@article{hotho2010ubiquitous,
  author = {Hotho, Andreas and {Ulslev Pedersen}, Rasmus and Wurst, Michael},
  interhash = {e779fb5dff41b65bce1aa38fdca4a376},
  intrahash = {56f2940d5d0f2ce59c342d3b8ad42ca1},
  issn = {0302-9743},
  journal = {Lecture Notes in Computer Science},
  number = 6202,
  pages = {61--74},
  publisher = {Springer},
  title = {Ubiquitous Data},
  url = {http://rd.springer.com/content/pdf/10.1007%2F978-3-642-16392-0_4.pdf},
  year = 2010
}

@inproceedings{anti2008krause,
  address = {New York, NY, USA},
  author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd},
  booktitle = {AIRWeb '08: Proceedings of the 4th international workshop on Adversarial information retrieval on the web},
  doi = {http://doi.acm.org/10.1145/1451983.1451998},
  interhash = {a45d40ac7776551301ad9dde5b25357f},
  intrahash = {68effe5d4b9460f9388e7685310f74c2},
  isbn = {978-1-60558-159-0},
  location = {Beijing, China},
  pages = {61--68},
  publisher = {ACM},
  title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems},
  url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf},
  year = 2008
}

@book{0387954333,
  asin = {0387954333},
  author = {Weiss, Sholom M. and Indurkhya, Nitin and Zhang, T.},
  dewey = {006.312},
  ean = {9780387954332},
  edition = 1,
  interhash = {d75b9da07cf40d54a79e6d8995f78a31},
  intrahash = {6ac07561b543e6033fd4c9811d0dccad},
  isbn = {0387954333},
  publisher = {Springer, Berlin},
  title = {Text Mining. Predictive Methods for Analyzing Unstructured Information},
  url = {http://www.amazon.de/gp/redirect.html%3FASIN=0387954333%26tag=ws%26lcode=xm2%26cID=2025%26ccmID=165953%26location=/o/ASIN/0387954333%253FSubscriptionId=13CT5CVB80YFWJEPWS02},
  year = 2004
}

@book{Berendt2007,
  abstract = {This book constitutes the refereed proceedings of the Workshop on Web Mining, WebMine 2006, held in Berlin, Germany, September 18th, 2006. Topics included are data mining based on analysis of bloggers and tagging, web mining, XML mining and further techniques of knowledge discovery. The book is especially valuable for those interested in the aspects of the Social Web (Web 2.0) and its inherent dynamic and diversity of user-generated content.},
  date = {September 18, 2006 Series:},
  editor = {Berendt, B. and Hotho, A. and Mladenic, D. and Semeraro, G.},
  interhash = {44843d4fe175e66198b58137dd924f44},
  intrahash = {8aa8d9bcbb5a5bb3fc480d1e53b27236},
  isbn = {978-3-540-74950-9},
  location = {Berlin, Germany},
  publisher = {Springer},
  series = {LNCS},
  title = {From Web to Social Web: Discovering and Deploying User and Content Profiles },
  url = {http://www.springer.com/dal/home?SGWID=1-102-22-173759307-0&changeHeader=true&referer=www.springeronline.com&SHORTCUT=www.springer.com/978-3-540-74950-9},
  vgwort = {279},
  volume = 4736,
  year = 2007
}

@article{1276056,
  address = {Amsterdam, The Netherlands, The Netherlands},
  author = {Wurst, Michael and Morik, Katharina},
  doi = {http://dx.doi.org/10.1016/j.future.2006.04.004},
  interhash = {591e4b107d4a5cafc0cf49e07fad72e0},
  intrahash = {e5eba80e58b4532a3fd3bcf50994734e},
  issn = {0167-739X},
  journal = {Future Gener. Comput. Syst.},
  number = 1,
  pages = {69--75},
  publisher = {Elsevier Science Publishers B. V.},
  title = {Distributed feature extraction in a p2p setting: a case study},
  url = {http://portal.acm.org/citation.cfm?id=1276056},
  volume = 23,
  year = 2007
}

@inbook{baldi03modelling,
  abstract = {Modeling the Internet and the Web covers the most important aspects of modeling the Web using a modern mathematical and probabilistic treatment. It focuses on the information and application layers, as well as some of the emerging properties of the Internet.  Provides a comprehensive introduction to the modeling of the Internet and the Web at the information level.  Takes a modern approach based on mathematical, probabilistic, and graphical modeling.  Provides an integrated presentation of theory, examples, exercises and applications.  Covers key topics such as text analysis, link analysis, crawling techniques, human behaviour, and commerce on the Web. Interdisciplinary in nature, Modeling the Internet and the Web will be of interest to students and researchers from a variety of disciplines including computer science, machine learning, engineering, statistics, economics, business, and the social sciences.},
  author = {Baldi, Pierre and Frasconi, Paolo and Smyth, Padhraic},
  booktitle = {Modeling the Internet and the Web: Probabilistic Methods and Algorithms},
  citeulike-article-id = {822915},
  interhash = {416f2405193ae7d30cffe673dee89df2},
  intrahash = {3e4e2899e7d6988218d02a264bcfe24a},
  month = {April},
  priority = {2},
  publisher = {Wiley},
  title = {Modeling the Internet and the Web: Probabilistic Methods and Algorithms},
  url = {http://eu.wiley.com/WileyCDA/WileyTitle/productCd-0470849061.html},
  year = 2003
}

@proceedings{DBLP:conf/kdd/1999web,
  bibsource = {DBLP, http://dblp.uni-trier.de},
  booktitle = {WEBKDD},
  editor = {Masand, Brij M. and Spiliopoulou, Myra},
  interhash = {29a69416c66bd604c4599009915dc0b0},
  intrahash = {18a9697e8ca04f637487e79b6be9cc83},
  isbn = {3-540-67818-2},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {Web Usage Analysis and User Profiling, International WEBKDD'99
               Workshop, San Diego, California, USA, August 15, 1999, Revised
               Papers},
  volume = 1836,
  year = 2000
}

@book{books/mk/Pyle99,
  author = {Pyle, Dorian},
  date = {2002-01-28},
  interhash = {3edec307e8a02fa778ee847eccfb4215},
  intrahash = {29f6bc4833269393dabf92bae3afa905},
  isbn = {1-55860-529-0},
  publisher = {Morgan Kaufmann},
  title = {Data Preparation for Data Mining},
  year = 1999
}

@article{wikipediaxml:2005,
  author = {Denoyer, Ludovic and Gallinari, Patrick},
  interhash = {0e9b9afb15804d3e625d73ada85900b1},
  intrahash = {493b849942fcaf9ba8e8e68e3cb46d38},
  journal = {SIGIR Forum},
  title = {{T}he {W}ikipedia {X}{M}{L} {C}orpus},
  url = {http://www-connex.lip6.fr/~denoyer/wikipediaXML/},
  year = 2006
}

@misc{Newman+Hettich+Blake+Merz:1998,
  author = {Newman, C.L. Blake D.J. and Merz, C.J.},
  institution = {University of California, Irvine, Dept. of Information and Computer Sciences},
  interhash = {325a6b5ac5a1f044943d4298c21d31dd},
  intrahash = {85308db3df761f63f16a7cab4eb8d4aa},
  title = {{UCI} Repository of machine learning databases},
  url = {http://www.ics.uci.edu/$\sim$mlearn/MLRepository.html},
  year = 1998
}

@book{books/mit/FayyadPSU96,
  editor = {Fayyad, Usama M. and Piatetsky-Shapiro, Gregory and Smyth, Padhraic and Uthurusamy, Ramasamy},
  interhash = {c11811ccd720de5dad0ffea4741725f0},
  intrahash = {3553c3acc971c03813352c40afe7476a},
  isbn = {0-262-56097-6},
  publisher = {AAAI/MIT Press},
  title = {Advances in Knowledge Discovery and Data Mining.},
  url = {http://www.amazon.com/gp/product/0262560976},
  year = 1996
}

@book{Handetal01,
  author = {Hand, D. and Mannila, H. and Smyth, P.},
  interhash = {1d7f5d27a1dfea47e1ac543fcb027c0d},
  intrahash = {e2e195a4102d09f2ed4976bf102af01d},
  location = {Santa Barbara, CA},
  publisher = {Cambridge, MA: MIT Press},
  title = {Principles of Data Mining},
  year = 2001
}