@inproceedings{content-only,
  author = {Cooley, R. and Mobasher, B. and Srivastava, J.},
  booktitle = {Proceedings of the Ninth IEEE International Conference          on Tools with Artificial Intelligence (ICTAI'97)},
  interhash = {94895d7c0cc214ed623d941b2dab7367},
  intrahash = {e385cc03235ad1efc751e12fb2fd11d0},
  location = {Newport Beach, CA},
  month = Nov,
  publisher = {IEEE Computer Society},
  title = {Web Mining: Information and Pattern Discovery on the World Wide Web},
  url = {http://maya.cs.depaul.edu/~mobasher/papers/webminer-tai97.ps},
  year = 1997
}

@article{journals/cacm/Etzioni96,
  author = {Etzioni, Oren},
  cdrom = {CACMs1/CACM3911/P0065.pdf},
  cite = {conf/kdd/ZaianeH95},
  date = {2003-11-20},
  ee = {db/journals/cacm/Etzioni96.html},
  interhash = {5c3111490c1f8a998d8d5f974c8afe65},
  intrahash = {a8955e592d1eed82fdf43314241b5423},
  journal = {Commun. ACM},
  number = 11,
  pages = {65-68},
  title = {The World-Wide Web: Quagmire or Gold Mine?},
  url = {http://doi.acm.org/10.1145/240455.240473},
  volume = 39,
  year = 1996
}

@inproceedings{conf/dawak/MadriaBNL99,
  author = {Madria, Sanjay Kumar and Bhowmick, Sourav S. and Ng, Wee Keong and Lim, Ee-Peng},
  booktitle = {DaWaK},
  crossref = {conf/dawak/1999},
  date = {2002-03-05},
  editor = {Mohania, Mukesh K. and Tjoa, A. Min},
  ee = {http://link.springer.de/link/service/series/0558/bibs/1676/16760303.htm},
  interhash = {706390429ca5bf6e33d2fda37f956922},
  intrahash = {1016d42a26ca0748ba227d62b7126933},
  isbn = {3-540-66458-0},
  pages = {303-312},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {Research Issues in Web Data Mining.},
  url = {http://dblp.uni-trier.de/db/conf/dawak/dawak99.html#MadriaBNL99},
  volume = 1676,
  year = 1999
}

@inproceedings{conf/kdd/BorgesL98,
  author = {Borges, José and Levene, Mark},
  booktitle = {KDD},
  date = {2002-12-17},
  interhash = {c231f04d16109f3e336deb073fe1fb5b},
  intrahash = {db40027e6c7e7a90ca72cc860208f7ab},
  pages = {149-153},
  title = {Mining Association Rules in Hypertext Databases.},
  url = {http://paginas.fe.up.pt/~jlborges/publications/arhtKDD98.ps},
  year = 1998
}

@article{keyhere,
  asin = {9812563393},
  author = {Schenker, Adam and Bunke, Horst and Last, Mark and Kandel, Abraham},
  interhash = {247e95a6025dff9119c7943b5a33f917},
  intrahash = {3f9897fc8abcf1bcb1fd0212a23a4134},
  isbn = {9812563393},
  title = {Graph-Theoretic Techniques for Web Content Mining},
  typesource = {Simple CitationSource},
  url = {http://www.amazon.ca/Graph-Theoretic-Techniques-Web-Content-Mining/dp/9812563393/ref=sr_1_7/701-3503486-7337153?ie=UTF8&s=books&qid=1175673405&sr=1-7},
  year = 2005
}

@inproceedings{conf/das/SchenkerBLK04,
  author = {Schenker, Adam and Bunke, Horst and Last, Mark and Kandel, Abraham},
  booktitle = {Document Analysis Systems},
  crossref = {conf/das/2004},
  date = {2005-01-05},
  editor = {Marinai, Simone and Dengel, Andreas},
  ee = {http://springerlink.metapress.com/openurl.asp?genre=article&issn=0302-9743&volume=3163&spage=401},
  interhash = {83ba06e8918a227fb2345e047e40f619},
  intrahash = {4450261ce5af13db99ce208800dff22c},
  isbn = {3-540-23060-2},
  pages = {401-412},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {A Graph-Based Framework for Web Document Mining.},
  url = {http://dblp.uni-trier.de/db/conf/das/das2004.html#SchenkerBLK04},
  volume = 3163,
  year = 2004
}

@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
}

@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
}

@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
}

@inproceedings{feldman95KDT,
  author = {Feldman, R. and Dagan, I.},
  booktitle = {Proc. of the First Int. Conf. on Knowledge Discovery (KDD)},
  interhash = {15f076596b35048463f828687410ea30},
  intrahash = {d1bb2e8dff9bd80da158b4b770685dce},
  key = {feldman95KDT},
  label = {KDT - Knowledge Discovery in Texts},
  pages = {112-117},
  title = {Knowledge Discovery in Textual Databases (KDT)},
  type = {InProceedings},
  year = 1995
}

@inproceedings{conf/icdm/PopesculULP03,
  author = {Popescul, Alexandrin and Ungar, Lyle H. and Lawrence, Steve and Pennock, David M.},
  booktitle = {ICDM},
  crossref = {conf/icdm/2003},
  date = {2004-01-28},
  ee = {http://csdl.computer.org/comp/proceedings/icdm/2003/1978/00/19780275abs.htm},
  interhash = {3bcb76c6628b1752db555f86fe39429e},
  intrahash = {7cdd6b0791fcdf17ec6d404b55f12c5c},
  isbn = {0-7695-1978-4},
  pages = {275-282},
  publisher = {IEEE Computer Society},
  title = {Statistical Relational Learning for Document Mining.},
  url = {http://www.cis.upenn.edu/~popescul/Publications/popescul03dm.pdf},
  year = 2003
}

@article{kostoff,
  abstract = {Literature-related discovery (LRD) is the linking of two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge (i.e., potential discovery). The open discovery systems (ODS) component of LRD starts with a problem to be solved, and generates solutions to that problem through potential discovery. We have been using ODS LRD to identify potential treatments or preventative actions for challenging medical problems, among myriad other applications. This paper describes the second medical problem we addressed (cataract) using ODS LRD; the first problem addressed was Raynaud's Phenomenon (RP), and was described in the third paper of this Special Issue. Cataract was selected because it is ubiquitous globally, appears intractable to all forms of treatment other than surgical removal of cataracts, and is a major cause of blindness in many developing countries. The ODS LRD study had three objectives: a) identify non-drug non-surgical treatments that would 1) help prevent cataracts, or 2) reduce the progression rate of cataracts, or 3) stop the progression of cataracts, or 4) maybe even reverse the progression of cataracts; b) demonstrate that we could solve an ODS LRD problem with no prior knowledge of any results or prior work (unlike the case with the RP problem); c) determine whether large time savings in the discovery process were possible relative to the time required for conducting the RP study. To that end, we used the MeSH taxonomy of MEDLINE to restrict potential discoveries to selected semantic classes, as a substitute for the manually-intensive process used in the RP study to restrict potential discoveries to selected semantic classes. We also used additional semantic filtering to identify potential discovery within the selected semantic classes. All these goals were achieved. As will be shown, we generated large amounts of potential discovery in more than an order of magnitude less time than required for the RP study. We identified many non-drug non-surgical treatments that may be able to reduce or even stop the progression rate of cataracts. Time, and much testing, will determine whether this is possible. Finally, the methodology has been developed to the point where ODS LRD problems can be solved with no results or knowledge of any prior work.},
  author = {Kostoff, Ronald N.},
  interhash = {45ce0cd73dd62182ce1e447ba9fe71eb},
  intrahash = {b9359f79985da9b9677340ffda849e74},
  journal = {Technological Forecasting and Social Change},
  pages = {--},
  title = {Literature-related discovery (LRD): Potential treatments for cataracts},
  url = {http://www.sciencedirect.com/science/article/B6V71-4RDB8SC-9/2/8991fe8968a0ef12f22ed7e9ac9d7c4f},
  volume = {In Press, Corrected Proof},
  year = 2007
}

@inproceedings{berendt05semantic,
  author = {Berendt, Bettina and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proc. of the 1st Intl. Workshop on Representation and Analysis of Web Space},
  editor = {Svatek, Vojtech and Snasel, Vaclav},
  interhash = {e4b853ff13b63a88b009610890b89348},
  intrahash = {f8826ba2790eeb857dd4becb31a08225},
  isbn = {80-248-0864-1},
  pages = {1--16},
  publisher = {Technical University of Ostrava},
  title = {Semantic Web Mining and the Representation, Analysis, and Evolution of Web Space},
  url = {http://ftp.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-164/raws2005-paper1.pdf},
  vgwort = {29},
  year = 2005
}

@book{Berendt2004Web,
  address = {Heidelberg},
  editor = {Berendt, Bettina and Hotho, Andreas and Mladenic, Dunja and van Someren, Maarten and Spiliopoulou, Myra and Stumme, Gerd},
  interhash = {f5223cd62ce3c9d458d4cb5721880a0e},
  intrahash = {495f8565cdda14bbbe197d11425f0fe8},
  isbn = {3-540-23258-3},
  price = {EUR 38,52},
  publisher = {Springer},
  series = {LNAI},
  title = {Web Mining: From Web to Semantic Web},
  volume = 3209,
  year = 2004
}

@inproceedings{trias2006jaeschke,
  address = {Hong Kong},
  author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Ganter, Bernhard and Stumme, Gerd},
  booktitle = {Proc. 6th ICDM conference},
  doi = {http://doi.ieeecomputersociety.org/10.1109/ICDM.2006.162},
  interhash = {b4964c3bdd2991a80873d7080ef6a73e},
  intrahash = {f9a6e80c21b1266491d2509ca0b88eea},
  isbn = {0-7695-2701-9},
  issn = {1550-4786},
  month = {December},
  title = {TRIAS - An Algorithm for Mining Iceberg Tri-Lattices},
  vgwort = {19},
  year = 2006
}

@proceedings{berendt2006webmining,
  editor = {Berendt, B. and Hotho, A. and Mladenic, D. and Semeraro, G.},
  interhash = {5e4e5a7285303d11a7f967495fe97059},
  intrahash = {ecab780995c630270857b610c7c54e67},
  title = {Workshop on Web Mining 2006 (WebMine)},
  url = {http://www.kde.cs.uni-kassel.de/ws/webmine2006/pdf/WebMine2006.pdf},
  year = 2006
}

@proceedings{stumme_semwebmine_ws01,
  address = {Freiburg},
  booktitle = {Proc. of the Semantic Web Mining Workshop},
  editor = {Stumme, G. and Hotho, A. and Berendt, B.},
  interhash = {ba288488b822fd20d4d7d947f8036360},
  intrahash = {604cb78986cc5596b4c336b9c5543add},
  month = {September 3rd},
  publisher = {Workshop at 12th Europ. Conf. on Machine Learning (ECML'01) / 5th Europ.              Conf. on Principles and Practice of Knowledge Discovery in              Databases (PKDD'01)},
  title = {Semantic Web Mining},
  year = 2001
}

@proceedings{WS_BHS02,
  address = {Helsinki},
  booktitle = {Proc. of the Semantic Web Mining          Workshop},
  editor = {Berendt, B. and Hotho, A. and Stumme, G.},
  interhash = {ad1bb62c9ae700cf0dc181ba42ee2b8f},
  intrahash = {f5bfd0060d08ec6aefea23c4add8da51},
  isbn = {3-540-41066-X},
  month = {August 20},
  publisher = {Workshop at 13th Europ. Conf. on Machine Learning (ECML'02) / 6th Europ.              Conf. on Principles and Practice of Knowledge Discovery in              Databases (PKDD'02)},
  title = {Semantic Web Mining},
  year = 2002
}

@proceedings{msw2004,
  editor = {Hotho, Andreas and Sure, York and Getoor, Lise},
  interhash = {0e2afdbc572d2f6c19c60559919931c1},
  intrahash = {0fbd582960b0f6917d82bd1825c3d167},
  month = AUG,
  note = {located at the 10th International ACM SIGKDD Conference on Knowledge Discovery and Data Mining KDD 2004, 22nd August 2004, Seattle, WA, USA},
  title = {International Workshop on Mining for and from the Semantic Web (MSW2004)},
  url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2004/msw2004_proceedings.pdf},
  year = 2004
}

@proceedings{berendt05european,
  editor = {Berendt, Bettina and Hotho, Andreas and Mladenic, Dunja and Semerano, Giovanni and Spiliopoulou, Myra and Stumme, Gerd and van Someren, Maarten},
  interhash = {6dfd547a42a7bd5ccacce75ea8875704},
  intrahash = {f306e43da22adede0286917d5d83eb3b},
  publisher = {Workshop at the 16th Europ. Conf. on Machine Learning (ECML'05) / 9th Europ. Conf. on Principles and Practice of Knowledge Discovery in Databases (PKDD'05)},
  title = {Proc. of the European Web Mining Forum 2005},
  year = 2005
}