@inproceedings{liu2005experimental,
  abstract = {Taxonomies of the Web typically have hundreds of thousands of categories and skewed category distribution over documents. It is not clear whether existing text classification technologies can perform well on and scale up to such large-scale applications. To understand this, we conducted the evaluation of several representative methods (Support Vector Machines, <i>k</i>-Nearest Neighbor and Naive Bayes) with Yahoo! taxonomies. In particular, we evaluated the effectiveness/efficiency tradeoff in classifiers with hierarchical setting compared to conventional (flat) setting, and tested popular threshold tuning strategies for their scalability and accuracy in large-scale classification problems.},
  acmid = {1062891},
  address = {New York, NY, USA},
  author = {LIU, Tie-Yan and YANG, Yiming and WAN, Hao and ZHOU, Qian and GAO, Bin and ZENG, Hua-Jun and CHEN, Zheng and MA, Wei-Ying},
  booktitle = {Special interest tracks and posters of the 14th international conference on World Wide Web},
  doi = {10.1145/1062745.1062891},
  interhash = {e581e4dd2ed6d748031a812c724c4b7c},
  intrahash = {36cc9f92b9c722b2aff441b23e44b2f7},
  isbn = {1-59593-051-5},
  location = {Chiba, Japan},
  numpages = {2},
  pages = {1106--1107},
  publisher = {ACM},
  series = {WWW '05},
  title = {An experimental study on large-scale web categorization},
  url = {http://doi.acm.org/10.1145/1062745.1062891},
  year = 2005
}

@article{malt1999knowing,
  author = {Malt, B.C. and Sloman, S.A. and Gennari, S. and Shi, M. and Wang, Y.},
  interhash = {c87af87d81af41f432ec16f1e21e70f0},
  intrahash = {5d022183458db304cc8dc59bff4506d0},
  issn = {0749-596X},
  journal = {Journal of Memory and Language},
  pages = {230--262},
  publisher = {Citeseer},
  title = {{Knowing versus naming: Similarity and the linguistic categorization of artifacts}},
  url = {http://scholar.google.de/scholar.bib?q=info:43NPl_inXfsJ:scholar.google.com/&output=citation&hl=de&as_sdt=2000&as_vis=1&ct=citation&cd=0},
  volume = 40,
  year = 1999
}

@inproceedings{lewis1991evaluating,
  abstract = {While certain standard procedures are widely used for evaluating text retrieval systems and algorithms, the same is not true for text categorization. Omission of important data from reports is common and methods of measuring effectiveness vary widely. This has made judging the relative merits of techniques for text categorization difficult and has disguised important research issues. In this paper I discuss a variety of ways of evaluating the effectiveness of text categorization systems, drawing both on reported categorization experiments and on methods used in evaluating query-driven retrieval. I also consider the extent to which the same evaluation methods may be used with systems for text extraction, a more complex task. In evaluating either kind of system, the purpose for which the output is to be used is crucial in choosing appropriate evaluation methods.},
  address = {San Mateo},
  author = {Lewis, David D.},
  booktitle = {Proceedings of Speech and Natural Language Workshop},
  interhash = {a9c64235f49e18a6b80c306b61ff40c2},
  intrahash = {2e8f19bde0a73d96d16c071b2016073f},
  month = Feb,
  pages = {312-318},
  publisher = {Morgan Kaufmann},
  title = {Evaluating text categorization},
  url = {http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=FB1ECC14412DFFF631E7C0725D4DB3CC?doi=10.1.1.56.9675&rep=rep1&type=pdf},
  year = 1991
}

@article{Sebastiani02,
  author = {Sebastiani, F.},
  bb-further-address = {--Dordrecht--London},
  interhash = {d945d9218673dad37dc2a06cbf9e554c},
  intrahash = {0fe0d5dd12c2cb59dfc330e684ec4b4a},
  journal = {ACM Computing Surveys},
  number = 1,
  pages = {1--47},
  title = {Machine learning in automated text categorization},
  url = {http://faure.iei.pi.cnr.it/~fabrizio/Publications/ACMCS02.pdf},
  volume = 34,
  year = 2002
}

@incollection{TM05,
  address = {Southampton, UK},
  author = {Sebastiani, Fabrizio},
  booktitle = {Text Mining and its Applications to Intelligence, CRM and                 Knowledge Management},
  editor = {Zanasi, Alessandro},
  interhash = {0343f986403f021264f6eea761722fd6},
  intrahash = {3b839b06f8139db217a9eb61d6015fc0},
  pages = {109--129},
  publisher = {WIT Press},
  title = {Text Categorization},
  url = {http://www.isti.cnr.it/People/F.Sebastiani/Publications/TM05.pdf},
  year = 2005
}