@misc{chakrabarti2000mining,
  abstract = {Many Web surfers maintain bookmark files containing URLs organized into folders which represent topics by function or content. We propose a new framework for discovering themes among such folders created by a community of surfers with overlapping interests. In principle, surfers need not create personal folders; they can just use a 'standard' tax- onomy such as Yahoo. In practice, a standard taxonomy is neither necessary nor sufficient; it is too detailed in most part, but likely to be inadequate in the community's areas of deep interest. Our framework, based on the minimum de- scription length principle, exploits two semantically different relations: "term occurs in document" and "document occurs in folder", and combines them without the need for heuris- tic weighting of attributes. Themes, in effect, finds common factors in people's interests when it can, while maintaining their individuality when it must. We present experimen- tal results to illustrate our framework and show how it is different from content-based clustering. We also propose a number of applications to finding themes, including collab- orative recommendation and resource discovery.},
  author = {Chakrabarti, S. and Batterrywala, Y.},
  file = {chakrabarti2000mining.pdf:chakrabarti2000mining.pdf:PDF},
  interhash = {dd726da3987cfe89f9654fd2a90da2d8},
  intrahash = {7c884093f2232d32cf226d774f93269a},
  lastdatemodified = {2005-08-06},
  lastname = {Chakrabarti},
  own = {own},
  pdf = {chakrabarti00.pdf},
  read = {read},
  title = {Mining themes from bookmarks},
  url = {chakrabarti00.ps},
  year = 2000
}

@article{Chakrabartietal99,
  author = {Chakrabarti, S. and van den Berg, M. and Dom, B.},
  interhash = {e35ac8e9c02ab2a5075b9c1692ac7a2d},
  intrahash = {004dd97a2b2e71fa2cfe6820c74c9701},
  isbn = {90-74821-43-X},
  journal = {Computer Networks},
  pages = {1623--1640},
  title = {Focused Crawling: A New Approach to Topic-Specific Web Resource Discovery},
  url = {citeseer.nj.nec.com/chakrabarti99focused.html},
  volume = 31,
  year = 1999
}

@inproceedings{Chakrabartietal98,
  author = {Chakrabarti, S. and Dom, B. and Gibson, D. and Kleinberg, J. and Raghavan, P. and Rajagopalan, S.},
  booktitle = {Proceedings of the 7th World-wide web conference (WWW7),30(1-7)},
  interhash = {911034f92829572cb2c211ad26849bda},
  intrahash = {9333fd6bd5864b94c9644e979c7a9fec},
  location = {Santa Barbara, CA},
  pages = {65--74},
  title = {Automatic resource compilation by analyzing hyperlink structure and associated text},
  url = {citeseer.nj.nec.com/chakrabarti98automatic.html},
  year = 1998
}

@book{Chakrabarti03,
  address = {San Francisco, CA},
  author = {Chakrabarti, S.},
  interhash = {17b9fcd01a172b10b3bd238457902ead},
  intrahash = {70fcada9c1a5537b5394a49c326a7110},
  isbn = {90-74821-43-X},
  publisher = {Morgan Kaufmann},
  title = {mining the web},
  year = 2003
}

@article{Chakrabarti2000,
  author = {Chakrabarti, S.},
  interhash = {e54787477738b367fad5aa57523a2cfd},
  intrahash = {31d8cbe4de9c172bf3284a29b0cf57bf},
  journal = {SIGKDD Explorations},
  location = {Santa Barbara, CA},
  number = 2,
  pages = {1--11},
  publisher = {ACM},
  title = {Data mining for hypertext: A tutorial survey},
  url = {citeseer.nj.nec.com/304115.html},
  volume = 1,
  year = 2000
}