@article{qi2009classification,
  abstract = {Classification of Web page content is essential to many tasks in Web information retrieval such as maintaining Web directories and focused crawling. The uncontrolled nature of Web content presents additional challenges to Web page classification as compared to traditional text classification, but the interconnected nature of hypertext also provides features that can assist the process.</p> <p>As we review work in Web page classification, we note the importance of these Web-specific features and algorithms, describe state-of-the-art practices, and track the underlying assumptions behind the use of information from neighboring pages.},
  acmid = {1459357},
  address = {New York, NY, USA},
  articleno = {12},
  author = {Qi, Xiaoguang and Davison, Brian D.},
  doi = {10.1145/1459352.1459357},
  interhash = {3e1f5f696040766fa9c1993748cdc465},
  intrahash = {a89af712b3597fb94e2a25f309324f4b},
  issn = {0360-0300},
  issue = {2},
  issue_date = {February 2009},
  journal = {ACM Comput. Surv.},
  month = {February},
  numpages = {31},
  pages = {12:1--12:31},
  publisher = {ACM},
  title = {Web page classification: Features and algorithms},
  url = {http://doi.acm.org/10.1145/1459352.1459357},
  volume = 41,
  year = 2009
}

@incollection{choi2005classification,
  abstract = {This chapter describes systems that automatically classify web pages into meaningful categories. It first defines two types of web page classification: subject based and genre based classifications. It then describes the state of the art techniques and subsystems used to build automatic web page classification systems, including web page representations, dimensionality reductions, web page classifiers, and evaluation of web page classifiers. Such systems are essential tools for Web Mining and for the future of Semantic Web.},
  address = {Berlin / Heidelberg},
  affiliation = {Louisiana Tech University Computer Science, College of Engineering and Science Ruston LA 71272 USA},
  author = {Choi, B. and Yao, Z.},
  booktitle = {Foundations and Advances in Data Mining},
  doi = {10.1007/11362197_9},
  editor = {Chu, Wesley and Young Lin, Tsau},
  interhash = {ee6322086817459b37b7cb774be344cc},
  intrahash = {8cae2b481187e15ec17f1aeac3c80a68},
  isbn = {978-3-540-25057-9},
  keyword = {Engineering},
  pages = {221-274},
  publisher = {Springer},
  series = {Studies in Fuzziness and Soft Computing},
  title = {Web Page Classification},
  url = {http://dx.doi.org/10.1007/11362197_9},
  volume = 180,
  year = 2005
}