@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 }