ISSN = {0001-0782},
KEYWORDS = {expert finding, expert location},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{587096,
AUTHOR = {Sean M. McNee and Istvan Albert and Dan Cosley and Prateep Gopalkrishnan and Shyong
K. Lam and Al Mamunur Rashid and Joseph A. Konstan and John Riedl},
TITLE = {On the recommending of citations for research papers},
BOOKTITLE = {CSCW '02: Proceedings
of the 2002 ACM conference on Computer supported cooperative work},
YEAR = {2002},
PAGES = {116--125},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/587078.587096},
ISBN = {1-58113-560-2},
LOCATION = {New Orleans, Louisiana, USA}
}
@ARTICLE{Menczer2006,
AUTHOR = {Filippo Menczer and Santo Fortunato and Alessandro Flammini and Alessandro Vespignani},
TITLE = {{Googlearchy} or {Googlocracy}?},
JOURNAL = {IEEE Spectrum},
YEAR = {2006},
MONTH = FEB,
URL = {http://www.spectrum.ieee.org/feb06/2787}
}
@ARTICLE{Milgram1967,
AUTHOR = {Stanley Milgram},
TITLE = {The small-world problem},
JOURNAL = {Psychology Today},
YEAR = {1967},
VOLUME = {2},
PAGES = {60--67}
}
@INPROCEEDINGS{Miller1999,
AUTHOR = {David R. H. Miller and Tim Leek and Richard M. Schwartz},
TITLE = {A hidden Markov model information retrieval system},
BOOKTITLE = {SIGIR '99: Proceedings of the 22nd annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1999},
PAGES = {214--221},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/312624.312680},
ISBN = {1-58113-096-1},
LOCATION = {Berkeley, California, United States}
}
@MASTERSTHESIS{nadjafi1998virtuelle,
AUTHOR = {Nasim Ulrike Nadjafi},
TITLE = {{V}irtuelle {G}emeinschaften. {O}rganisation -- {I}nteraktion},
SCHOOL = {Ludwig-Maximilians-Universit{\"a}t M{\"unchen}},
YEAR = {1998}
}
@ARTICLE{Newman2001,
AUTHOR = {M. E. Newman},
TITLE = {The structure of scientific collaboration networks},
JOURNAL = {Proceedings of the National Academy of Sciences of the United States of America},
YEAR = {2001},
VOLUME = {98},
PAGES = {404-409},
NUMBER = {2},
MONTH = JAN,
ABSTRACT = {The structure of scientific collaboration
networks is investigated. Two scientists are considered connected if
they have authored a paper together and explicit networks of such
connections are constructed by using data drawn from a number of
databases, including MEDLINE (biomedical research), the Los Alamos e-Print
Archive (physics), and NCSTRL (computer science). I show that these
collaboration networks form "small worlds," in which randomly chosen
pairs of scientists are typically separated by only a short path of
intermediate acquaintances. I further give results for mean and distribution
of numbers of collaborators of authors, demonstrate the presence
of clustering in the networks, and highlight a number of apparent
differences in the patterns of collaboration between the fields studied.},
DOI = {10.1073/pnas.021544898},
KEYWORDS = {Authorship, Bibliographic,
Bibliometrics, Cluster Analysis, Cooperative Behavior, Databases,
Humans, MEDLINE, Models, Non-P.H.S., Non-U.S. Gov't, Research, Research
Personnel, Research Support, Science, Theoretical, U.S. Gov't, 11149952},
PII = {021544898},
URL = {http://dx.doi.org/10.1073/pnas.021544898}
}
@ARTICLE{Newman2001a,
AUTHOR = {M. E. Newman},
TITLE = {Clustering and preferential attachment in growing networks.},
JOURNAL = {Physical Review E (Statistics, Nonlinear, and Soft Matter Physics)},
YEAR = {2001},
VOLUME = {64},
PAGES = {025102},
NUMBER = {2 Pt 2},
MONTH = {Aug},
ABSTRACT = {We study empirically the
time evolution of scientific collaboration networks in physics and
biology. In these networks, two scientists are considered connected if
they have coauthored one or more papers together. We show that the
probability of a pair of scientists collaborating increases with
the number of other collaborators they have in common, and that the
probability of a particular scientist acquiring new collaborators
increases with the number of his or her past collaborators. These results
provide experimental evidence in favor of previously conjectured
mechanisms for clustering and power-law degree distributions in networks.},
DOI = {http://dx.doi.org/10.1103/PhysRevE.64.025102},
URL = {http://link.aps.org/abstract/PRE/v64/e025102}
}
@ARTICLE{Newman2005,
AUTHOR = {M. E. J. Newman},
TITLE = {Power laws, Pareto distributions and Zipf's law},
JOURNAL = {Contemporary Physics},
YEAR = {2005},
VOLUME = {46},
PAGES = {323--351},
NUMBER = {5},
MONTH = SEP,
ABSTRACT = {When the probability of measuring a particular
value of some quantity varies inversely as a power of that value,
the quantity is said to follow a power law, also known variously
as Zipf's law or the Pareto distribution. Power laws appear widely
in physics, biology, earth and planetary sciences, economics and
finance, computer science, demography and the social sciences. For
instance, the distributions of the sizes of cities, earthquakes,
solar flares, moon craters, wars and people's personal fortunes all
appear to follow power laws. The origin of power-law behaviour has
been a topic of debate in the scientific community for more than
a century. Here we review some of the empirical evidence for the
existence of power-law forms and the theories proposed to explain them.},
DOI = {http://dx.doi.org/10.1080/00107510500052444},
URL = {http://arxiv.org/abs/cond-mat/0412004}
}
@ARTICLE{Newman2004,
AUTHOR = {M. E. J. Newman},
TITLE = {Coauthorship networks and patterns of scientific collaboration.},
JOURNAL = {Proc Natl Acad Sci U S A},
YEAR = {2004},
VOLUME = {101 Suppl 1},
PAGES = {5200-5},
MONTH = {Apr},
ABSTRACT = {By using data from three bibliographic databases in biology, physics, and
mathematics, respectively, networks are constructed in which the
nodes are scientists, and two scientists are connected if they have
coauthored a paper. We use these networks to answer a broad variety of
questions about collaboration patterns, such as the numbers of papers
authors write, how many people they write them with, what the typical
distance between scientists is through the network, and how patterns of
collaboration vary between subjects and over time. We also summarize a
number of recent results by other authors on coauthorship patterns.},
DOI = {10.1073/pnas.0307545100},
KEYWORDS = {Authorship, Models, Neural Networks (Computer), Non-P.H.S., Non-U.S. Gov't,
Periodicals, Research Support, Statistical, U.S. Gov't, 14745042},
PII = {0307545100},
URL = {http://dx.doi.org/10.1073/pnas.0307545100}
}
@ARTICLE{Newman2003a,
AUTHOR = {M. E. J. Newman},
TITLE = {Properties of highly clustered networks},
JOURNAL = {Physical Review E},
YEAR = {2003},
VOLUME = {68},
PAGES = {026121},
MONTH = AUG,
ABSTRACT = {We propose and solve exactly a model of a
network that has both a tunable degree distribution and a tunable
clustering coefficient. Among other things, our results indicate that
increased clustering leads to a decrease in the size of the giant
component of the network. We also study susceptible/infective/recovered
type epidemic processes within the model and find that clustering
decreases the size of epidemics, but also decreases the epidemic
threshold, making it easier for diseases to spread. In addition,
clustering causes epidemics to saturate sooner, meaning that they infect a
near-maximal fraction of the network for quite low transmission rates.},
URL = {http://link.aps.org/abstract/PRE/v68/e026121}
}
@TECHREPORT{Newman2002a,
AUTHOR = {M. E. J. Newman},
TITLE = {Random Graphs as Models of Networks},
INSTITUTION = {Santa Fe Institute},
YEAR = {2002},
TYPE = {Working Papers},
NUMBER = {02-02-005},
MONTH = FEB,
URL = {http://www.santafe.edu/research/publications/workingpapers/02-02-005.pdf}
}
@INCOLLECTION{Newman2003,
AUTHOR = {Newman, M. E. J. and Girvan, M.},
TITLE = {Mixing Patterns and Community Structure in Networks},
BOOKTITLE = {Statistical Mechanics of Complex Networks},
PUBLISHER = {Springer},
YEAR = {2003},
EDITOR = {Romualdo Pastor-Satorras and Miguel Rubi and Albert Diaz-Guilera},
VOLUME = {625},
SERIES = {Lecture Notes in Physics},
PAGES = {66--87},
MONTH = JAN,
JOURNAL = {Lecture Notes in Physics},
URL = {http://www.springerlink.com/openurl.asp?genre=article&id=UP95B47KKR8P5MFH}
}
@ARTICLE{Newman2004a,
AUTHOR = {M. E. J. Newman and M. Girvan},
TITLE = {Finding and evaluating community structure in networks.},
JOURNAL = {Phys Rev E Stat Nonlin Soft Matter Phys},
YEAR = {2004},
VOLUME = {69},
PAGES = {026113},
NUMBER = {2 Pt 2},
MONTH = {Feb},
ABSTRACT = {We propose and study a set of algorithms for
discovering community structure in networks-natural divisions of network
nodes into densely connected subgroups. Our algorithms all share two
definitive features: first, they involve iterative removal of edges from
the network to split it into communities, the edges removed being
identified using any one of a number of possible "betweenness" measures,
and second, these measures are, crucially, recalculated after each
removal. We also propose a measure for the strength of the community
structure found by our algorithms, which gives us an objective metric for
choosing the number of communities into which a network should be
divided. We demonstrate that our algorithms are highly effective
at discovering community structure in both computer-generated and
real-world network data, and show how they can be used to shed light on
the sometimes dauntingly complex structure of networked systems.}
}
@ARTICLE{newman2003why,
AUTHOR = {M. E. J. Newman and Juyong Park},
TITLE = {Why social networks are different from other types of networks},
JOURNAL = {Physical Review E},
YEAR = {2003},
VOLUME = {68},
PAGES = {036122},
MONTH = SEP,
DOI = {10.1103/PhysRevE.68.036122},
ISSUE = {3 Pt 2},
KEYWORDS = {social networks},
URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&list_uids=14524847}
}
@ARTICLE{Newman2001b,
AUTHOR = {M. E. J. Newman and S. H. Strogatz and D. J. Watts},
TITLE = {Random graphs with arbitrary degree distributions and their applications},
JOURNAL = {Physical Review E},
YEAR = {2001},
VOLUME = {64},
PAGES = {026118},
DOI = {http://dx.doi.org/10.1103/PhysRevE.64.026118},
URL = {http://link.aps.org/abstract/PRE/v64/e026118}
}
@ARTICLE{Newman2002,
AUTHOR = {M. E. J. Newman and D. J. Watts and S. H. Strogatz},
TITLE = {Random graph models of social networks},
JOURNAL = {Proc Natl Acad Sci U S A},
YEAR = {2002},
VOLUME = {99 Suppl. 1},
PAGES = {2566-2572},
MONTH = FEB,
ABSTRACT = {We describe some new exactly solvable models of the structure
of social networks, based on random graphs with arbitrary degree
distributions. We give models both for simple unipartite networks, such as
acquaintance networks, and bipartite networks, such as affiliation networks.
We compare the predictions of our models to data for a number of
real-world social networks and find that in some cases, the models
are in remarkable agreement with the data, whereas in others the
agreement is poorer, perhaps indicating the presence of additional social
structure in the network that is not captured by the random graph.},
DOI = {10.1073/pnas.012582999},
KEYWORDS = {Biological, Humans, Models, Non-P.H.S.,
Non-U.S. Gov't, Research Support, Social Support, U.S. Gov't, 11875211},
PII = {99/suppl_1/2566},
URL = {http://dx.doi.org/10.1073/pnas.012582999}
}
@INPROCEEDINGS{Ng2001,
AUTHOR = {Andrew Y. Ng and Alice X. Zheng and Michael I. Jordan},
TITLE = {Stable algorithms for link analysis},
BOOKTITLE = {SIGIR '01: Proceedings of the 24th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {2001},
PAGES = {258--266},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/383952.384003},
ISBN = {1-58113-331-6},
LOCATION = {New Orleans, Louisiana, United States}
}
@ARTICLE{North2000,
AUTHOR = {Klaus North and Kai Romhardt and Gilbert Probst},
TITLE = {{W}issensgemeinschaften. {K}eimzellen lebendigen {W}issensmanagements},
JOURNAL = {io management},
YEAR = {2000},
VOLUME = {7/8},
PAGES = {52--62},
OWNER = {skirsch},
URL = {http://know.unige.ch/publications/CoP-Artikel%20im%20ioMgt.PDF}
}
@ARTICLE{Nuutila1993,
AUTHOR = {Esko Nuutila and Eljas Soisalon-Soininen},
TITLE = {On finding the strongly connected components in a directed graph},
JOURNAL = {Information Processing Letters},
YEAR = {1993},
VOLUME = {49},
PAGES = {9--14},
URL = {http://www.cs.hut.fi/%7Eenu/ps/ipl-scc.ps}
}
@ARTICLE{OMadadhain,
AUTHOR = {Joshua O'Madadhain and
Danyel Fisher and Padhraic Smyth and Scott White and Yan-Biao Boey},
TITLE = {Analysis and Visualization of Network Data using {JUNG}},
JOURNAL = {Journal of Statistical Software},
YEAR = {2005},
NOTE = {To appear.},
ABSTRACT = {The JUNG (Java Universal
Network/Graph) Framework is a free, open-source software library
that provides a common and extendible language for the manipulation,
analysis, and visualization of data that can be represented as a
graph or network. It is written in the Java programming language,
allowing JUNG-based applications to make use of the extensive built-in
capabilities of the Java Application Programming Interface (API),
as well as those of other existing third-party Java libraries. We
describe the design, and some details of the implementation, of the
JUNG architecture, and provide illustrative examples of its use.},
URL = {http://jung.sourceforge.net/doc/JUNG_journal.pdf}
}
@ARTICLE{Oard1997,
AUTHOR = {Douglas W. Oard},
TITLE = {The State of the Art in Text Filtering},
JOURNAL = {User Modeling and User-Adapted Interaction},
YEAR = {1997},
VOLUME = {7},
PAGES = {141--178},
NUMBER = {3},
ABSTRACT = {This paper develops a conceptual framework for text filtering practice and
research, and reviews present practice in the field. Text filtering is an
information seeking process in which documents are selected from a dynamic
text stream to satisfy a relatively stable and specific information
need. A model of the information seeking process is introduced and
specialized to define text filtering. The historical development of
text filtering is then reviewed and case studies of recent work are
used to highlight important design characteristics of modern text
filtering systems. User modeling techniques drawn frominformation
retrieval, recommender systems,machine learning and other fields are
described. The paper concludes with observations on the present state
of the art and implications for future research on text filtering.},
ADDRESS = {Hingham, MA, USA},
DOI = {http://dx.doi.org/10.1023/A:1008287121180},
ISSN = {0924-1868},
KEYWORDS = {Information filtering, Text
retrieval, Social filtering, Collaborative, Content-based, Selective
Dissemination of Information, Current awareness, Recommender systems},
PUBLISHER = {Kluwer Academic Publishers},
URL = {http://portal.acm.org/citation.cfm?id=598306}
}
@INPROCEEDINGS{Ogilvie2003,
AUTHOR = {Paul Ogilvie and Jamie Callan},
TITLE = {Combining document representations for known-item search},
BOOKTITLE = {SIGIR '03: Proceedings of the 26th annual international ACM
SIGIR conference on Research and development in informaion retrieval},
YEAR = {2003},
PAGES = {143--150},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/860435.860463},
ISBN = {1-58113-646-3},
LOCATION = {Toronto, Canada}
}
@MISC{USPTO6285999,
AUTHOR = {Lawrence Page},
TITLE = {Method for node ranking in a linked database},
HOWPUBLISHED = {U.\,S.\ Patent 6,285,999},
MONTH = SEP,
YEAR = {2001},
NOTE = {Assignee: The Board of
Trustees of the Leland Stanford Junior University (Stanford, CA)},
ABSTRACT = {A method assigns importance ranks to nodes in a linked database, such as any
database of documents containing citations, the world wide web or
any other hypermedia database. The rank assigned to a document is
calculated from the ranks of documents citing it. In addition, the
rank of a document is calculated from a constant representing the
probability that a browser through the database will randomly jump to
the document. The method is particularly useful in enhancing the
performance of search engine results for hypermedia databases, such as the
world wide web, whose documents have a large variation in quality.},
URL = {http://patft.uspto.gov/netacgi/nph-Parser?Sect2=PTO1&Sect2=HITOFF&p=1&u=%2Fnetahtml%2Fsearch-bool.html&r=1&f=G&l=50&d=PALL&RefSrch=yes&Query=PN%2F6285999}
}
@TECHREPORT{Page1999,
AUTHOR = {Lawrence Page and Sergey Brin and Rajeev Motwani and Terry Winograd},
TITLE = {The {P}age{R}ank Citation Ranking: Bringing Order to the {Web}},
INSTITUTION = {Stanford University},
YEAR = {1999},
MONTH = NOV,
ABSTRACT = {The importance of a Web page is an
inherently subjective matter, which depends on the readers interests,
knowledge and attitudes. But there is still much that can be said
objectively about the relative importance of Web pages. This paper
describes PageRank, a mathod for rating Web pages objectively and
mechanically, effectively measuring the human interest and attention devoted
to them. We compare PageRank to an idealized random Web surfer. We
show how to efficiently compute PageRank for large numbers of pages.
And, we show how to apply PageRank to search and to user navigation.},
CITESEERURL = {http://citeseer.ist.psu.edu/page98pagerank.html},
OWNER = {skirsch},
URL = {http://dbpubs.stanford.edu:8090/pub/1999-66}
}
@INPROCEEDINGS{Pandurangan2002,
AUTHOR = {Gopal Pandurangan and Prabhakar Raghavan and Eli Upfal},
TITLE = {Using {P}age{R}ank to Characterize Web Structure},
BOOKTITLE = {COCOON '02: Proceedings of the
8th Annual International Conference on Computing and Combinatorics},
YEAR = {2002},
NUMBER = {2387},
SERIES = {Lecture Notes in Computer Science},
PAGES = {330--339},
ADDRESS = {London, UK},
PUBLISHER = {Springer-Verlag},
ISBN = {3-540-43996-X}
}
@INPROCEEDINGS{Pandurangan2002a,
AUTHOR = {Gopal Pandurangan and Prabhakar Raghavan and Eli Upfal},
TITLE = {Using PageRank to Characterize Web Structure},
BOOKTITLE = {COCOON '02: Proceedings of the
8th Annual International Conference on Computing and Combinatorics},
YEAR = {2002},
PAGES = {330--339},
ADDRESS = {London, UK},
PUBLISHER = {Springer-Verlag},
ISBN = {3-540-43996-X},
URL = {http://www.cs.purdue.edu/homes/gopal/prankfinal.pdf}
}
@ARTICLE{Perlis1982,
AUTHOR = {Alan J. Perlis},
TITLE = {Epigrams in Programming},
JOURNAL = {ACM SIGPLAN Notices},
YEAR = {1982},
VOLUME = {17},
PAGES = {7--13},
NUMBER = {9},
MONTH = SEP,
COMMENT = {Another version is at
http://www.bio.cam.ac.uk/~mw263/Perlis_Epigrams.html; it is not available via the ACM Digital Library.},
ISSN = {0362-1340},
URL = {http://www-pu.informatik.uni-tuebingen.de/users/klaeren/epigrams.html}
}
@ARTICLE{Pinski1976,
AUTHOR = {Gabriel Pinski and Francis Narin},
TITLE = {Citation influence for journal aggregates of scientific
publications: Theory, with application to the literature of physics},
JOURNAL = {Information Processing and Management},
YEAR = {1976},
VOLUME = {12},
PAGES = {297--312},
NUMBER = {5},
ABSTRACT = {A self-consistent methodology is developed for determining citation based influence
measures for scientific journals, subfields and fields. Starting
with the cross citing matrix between journals or between aggregates
of journals, an eigenvalue problem is formulated leading to a size
independent influence weight for each journal or aggregate. Two other
measures, the influence per publication and the total influence are
then defined. Hierarchical influence diagrams and numerical data are
presented to display journal interrelationships for journals within the
subfields of physics. A wide range in influence is found between
the most influential and least influential or peripheral journals.},
DOI = {http://dx.doi.org/10.1016/0306-4573(76)90048-0}
}
@INPROCEEDINGS{Pirolli1996,
AUTHOR = {Peter Pirolli and James Pitkow and Ramana Rao},
TITLE = {Silk from a sow's ear: extracting usable structures from the {Web}},
BOOKTITLE = {CHI '96: Proceedings of the SIGCHI conference on Human factors in computing systems},
YEAR = {1996},
PAGES = {118--125},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
ABSTRACT = {In its current implementation, the
World-Wide Web lacks much of the explicit structure and strong typing
found in many closed hypertext systems. While this property probably
relates to the explosive acceptance of the Web, it further complicates
the already difficult problem of identifying usable structures and
aggregates in large hypertext collections. These reduced structures, or
localities, form the basis for simplifying visualizations of and navigation
through complex hypertext systems. Much of the previous research into
identifying aggregates utilize graph theoretic algorithms based upon
structural topology, i.e., the linkages between items. Other research
has focused on content analysis to form document collections. This
paper presents our exploration into techniques that utilize both the
topology and textual similarity between items as well as usage data
collected by servers and page meta-information lke title and size. Linear
equations and spreading activation models are employed to arrange Web
pages based upon functional categories, node types, and relevancy.},
DOI = {http://doi.acm.org/10.1145/238386.238450},
ISBN = {0-89791-777-4},
KEYWORDS = {Information Visualization, World Wide Web, Hypertext, spreading activation},
LOCATION = {Vancouver, British Columbia, Canada},
URL = {http://www.pitkow.com/docs/1996-CHI-Silk.pdf}
}
@ARTICLE{Pitkow2002,
AUTHOR = {James Pitkow and Hinrich Schütze and Todd Cass and Rob Cooley
and Don Turnbull and Andy Edmonds and Eytan Adar and Thomas Breuel},
TITLE = {Personalized search},
JOURNAL = {Commununications of the ACM},
YEAR = {2002},
VOLUME = {45},
PAGES = {50--55},
NUMBER = {9},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/567498.567526},
ISSN = {0001-0782},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{Ponte1998,
AUTHOR = {Jay M. Ponte and W. Bruce Croft},
TITLE = {A language modeling approach to information retrieval},
BOOKTITLE = {SIGIR '98: Proceedings of the 21st annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1998},
PAGES = {275--281},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/290941.291008},
ISBN = {1-58113-015-5},
LOCATION = {Melbourne, Australia}
}
@PHDTHESIS{Preece1981,
AUTHOR = {Scott Everett Preece},
TITLE = {A Spreading Activation Network Model for Information Retrieval},
SCHOOL = {University of Illinois at Urbana-Champaign},
YEAR = {1981},
URL = {http://wwwlib.umi.com/dissertations/fullcit/8203555}
}
@INCOLLECTION{Quillian1968,
AUTHOR = {M. Ross Quillian},
TITLE = {Semantic Memory},
BOOKTITLE = {Semantic Information Processing},
PUBLISHER = {MIT Press},
YEAR = {1968},
EDITOR = {Marvin Minsky},
ADDRESS = {Cambridge, Mass.},
COMMENT = {Semantic information processing / Marvin Minsky, ed. Cambridge, Mass. (u.a.) : MIT
Pr., 1968. VIII, 440 S. : graph. Darst. Schlagwoerter: Kuenstliche
Intelligenz * Semantik * Aufsatzsammlung Philosophisches Seminar /
Lehr- und Forschungsbereich III (Sigel 5/158) Signatur: IKs 68/750}
}
@ARTICLE{Quillian1969,
AUTHOR = {M. Ross Quillian},
TITLE = {The teachable language comprehender: a simulation program and theory of language},
JOURNAL = {Commun. ACM},
YEAR = {1969},
VOLUME = {12},
PAGES = {459--476},
NUMBER = {8},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/363196.363214},
ISSN = {0001-0782},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{Resnick1994,
AUTHOR = {Paul Resnick and Neophytos Iacovou and Mitesh Suchak and Peter Bergstrom and John Riedl},
TITLE = {{G}roup{L}ens: an open architecture for collaborative filtering of netnews},
BOOKTITLE = {CSCW '94: Proceedings
of the 1994 ACM conference on Computer supported cooperative work},
YEAR = {1994},
PAGES = {175--186},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/192844.192905},
ISBN = {0-89791-689-1},
LOCATION = {Chapel Hill, North Carolina, United States}
}
@BOOK{Rijsbergen1979,
TITLE = {Information Retrieval},
PUBLISHER = {Butterworths},
YEAR = {1979},
AUTHOR = {C. J. {v}an Rijsbergen},
OWNER = {skirsch},
URL = {http://www.dcs.gla.ac.uk/Keith/Preface.html}
}
@INPROCEEDINGS{Robertson1981,
AUTHOR = {S. E. Robertson and C. J. van Rijsbergen and M. F. Porter},
TITLE = {Probabilistic models of indexing and searching},
BOOKTITLE = {SIGIR '80: Proceedings of the 3rd annual ACM
conference on Research and development in information retrieval},
YEAR = {1981},
PAGES = {35--56},
ADDRESS = {Kent, UK},
PUBLISHER = {Butterworth \& Co.},
ISBN = {0-408-10775-8},
LOCATION = {Cambridge, England}
}
@INPROCEEDINGS{Robertson1994,
AUTHOR = {S. E. Robertson and S. Walker},
TITLE = {Some simple effective
approximations to the 2-Poisson model for probabilistic weighted retrieval},
BOOKTITLE = {SIGIR '94: Proceedings of the 17th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1994},
PAGES = {232--241},
ADDRESS = {New York, NY, USA},
PUBLISHER = {Springer-Verlag New York, Inc.},
ISBN = {0-387-19889-X},
LOCATION = {Dublin, Ireland}
}
@INPROCEEDINGS{Robertson1995,
AUTHOR = {S. E. Robertson and S. Walker and S. Jones and M. M. Hancock-Beaulieu and M. Gatford},
TITLE = {Okapi at TREC-3},
BOOKTITLE = {Proceceedings of the Third {T}ext {RE}trieval {C}onference ({TREC}-3)},
YEAR = {1995},
EDITOR = {D. K. Harman},
NUMBER = {500-226},
SERIES = {{NIST} Special Publications},
PAGES = {109--126},
ORGANIZATION = {U.S. National Institute of Standards and Technology (NIST)},
KEYWORDS = {BM25},
LOCATION = {Washington, D.C., United States},
URL = {http://trec.nist.gov/pubs/trec3/papers/city.ps.gz}
}
@INPROCEEDINGS{Robertson2004,
AUTHOR = {S.E. Robertson and H. Zaragoza and M. Taylor},
TITLE = {Simple {BM25} Extension to Multiple Weighted Fields},
BOOKTITLE = {Thirteenth Conference on Information and Knowledge Management (CIKM)},
YEAR = {2004},
URL = {http://research.microsoft.com/users/cambridge/hugoz/pubs/ps/robertson_cikm04.zip}
}
@INPROCEEDINGS{Romano1999,
AUTHOR = {Romano, Jr, Nicholas C.
and Roussinov, Dmitri and Nunamaker, Jr, Jay F. and Chen, Hsinchun},
TITLE = {Collaborative Information Retrieval Environment:
Integration of Information Retrieval with Group Support Systems},
BOOKTITLE = {HICSS '99: Proceedings of the Thirty-Second
Annual Hawaii International Conference on System Sciences-Volume 1},
YEAR = {1999},
PAGES = {1053--1062},
ADDRESS = {Washington, DC, USA},
PUBLISHER = {IEEE Computer Society},
ABSTRACT = {Observations of Information
Retrieval (IR) system user experiences reveal strong desires for
collaborative search efforts; however the same user experiences suggest that
collaborative capabilities are rarely, and then only in a limited
fashion, supported by current tools for searching and visualizing query
results. Equally interesting is the fact that observations of user
experiences with Group Support Systems (GSS) reveal that access to
external information and the ability to search for relevant material
is often vital to the progress of GSS sessions, however these same
user experiences suggest that integrated support for collaborative
searching and visualization of results is lacking in GSS systems. After
reviewing user experiences described in both IR and GSS literature and
observing and interviewing users of existing IR and GSS commercial
and prototype systems, the Author's conclude that the demand for
systems supporting multi-user IR is obvious. It is surprising to the
Authors that very little attention has been given to the common ground
shared by these two important research domains. With this in mind, Our
paper describes how user experiences with IR and GSS systems has shed
light onto a promising new area of collaborative research and led to
the development of a prototype that merges the two paradigms into
a Collaborative Information Retrieval Environment (CIRE). Finally
the paper presents theory developed from initial user experiences
with our prototype and describes our plans to empirically test the
efficacy of this new paradigm through controlled experimentation.},
ISBN = {0-7695-0001-3}
}
@INPROCEEDINGS{Root1988,
AUTHOR = {Robert W. Root},
TITLE = {Design of a multi-media vehicle for social browsing},
BOOKTITLE = {CSCW '88: Proceedings
of the 1988 ACM conference on Computer-supported cooperative work},
YEAR = {1988},
PAGES = {25--38},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
ABSTRACT = {In this paper we present a new approach to the use of
computer-mediated communications technology to support distributed
cooperative work. In contrast to most of the existing approaches to
CSCW, we focus explicitly on tools to enable unplanned, informal
social interaction. We describe a ?social interface? which provides
direct, low-cost access to other people through the use of multi-media
communications channels. The design of the system centers around
three basic concepts derived from the research literature and our own
observations of the workplace: social browsing, a virtual workplace, and
interaction protocols. We use these design properties to describe a
new system concept, and examine the implications for CSCW of having
automated social interaction available through the desktop workstation.},
DOI = {http://doi.acm.org/10.1145/62266.62269},
ISBN = {0-89791-282-9},
LOCATION = {Portland, Oregon, United States}
}
@MASTERSTHESIS{Ruhl2003,
AUTHOR = {Thorsten Ruhl},
TITLE = {{Personal Search Memory -- Design und Realisierung einer Suchschnittstelle
zur kombinierten Suche in fr{\"u}heren und neuen Suchergebnissen}},
SCHOOL = {Rheinische Friedrich-Wilhelms-Universit{\"a}t Bonn},
YEAR = {2003},
TYPE = {Diploma thesis},
ABSTRACT = {Die Zielsetzung der vorliegenden Arbeit ist das
Design und die Realisierung einer Suchschnittstelle, mit der eine
kombinierte Suche in früheren und neuen Suchergebnissen möglich ist. Das
Suchinterface soll dabei dem Benutzer die Möglichkeit geben, durch das
Setzen und Speichern von Assoziationen zwischen Suchanfragen und
Suchergebnissen, sein persönliches externes Suchgedächtnis aufzubauen.
Ferner sollen alle Suchanfragen mitprotokolliert und die Erweiterungen
und Modifikationen der Anfragen entsprechend den Vorstellungen von
Bush [Bush, 1945] in Suchpfaden abgelegt werden. Der Bedarf an einem
personalisierten Suchinterface wird dadurch bekräftigt, dass die konventionellen
Suchmaschinen ihre Ergebnislisten unabhängig vom Benutzer erzeugen und viele
irrelevante Treffer zurückliefern. Außerdem erweist sich die Rückkehr
zu bekannten Dokumenten nicht immer als einfach. Die Grundlage für
das Suchinterfacedesign bildet die Festlegung der Anwendungsfälle
und die Analyse der Anforderungen an das System. Es wurden dabei
folgende vier Anwendungsfälle festgelegt: 1) Mit dem Suchinterface soll
nach Informationen gesucht werden können, 2) die Webdokumente der
Suchergebnisse sollen angezeigt werden können, 3) die Suchergebnisse
sollen bewertet werden können und 4) die Daten der aufgenommenen
Anfrage-Resultat-Assoziationen sollen geändert werden können. Zu Beginn wurde eine
Anforderungsanalyse an einigen Probanden durchgeführt. Allgemein kann gesagt
werden, dass die Probanden eine einfache und schnelle Installation des
Suchinterfaces, keine Beschränkung des Benutzers auf Browser oder
Plattform und eine natürliche und einfache Bedienung fordern. Darüber
hinaus hatte jeder Proband eine andere Vorstellung darüber, was das
Suchinterface nach seinen Wünschen nach leisten sollte. Im späteren
Design des Suchinterfaces wurde eine Auswahl der Benutzerwünsche
getroffen, die in dem Prototyp realisiert wurden. Anhand der festgelegten
Anwendungsfälle wurde das Konzept des Suchinterfaces entworfen, das aus
mehreren Komponenten besteht. Zu diesen Komponenten gehören z.B. die
personalisierte Suchmaschine, die nach früheren Resultaten im persönlichen
Suchgedächtnis des Benutzers sucht, und die Datenbank, die das Suchgedächtnis
des Benutzers darstellt. Diese Komponenten wurden näher untersucht
und Empfehlungen für die Realisierung im Prototyp gegeben. Für die
personalisierte Suche wurden neue Rankingalgorithmen entwickelt und neue
Relevanzwerte definiert, die die Daten des persönlichen Suchgedächtnisses
nutzen. Eine weitere Komponente des Konzepts ist die Visualisierung
von Suchergebnissen. Hier wurde für die kombinierte Suche eine neue
Darstellungsform auf der Metapher der Mengen entworfen und einer
kritischen Bewertung unterzogen. Im Vergleich mit Konzepten ähnlicher
Systeme konnte unter anderem festgestellt werden, dass diese sich beim
Setzen eines Lesezeichens auf eine Webseite nicht zusätzlich das
zugehörige Informationsbedürfnis merken und somit nicht dem Ansatz von
Anfrage-Resultat-Assoziationen folgen. Ferner hat keines der Systeme eine Suchhistorie, in der
der Benutzer einen strukturierten Verlauf seiner Suchanfragen sehen
kann. Auf der Basis der Anwendungsfälle und unter der Forderung,
dass sich das Suchinterface ohne zusätzlichen Arbeitsaufwand in den
täglichen Suchprozess des Benutzers integrieren lässt, wurde das
entwickelte Suchinterface-Konzept als Prototyp realisiert. Ferner wurde
darauf geachtet, dass sich das Suchinterface in einen beliebigen
Webbrowser integrieren lässt und Plattformunabhängigkeit bietet. Die
Evaluation des realisierten Prototyps rundet die Arbeit ab. Sie wurde
mit der Thinking-aloud Methode an Testpersonen mit verschiedenen
Fachkenntnissen im Bereich Suchdienste und Recherchesystemen durchgeführt.}
}
@ARTICLE{Salton1963,
AUTHOR = {Gerard Salton},
TITLE = {Associative Document Retrieval Techniques Using Bibliographic Information},
JOURNAL = {Journal of the ACM},
YEAR = {1963},
VOLUME = {10},
PAGES = {440--457},
NUMBER = {4},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/321186.321188},
ISSN = {0004-5411},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{Salton1988,
AUTHOR = {Gerard Salton and Chris Buckley},
TITLE = {On the Use of Spreading Activation Methods in Automatic Information Retrieval},
BOOKTITLE = {Proceedings of the ACM SIGIR},
YEAR = {1988},
ADDRESS = {Grenoble, France},
MONTH = JUN,
ABSTRACT = {Spreading activation methods have been recommended in information
retrieval to expand the search vocabulary and to complement the retrieved
document sets. The spreading activation strategy is reminiscent of
earlier associative indexing and retrieval systems. Some spreading
activation procedures briefly described, and evaluation output is
given, reflecting the effectiveness of one of the proposed procedures.},
KEYWORDS = {spreading activation},
OWNER = {skirsch},
URL = {http://doi.acm.org/10.1145/62437.62447}
}
@ARTICLE{Salton1988a,
AUTHOR = {Gerard Salton and Chris Buckley},
TITLE = {Term-weighting approaches in automatic information retrieval},
JOURNAL = {Information Processing and Management},
YEAR = {1988},
VOLUME = {24},
PAGES = {513--523},
NUMBER = {5}
}
@ARTICLE{163402,
AUTHOR = {Michael F. Schwartz and David C. M. Wood},
TITLE = {Discovering shared interests using graph analysis},
JOURNAL = {Commun. ACM},
YEAR = {1993},
VOLUME = {36},
PAGES = {78--89},
NUMBER = {8},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/163381.163402},
ISSN = {0001-0782},
KEYWORDS = {expert finding, expert location, graph analysis},
PUBLISHER = {ACM Press}
}
@BOOK{Scott1991,
TITLE = {Social Network Analysis. A Handbook},
PUBLISHER = {SAGE Publications},
YEAR = {1991},
AUTHOR = {John Scott},
ADDRESS = {London},
ISBN = {0-8039-8481-2},
OWNER = {skirsch}
}
@MASTERSTHESIS{Shah1997,
AUTHOR = {Mehul Shah},
TITLE = {{R}eferral{W}eb: A Resource Location System Guided By Personal Relations},
SCHOOL = {Massachusetts Institute of Technology},
YEAR = {1997},
TYPE = {Master's thesis},
MONTH = MAY
}
@ARTICLE{Silverstein1999,
AUTHOR = {Craig Silverstein and Hannes Marais and Monika Henzinger and Michael Moricz},
TITLE = {Analysis of a very large web search engine query log},
JOURNAL = {SIGIR Forum},
YEAR = {1999},
VOLUME = {33},
PAGES = {6--12},
NUMBER = {1},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/331403.331405},
ISSN = {0163-5840},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{Singhal1996,
AUTHOR = {Amit Singhal and Chris Buckley and Mandar Mitra},
TITLE = {Pivoted document length normalization},
BOOKTITLE = {SIGIR '96: Proceedings of the 19th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1996},
PAGES = {21--29},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/243199.243206},
ISBN = {0-89791-792-8},
LOCATION = {Zurich, Switzerland}
}
@ARTICLE{Smeaton2002,
AUTHOR = {Alan F. Smeaton and Gary Keogh and Cathal Gurrin and Kieran McDonald and Tom S{\o}dring},
TITLE = {Analysis of papers from twenty-five years of {SIGIR}
conferences: {W}hat have we been doing for the last quarter of a century?},
JOURNAL = {SIGIR Forum},
YEAR = {2002},
VOLUME = {36},
PAGES = {39--43},
NUMBER = {2},
ABSTRACT = {As part of the celebration of twenty-five years of ACM SIGIR
conferences we performed a content analysis of all papers published in the
proceedings of SIGIR conferences, including those from 2002. From this we
determined, using information retrieval approaches of course, which
topics had come and gone over the last two and a half decades, and
which topics are currently ?hot?. We also performed a co-authorship
analysis among authors of the 853 SIGIR conference papers to determine
which author is the most ?central? in terms of a co-authorship graph
and is our equivalent of Paul Erdös in Mathematics. In the first
section we report on the content analysis, leading to our prediction
as to the most topical paper likely to appear at SIGIR2003. In the
second section we present details of our co-authorship analysis,
revealing who is the ?Christopher Lee? of SIGIR, and in the final section
we give pointers to where readers who are SIGIR conference paper
authors may find details of where they fit into the coauthorship graph.},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/792550.792556},
ISSN = {0163-5840},
PUBLISHER = {ACM Press},
URL = {http://portal.acm.org/citation.cfm?id=792556}
}
@ARTICLE{Strogatz2001,
AUTHOR = {Steven H. Strogatz},
TITLE = {Exploring complex networks},
JOURNAL = {Nature},
YEAR = {2001},
VOLUME = {410},
PAGES = {268--276},
MONTH = MAR,
DOI = {http://dx.doi.org/10.1038/35065725}
}
@MISC{Sturgeon1958,
AUTHOR = {Theodore Sturgeon},
HOWPUBLISHED = {Venture Science Fiction},
MONTH = MAR,
YEAR = {1958},
COMMENT = {Probable source for Sturgeon's Law ("Ninety percent of everything is crud.")}
}
@INPROCEEDINGS{Turtle1990,
AUTHOR = {H. Turtle and W. B. Croft},
TITLE = {Inference networks for document retrieval},
BOOKTITLE = {SIGIR '90: Proceedings of the 13th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1990},
PAGES = {1--24},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/96749.98006},
ISBN = {0-89791-408-2},
LOCATION = {Brussels, Belgium}
}
@INPROCEEDINGS{Tyler2003,
AUTHOR = {Joshua R. Tyler and Dennis M. Wilkinson and Bernardo A. Huberman},
TITLE = {Email as spectroscopy:
automated discovery of community structure within organizations},
BOOKTITLE = {Proceedings of the Communities and Technologies (C\&T 2003) International Conference},
YEAR = {2003},
PAGES = {81--96},
ADDRESS = {Deventer, The Netherlands, The Netherlands},
PUBLISHER = {Kluwer, B.V.},
ISBN = {1-4020-1611-5}
}
@ARTICLE{Upstill2003,
AUTHOR = {Trystan Upstill and Nick Craswell and David Hawking},
TITLE = {Query-independent evidence in home page finding},
JOURNAL = {ACM Trans. Inf. Syst.},
YEAR = {2003},
VOLUME = {21},
PAGES = {286--313},
NUMBER = {3},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/858476.858479},
ISSN = {1046-8188},
PUBLISHER = {ACM Press}
}
@INPROCEEDINGS{Voorhees1995,
AUTHOR = {Ellen M. Voorhees and Narendra K. Gupta and Ben Johnson-Laird},
TITLE = {Learning collection fusion strategies},
BOOKTITLE = {SIGIR '95: Proceedings of the 18th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1995},
PAGES = {172--179},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/215206.215357},
ISBN = {0-89791-714-6},
KEYWORDS = {data fusion},
LOCATION = {Seattle, Washington, United States}
}
@ARTICLE{Watts1998,
AUTHOR = {Watts, Duncan J. and Strogatz, Steven H.},
TITLE = {Collective dynamics of `small-world' networks},
JOURNAL = {Nature},
YEAR = {1998},
VOLUME = {393},
PAGES = {440--442},
MONTH = JUN,
ISSN = {0028-0836},
URL = {http://dx.doi.org/10.1038/30918}
}
@ARTICLE{Weiss2005,
AUTHOR = {Aaron Weiss},
TITLE = {The power of collective intelligence},
JOURNAL = {netWorker},
YEAR = {2005},
VOLUME = {9},
PAGES = {16--23},
NUMBER = {3},
ADDRESS = {New York, NY, USA},
DOI = {http://doi.acm.org/10.1145/1086762.1086763},
ISSN = {1091-3556},
PUBLISHER = {ACM Press}
}
@ARTICLE{Wenger1998,
AUTHOR = {Etienne Wenger},
TITLE = {Communities of practice: Learning as a social system},
JOURNAL = {Systems Thinker},
YEAR = {1998},
VOLUME = {9},
NUMBER = {5},
OWNER = {skirsch},
URL = {http://www.ewenger.com/pub/pub_systems_thinker_wrd.doc}
}
@ARTICLE{Wenger1996,
AUTHOR = {Etienne Wenger},
TITLE = {How we learn. {C}ommunities of practice. {T}he social fabric of a learning organization.},
JOURNAL = {Healthcare Forum Journal},
YEAR = {1996},
VOLUME = {39},
PAGES = {20-26},
NUMBER = {4},
KEYWORDS = {Education, Continuing, Humans,
Learning, Models, Educational, Nurse-Patient Relations, Organizational
Culture, Problem Solving, Social Environment, United States, 10158755},
OWNER = {skirsch},
URL = {http://www.ewenger.com/pub/pubhealthcareforum.htm}
}
@INPROCEEDINGS{Westerveld2001,
AUTHOR = {Thijs Westerveld and Wessel Kraaij and Djoerd Hiemstra},
TITLE = {Retrieving Web Pages using Content, Links, URLs and Anchors},
BOOKTITLE = {Proceedings of the Tenth {T}ext {RE}trieval {C}onference {TREC}-10},
YEAR = {2001},
EDITOR = {E. M. Voorhees and D. K. Harman},
NUMBER = {500-250},
SERIES = {NIST Special Publications},
PAGES = {663--672},
ORGANIZATION = {U.S. National Institute of Standards and Technology (NIST)},
URL = {http://trec.nist.gov/pubs/trec10/papers/TNO-UTwente-trec10-final.pdf}
}
@INPROCEEDINGS{White2003,
AUTHOR = {Scott White and Padhraic Smyth},
TITLE = {Algorithms for estimating relative importance in networks},
BOOKTITLE = {KDD '03: Proceedings of the ninth ACM SIGKDD
international conference on Knowledge discovery and data mining},
YEAR = {2003},
PAGES = {266--275},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
DOI = {http://doi.acm.org/10.1145/956750.956782},
ISBN = {1-58113-737-0},
LOCATION = {Washington, D.C.}
}
@ARTICLE{Wilson2005,
AUTHOR = {Richard C. Wilson and Edwin R. Hancock and Bin Luo},
TITLE = {Pattern Vectors from Algebraic Graph Theory},
JOURNAL = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
YEAR = {2005},
VOLUME = {27},
PAGES = {1112--1124},
NUMBER = {7},
MONTH = JUL,
DOI = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2005.145},
KEYWORDS = {Graph matching, graph features, spectral methods}
}
@INCOLLECTION{Wilson1994,
AUTHOR = {T. D. Wilson},
TITLE = {Information needs and uses: fifty years of progress},
BOOKTITLE = {Fifty years of information progress: a Journal of Documentation review},
PUBLISHER = {Aslib},
YEAR = {1994},
EDITOR = {B. C. Vickery},
PAGES = {15--51},
ADDRESS = {London},
OWNER = {skirsch},
URL = {http://informationr.net/tdw/publ/papers/1994FiftyYears.html}
}
@ARTICLE{Wilson1981,
AUTHOR = {T. D. Wilson},
TITLE = {On user studies and information needs},
JOURNAL = {Journal of Librarianship},
YEAR = {1981},
VOLUME = {37},
PAGES = {3--15},
NUMBER = {1},
OWNER = {skirsch},
URL = {http://informationr.net/tdw/publ/papers/1981infoneeds.html}
}
@ARTICLE{Wu2004,
AUTHOR = {Fang Wu and Bernardo A. Huberman and Lada A. Adamic and Joshua R. Tyler},
TITLE = {Information Flow in Social Groups},
JOURNAL = {Physica A},
YEAR = {2004},
VOLUME = {337},
PAGES = {327--335},
URL = {http://www.hpl.hp.com/research/idl/papers/flow/}
}
@INPROCEEDINGS{Xu1996,
AUTHOR = {Jinxi Xu and W. Bruce Croft},
TITLE = {Query expansion using local and global document analysis},
BOOKTITLE = {SIGIR '96: Proceedings of the 19th annual international ACM SIGIR
conference on Research and development in information retrieval},
YEAR = {1996},
PAGES = {4--11},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
ABSTRACT = {Automatic query expansion has long been
suggested as a technique for dealing with the fundamental issue of
word mismatch in information retrieval. A number of approaches to
ezpanrnion have been studied and, more recently, attention has focused on
techniques that analyze the corpus to discover word relationship (global
techniques) and those that analyze documents retrieved by the initial quer~
( local feedback). In this paper, we compare the effectiveness of
these approaches and show that, although global analysis haa some
advantages, local analysia is generally more effective. We also show that
using global analysis techniques, such as word contezt and phrase
structure, on the local aet of documents produces results that are
both more effective and more predictable than simple local feedback.},
DOI = {http://doi.acm.org/10.1145/243199.243202},
ISBN = {0-89791-792-8},
LOCATION = {Zurich, Switzerland}
}
@INPROCEEDINGS{Yamamoto2004,
AUTHOR = {Atsushi Yamamoto and
Daisuke Asahara and Tomoko Itao and Satoshi Tanaka and Tatsuya Suda},
TITLE = {Distributed Pagerank: A Distributed Reputation Model for Open Peer-to-Peer Networks},
BOOKTITLE = {SAINT-W '04: Proceedings of the 2004 Symposium
on Applications and the Internet-Workshops (SAINT 2004 Workshops)},
YEAR = {2004},
PAGES = {389},
ADDRESS = {Washington, DC, USA},
PUBLISHER = {IEEE Computer Society},
ABSTRACT = {This paper proposes a distributed reputation model for open peer-to-peer
networks called distributed pagerank. This model is motivated by the
observation that although pagerank has already satisfied the requirements
of reputation models, the centralized calculation of pagerank is
incompatible with peer-to-peer networks. Distributed pagerank is a
decentralized approach for calculating the pagerank of each peer by its
reputation, in which the relationship between peers is introduced as the
equivalent to the link between web pages. The distributed calculation of
pagerank is performed asynchronously by each peer as it communicates
with the other peers. The asynchronous calculation accomplishes both
demanding no extra messages for the calculation of pagerank and steadily
calculating an accurate pagerank of each peer even under the dynamic
topology of relationships. The result of the simulation has indicated
that the calculated pagerank value of each peer converges at the
original pagerank value under the static topology of relationships,
which is presumable under a dynamic topology. A fully implemented
application of distributed pagerank has also been presented, which
supports dynamic formation of communities with reputation ranking.},
ISBN = {0-7695-2050-2}
}
@ARTICLE{Yimam-Seid2003,
AUTHOR = {Dawit Yimam-Seid and Alfred Kobsa},
TITLE = {Expert Finding Systems for
Organizations: Problem and Domain Analysis and the {DEMOIR} Approach},
JOURNAL = {Journal of Organizational Computing and Electronic Commerce},
YEAR = {2003},
VOLUME = {13},
PAGES = {1--24},
NUMBER = {1},
ABSTRACT = {Computer systems that augment the process of finding the
right expert for a given problem in an organization or world-wide are
becoming feasible more than ever before, thanks to the prevalence of
corporate Intranets and the Internet. This paper investigates such
systems in two parts. We first explore the expert finding problem
in depth, review and analyze existing systems in this domain, and
suggest a domain model that can serve as a framework for design and
development decisions. Based on our analyses of the problem and solution
spaces, we then bring to light the gaps that remain to be addressed.
Finally, we present our approach called DEMOIR, which is a modular
architecture for expert finding systems that is based on a centralized
expertise modeling server while also incorporating decentralized
components for expertise information gathering and exploitation.},
KEYWORDS = {expert finding, expert location},
OWNER = {skirsch}
}
@INPROCEEDINGS{Yu2003,
AUTHOR = {Bin Yu and Munindar P. Singh},
TITLE = {Searching social networks},
BOOKTITLE = {AAMAS '03: Proceedings of the second
international joint conference on Autonomous agents and multiagent systems},
YEAR = {2003},
PAGES = {65--72},
ADDRESS = {New York, NY, USA},
PUBLISHER = {ACM Press},
ABSTRACT = {A referral system is a
multiagent system whose member agents are capable of giving and following
referrals. The specific cases of interest arise where each agent has a
user. The agents cooperate by giving and taking referrals so each
can better help its user locate relevant information. This use of
referrals mimics human interactions and can potentially lead to greater
effectiveness and efficiency than in single-agent systems. Existing
approaches consider what referrals may be given and treat the referring
process simply as path search in a static graph. By contrast, the
present approach understands referrals as arising in and influencing
dynamic social networks, where the agents act autonomously based on
local knowledge. This paper studies strategies using which agents may
search dynamic social networks. It evaluates the proposed approach
empirically for a community of AI scientists (partially derived from
bibliographic data). Further, it presents a prototype system that
assists users in finding other users in practical social networks.},
DOI = {http://doi.acm.org/10.1145/860575.860587},
ISBN = {1-58113-683-8},
KEYWORDS = {referrrals},
LOCATION = {Melbourne, Australia},
URL = {http://portal.acm.org/citation.cfm?id=860587}
}
@INPROCEEDINGS{Zhang2005,
AUTHOR = {Xiangmin Zhang and Yuelin Li},
TITLE = {An Exploratory Study on Knowledge Sharing in Information Retrieval},
BOOKTITLE = {Proceedings of the 38th
Annual Hawaii International Conference on System Sciences (HICSS'05)},
YEAR = {2005},
PAGES = {245pp},
PUBLISHER = {Computer Society Press},
DOI = {http://doi.ieeecomputersociety.org/10.1109/HICSS.2005.91},
URL = {http://csdl.computer.org/comp/proceedings/hicss/2005/2268/08/22680245c.pdf}
}
@MISC{DublinCore,
AUTHOR = {{Dublin Core Metadata Initiative}},
TITLE = {{DCMI Metadata Terms}},
HOWPUBLISHED = {\url{http://dublincore.org/documents/dcmi-terms/}},
YEAR = {2005}
}
@MISC{LiveJournalBots,
AUTHOR = {{Six Apart Ltd.}},
TITLE = {{L}ive{J}ournal Bot Policy},
HOWPUBLISHED = {\url{http://www.livejournal.com/bots/}},
MONTH = JAN,
YEAR = {2006}
}
@BOOK{Baader2003,
TITLE = {The Description Logic Handbook: Theory, Implementation and Applications},
PUBLISHER = {Cambridge University Press},
YEAR = {2003},
EDITOR = {Franz Baader and Diego Calvanese and
Deborah L. McGuinness and Daniele Nardi and Peter F. Patel-Schneider}
}
@BOOK{Bobrow1975,
TITLE = {Representation and Understanding},
PUBLISHER = {Academic Press},
YEAR = {1975},
EDITOR = {D. G. Bobrow and A. Collins},
ADDRESS = {New York},
ISBN = {0-12-108550-3}
}
@BOOK{Brachman1985,
TITLE = {Readings in Knowledge Representation},
PUBLISHER = {Morgan Kaufman},
YEAR = {1985},
EDITOR = {R. Brachman and H. Levesque},
ADDRESS = {Los Altos}
}
@BOOK{Frakes1992,
TITLE = {Information Retrieval. Data Structures \& Algorithms},
PUBLISHER = {Prentice Hall},
YEAR = {1992},
EDITOR = {William B. Frakes and Ricardo Baeza-Yates},
OWNER = {skirsch}
}
@BOOK{lueg2003,
TITLE = {From {U}senet to {C}o{W}ebs. Interacting with social information spaces},
PUBLISHER = {Springer},
YEAR = {2003},
EDITOR = {Christopher Lueg and Danyel Fisher},
ISBN = {1-85233-532-7},
OWNER = {skirsch}
}
@BOOK{Salton1971,
TITLE = {The Smart Retrieval System. Experiments in Automatic Document Processing},
PUBLISHER = {Prentice Hall Inc.},
YEAR = {1971},
EDITOR = {Gerard Salton},
ADDRESS = {Englewood Cliffs NJ},
OWNER = {skirsch}
}
@PROCEEDINGS{Sundheim1995,
TITLE = {MUC6 '95: Proceedings of the 6th conference on Message understanding},
YEAR = {1995},
EDITOR = {Beth Sundheim and Ralph Grishman},
ADDRESS = {Morristown, NJ, USA},
PUBLISHER = {Association for Computational Linguistics},
ISBN = {1-55860-402-2},
LOCATION = {Columbia, Maryland}
}
@PROCEEDINGS{TREC2004,
TITLE = {Proceedings of the Thirteenth {T}ext {RE}trieval {C}onference ({TREC} 2004)},
YEAR = {2004},
EDITOR = {E. M. Voorhees and Lori P. Buckland},
NUMBER = {500-261},
SERIES = {NIST Special Publications},
ADDRESS = {Gaithersburg, MD},
MONTH = NOV,
ORGANIZATION = {U.~S.\ National Institute of Standards and Technology},
URL = {http://trec.nist.gov/pubs/trec13/t13_proceedings.html}
}
@COMMENT{{jabref-meta: selector_journal:Artificial Intelligence Review;
Communications of the ACM;IEEE Transactions on Pattern Analysis and Ma
chine Intelligence;Information Processing and Management;Proceedings o
f the National Academy of Sciences of the United States of America;}}
@COMMENT{{jabref-meta: selector_keywords:community;i;information filter
ing;information retrieval;social networks;}}
@COMMENT{{jabref-meta: selector_publisher:1975;}}
@COMMENT{{jabref-meta: groupstree:(AllEntriesGroup:,KeywordGroup:iskodo
r\\\;keywords\\\;ISKODOR\\\;,KeywordGroup:spreading activation\\\;keyw
ords\\\;spreading activation\\\;,KeywordGroup:expert location\\\;keywo
rds\\\;expert location\\\;,KeywordGroup:social networks\\\;keywords\\
;social networks\\\;,KeywordGroup:data fusion\\\;keywords\\\;data fusi
on\\\;)}}
This file has been generated by bibtex2html 1.74