Tang, L. & Liu, H.: Community Detection and Mining in Social Media. 2010
[Volltext]
The past decade has witnessed the emergence of participatory Web and social media, bringing people together in many creative ways. Millions of users are playing, tagging, working, and socializing online, demonstrating new forms of collaboration, communication, and intelligence that were hardly imaginable just a short time ago. Social media also helps reshape business models, sway opinions and emotions, and opens up numerous possibilities to study human interaction and collective behavior in an unparalleled scale. This lecture, from a data mining perspective, introduces characteristics of social media, reviews representative tasks of computing with social media, and illustrates associated challenges. It introduces basic concepts, presents state-of-the-art algorithms with easy-to-understand examples, and recommends effective evaluation methods. In particular, we discuss graph-based community detection techniques and many important extensions that handle dynamic, heterogeneous networks in social media. We also demonstrate how discovered patterns of communities can be used for social media mining. The concepts, algorithms, and methods presented in this lecture can help harness the power of social media and support building socially-intelligent systems. This book is an accessible introduction to the study of community detection and mining in social media. It is an essential reading for students, researchers, and practitioners in disciplines and applications where social media is a key source of data that piques our curiosity to understand, manage, innovate, and excel.
This book is supported by additional materials, including lecture slides, the complete set of figures, key references, some toy data sets used in the book, and the source code of representative algorithms. The readers are encouraged to visit the book website for the latest information.
Table of Contents: Social Media and Social Computing / Nodes, Ties, and Influence / Community Detection and Evaluation / Communities in Heterogeneous Networks / Social Media Mining
@book{noauthororeditoryahoo,
author = {Tang, Lei and Liu, Huan},
title = {Community Detection and Mining in Social Media},
year = {2010},
url = {http://www.morganclaypool.com/doi/abs/10.2200/S00298ED1V01Y201009DMK003},
doi = {10.2200/S00298ED1V01Y201009DMK003},
keywords = {community, detection, lecture, media, social, toread},
abstract = {The past decade has witnessed the emergence of participatory Web and social media, bringing people together in many creative ways. Millions of users are playing, tagging, working, and socializing online, demonstrating new forms of collaboration, communication, and intelligence that were hardly imaginable just a short time ago. Social media also helps reshape business models, sway opinions and emotions, and opens up numerous possibilities to study human interaction and collective behavior in an unparalleled scale. This lecture, from a data mining perspective, introduces characteristics of social media, reviews representative tasks of computing with social media, and illustrates associated challenges. It introduces basic concepts, presents state-of-the-art algorithms with easy-to-understand examples, and recommends effective evaluation methods. In particular, we discuss graph-based community detection techniques and many important extensions that handle dynamic, heterogeneous networks in social media. We also demonstrate how discovered patterns of communities can be used for social media mining. The concepts, algorithms, and methods presented in this lecture can help harness the power of social media and support building socially-intelligent systems. This book is an accessible introduction to the study of community detection and mining in social media. It is an essential reading for students, researchers, and practitioners in disciplines and applications where social media is a key source of data that piques our curiosity to understand, manage, innovate, and excel.
This book is supported by additional materials, including lecture slides, the complete set of figures, key references, some toy data sets used in the book, and the source code of representative algorithms. The readers are encouraged to visit the book website for the latest information.
Table of Contents: Social Media and Social Computing / Nodes, Ties, and Influence / Community Detection and Evaluation / Communities in Heterogeneous Networks / Social Media Mining }
}
Manning, C. D.; Raghavan, P. & Schütze, H.: Introduction to Information Retrieval. Cambridge University Press, 2008
[Volltext]
@book{manning2008,
author = {Manning, C. D. and Raghavan, P. and Schütze, H.},
title = {Introduction to Information Retrieval},
publisher = {Cambridge University Press},
year = {2008},
url = {http://www-csli.stanford.edu/~hinrich/information-retrieval-book.html},
keywords = {books, buch, introduction, ir, lecture, standard, toread}
}
Lowd, D. & Meek, C.: Good Word Attacks on Statistical Spam Filters. (2005),
[Volltext]
@article{goodword2006lowd,
author = {Lowd, Daniel and Meek, Christopher},
title = {Good Word Attacks on Statistical Spam Filters},
booktitle = {Second Conference on Email and Anti-Spam (CEAS)},
address = {Palo Alto, CA},
year = {2005},
url = {http://www.cs.washington.edu/homes/lowd/ceas05lowd.pdf},
keywords = {2006, lecture, spam, email, kdd, application}
}
Boykin, P. & Roychowdhury, V.: Personal Email Networks: An Effective Anti-Spam Tool. , 2004
[Volltext]
@techreport{boykin04:_person_email_networ,
author = {Boykin, P.O. and Roychowdhury, V.},
title = {Personal Email Networks: An Effective Anti-Spam Tool},
year = {2004},
url = {http://arxiv.org/abs/cond-mat/0402143},
keywords = {2006, lecture, spam, email, kdd, application}
}
Carstensen, K.-U.; Eber, C.; Endriss, C.; Jekat, S.; Klabunde, R. & Langer, H. (Hrsg.): Computerlinguistik und Sprachtechnologie. Eine Einführung. Heidelberg: Spektrum Akademischer Verlag, 2004
[Volltext]
@book{carstensen04coling,,
title = {Computerlinguistik und Sprachtechnologie. Eine Einführung},
editor = {Carstensen, K.-U. and Eber, Ch. and Endriss, C. and Jekat, S. and Klabunde, R. and Langer, H.},
publisher = {Spektrum Akademischer Verlag},
address = {Heidelberg},
year = {2004},
url = {http://www.worldcat.org/wcpa/oclc/47812608?page=frame&url=http%3A%2F%2Fopac.bibliothek.uni-kassel.de%2FDB%3D23%2FSET%3D1%2FTTL%3D1%2FCMD%3FACT%3DSRCHA%3FIKT%3D7%26SRT%3DYOP%26TRM%3D3827410274&title=Univ+Gesamthochschule+Kassel&linktype=opac&detail=DEUBK%3AUniv+Gesamthochschule+Kassel%3AAcademic},
keywords = {einführung, introduction, lecture, nlp}
}
Ferber, R.: Information Retrieval: Suchmodelle und Data-Mining-Verfahren für Textsammlungen und das Web. Heidelberg: dpunkt Verlag, 2003
[Volltext]
@book{ferber2003information,
author = {Ferber, Reginald},
title = {Information Retrieval: Suchmodelle und Data-Mining-Verfahren für Textsammlungen und das Web},
publisher = {dpunkt Verlag},
address = {Heidelberg},
year = {2003},
url = {http://information-retrieval.de/},
keywords = {information, ir, lecture, mining, retrieval, standard, vorlesung}
}
MacKay, D. J. C.: Information Theory, Inference, and Learning Algorithms. (2003),
[Volltext]
@article{MacKay2003,
author = {MacKay, David J. C.},
title = {Information Theory, Inference, and Learning Algorithms},
year = {2003},
url = {http://www.inference.phy.cam.ac.uk/mackay/itila/},
isbn = {9780521642989},
keywords = {2006, learning, lecture, kdd, algorithm}
}
Berkhin, P.: Survey Of Clustering Data Mining Techniques. San Jose, CA, 2002
[Volltext]
@techreport{berkhin02survey,
author = {Berkhin, Pavel},
title = {Survey Of Clustering Data Mining Techniques},
address = {San Jose, CA},
year = {2002},
url = {http://citeseer.ist.psu.edu/berkhin02survey.html},
keywords = {clustering, 2006, lecture, survey, kdd}
}
Sarwar, B. M.; Karypis, G.; Konstan, J. A. & Riedl, J.: Item-based collaborative filtering recommendation algorithms.. WWW. 2001, S. 285-295
[Volltext]
@inproceedings{conf/www/SarwarKKR01,
author = {Sarwar, Badrul M. and Karypis, George and Konstan, Joseph A. and Riedl, John},
title = {Item-based collaborative filtering recommendation algorithms.},
booktitle = {WWW},
year = {2001},
pages = {285-295},
url = {http://www10.org/cdrom/papers/pdf/p519.pdf},
keywords = {collaborative, filtering, ir, lecture, recommender, seminar2006}
}
Baeza-Yates, R. A. & Ribeiro-Neto, B. A.: Modern Information Retrieval. ACM Press / Addison-Wesley, 1999
[Volltext]
@book{books/aw/Baeza-YatesR99,
author = {Baeza-Yates, Ricardo A. and Ribeiro-Neto, Berthier A.},
title = {Modern Information Retrieval},
publisher = {ACM Press / Addison-Wesley},
year = {1999},
url = {http://www.ischool.berkeley.edu/~hearst/irbook/glossary.html},
isbn = {0-201-39829-X},
keywords = {information, ir, lecture, retrieval, standard, vorlesung}
}
Manning, C. D. & Schütze, H.: Foundations of Statistical Natural Language Processing. Cambridge, Massachusetts: The MIT Press, 1999
[Volltext]
@book{manning99foundations,
author = {Manning, Christopher D. and Schütze, Hinrich},
title = {Foundations of Statistical Natural Language Processing},
publisher = {The MIT Press},
address = {Cambridge, Massachusetts},
year = {1999},
url = {http://nlp.stanford.edu/fsnlp/},
keywords = {lecture, nlp}
}
Witten, I. H.; Moffat, A. & Bell, T. C.: Managing Gigabytes: Compressing and Indexing Documents and Images, Second Edition. Morgan Kaufmann, 1999
[Volltext]
@book{books/mk/WittenMB99,
author = {Witten, Ian H. and Moffat, Alistair and Bell, Timothy C.},
title = {Managing Gigabytes: Compressing and Indexing Documents and Images, Second Edition},
publisher = {Morgan Kaufmann},
year = {1999},
url = {http://www.cs.mu.oz.au/mg/},
isbn = {1-55860-570-3},
keywords = {advanced, ir, lecture}
}
Ng, R. T.; Lakshmanan, L. V. S.; Han, J. & Pang, A.: Exploratory Mining and Pruning Optimizations of Constrained Association Rules.. SIGMOD Conference. 1998, S. 13-24
[Volltext]
@inproceedings{conf/sigmod/NgLHP98,
author = {Ng, Raymond T. and Lakshmanan, Laks V. S. and Han, Jiawei and Pang, Alex},
title = {Exploratory Mining and Pruning Optimizations of Constrained Association Rules.},
booktitle = {SIGMOD Conference},
year = {1998},
pages = {13-24},
url = {http://dblp.uni-trier.de/db/conf/sigmod/sigmod98.html#NgLHP98},
keywords = {2006, lecture, rules, association, constraints, kdd, mining}
}
Charniak, E.: Statistical Techniques for Natural Language Parsing. In: AI Magazine 18 (1997), Nr. 4, S. 33-44
[Volltext]
@article{charniak97statistical,
author = {Charniak, Eugene},
title = {Statistical Techniques for Natural Language Parsing},
journal = {AI Magazine},
year = {1997},
volume = {18},
number = {4},
pages = {33-44},
url = {http://citeseer.ist.psu.edu/article/charniak97statistical.html},
keywords = {learning, lecture, model, nlp, tagging, taggingsurvey}
}
Brachman, R. J. & Anand, T.: The Process of Knowledge Discovery in Databases.. Advances in Knowledge Discovery and Data Mining. 1996, S. 37-57
[Volltext]
@incollection{books/mit/fayyadPSU96/BrachmanA96,
author = {Brachman, Ronald J. and Anand, Tej},
title = {The Process of Knowledge Discovery in Databases.},
booktitle = {Advances in Knowledge Discovery and Data Mining},
year = {1996},
pages = {37-57},
url = {http://dblp.uni-trier.de/db/books/collections/fayyad96.html#BrachmanA96},
isbn = {0-262-02313-X},
keywords = {2006, lecture, process, kdd}
}
Fayyad, U. M.; Piatetsky-Shapiro, G.; Smyth, P. & Uthurusamy, R. (Hrsg.): Advances in Knowledge Discovery and Data Mining.. AAAI/MIT Press, 1996
[Volltext]
@book{books/mit/FayyadPSU96,,
title = {Advances in Knowledge Discovery and Data Mining.},
editor = {Fayyad, Usama M. and Piatetsky-Shapiro, Gregory and Smyth, Padhraic and Uthurusamy, Ramasamy},
publisher = {AAAI/MIT Press},
year = {1996},
url = {http://www.amazon.com/gp/product/0262560976},
isbn = {0-262-56097-6},
keywords = {2006, data, definition, discovery, dm, kdd, knowledge, lecture, mining}
}
Park, J.; Chen, M. & Yu, P.: An effective hash-based algorithm for mining association rules. In: Proceedings of the 1995 ACM SIGMOD international conference on Management of data (1995), S. 175-186
@article{park1995ehb,
author = {Park, J.S. and Chen, M.S. and Yu, P.S.},
title = {An effective hash-based algorithm for mining association rules},
journal = {Proceedings of the 1995 ACM SIGMOD international conference on Management of data},
publisher = {ACM Press New York, NY, USA},
year = {1995},
pages = {175-186},
keywords = {2006, table, lecture, rules, association, kdd, mining, hash}
}
Agrawal, R. & Srikant, R.: Fast Algorithms for Mining Association Rules in Large Databases. VLDB '94: Proceedings of the 20th International Conference on Very Large Data Bases. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1994, S. 487-499
@inproceedings{672836,
author = {Agrawal, Rakesh and Srikant, Ramakrishnan},
title = {Fast Algorithms for Mining Association Rules in Large Databases},
booktitle = {VLDB '94: Proceedings of the 20th International Conference on Very Large Data Bases},
publisher = {Morgan Kaufmann Publishers Inc.},
address = {San Francisco, CA, USA},
year = {1994},
pages = {487--499},
isbn = {1-55860-153-8},
keywords = {2006, lecture, rule, association, kdd, mining}
}
van Rijsbergen, C. J.: Information retrieval. 2. Aufl. London: Butterworths, 1979
[Volltext]
@book{rijsbergen79information,
author = {van Rijsbergen, C. J.},
title = {Information retrieval},
publisher = {Butterworths},
address = {London},
year = {1979},
edition = {2},
url = {http://www.dcs.gla.ac.uk/Keith/Preface.html},
keywords = {advanced, information, ir, lecture, vorlesung}
}
Dempster, A.; Laird, N. & Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm.. In: J. Royal Statistical Society, Series B 39 (1977), Nr. 1, S. 1-38
@article{dempster77,
author = {Dempster, A. and Laird, N. and Rubin, D.},
title = {Maximum likelihood from incomplete data via the EM algorithm.},
journal = {J. Royal Statistical Society, Series B},
year = {1977},
volume = {39},
number = {1},
pages = {1-38},
keywords = {clustering, 2006, lecture, kdd}
}