%0 Conference Paper %1 Glover:2002:UWS:511446.511520 %A Glover, Eric J. %A Tsioutsiouliklis, Kostas %A Lawrence, Steve %A Pennock, David M. %A Flake, Gary W. %B Proceedings of the 11th international conference on World Wide Web %C New York, NY, USA %D 2002 %I ACM %K anchor bachelor:2011:bachmann classification webpage %P 562--569 %R 10.1145/511446.511520 %T Using web structure for classifying and describing web pages %U http://doi.acm.org/10.1145/511446.511520 %X The structure of the web is increasingly being used to improve organization, search, and analysis of information on the web. For example, Google uses the text in citing documents (documents that link to the target document) for search. We analyze the relative utility of document text, and the text in citing documents near the citation, for classification and description. Results show that the text in citing documents, when available, often has greater discriminative and descriptive power than the text in the target document itself. The combination of evidence from a document and citing documents can improve on either information source alone. Moreover, by ranking words and phrases in the citing documents according to expected entropy loss, we are able to accurately name clusters of web pages, even with very few positive examples. Our results confirm, quantify, and extend previous research using web structure in these areas, introducing new methods for classification and description of pages. %@ 1-58113-449-5

@inproceedings{Glover:2002:UWS:511446.511520, abstract = {The structure of the web is increasingly being used to improve organization, search, and analysis of information on the web. For example, Google uses the text in citing documents (documents that link to the target document) for search. We analyze the relative utility of document text, and the text in citing documents near the citation, for classification and description. Results show that the text in citing documents, when available, often has greater discriminative and descriptive power than the text in the target document itself. The combination of evidence from a document and citing documents can improve on either information source alone. Moreover, by ranking words and phrases in the citing documents according to expected entropy loss, we are able to accurately name clusters of web pages, even with very few positive examples. Our results confirm, quantify, and extend previous research using web structure in these areas, introducing new methods for classification and description of pages.}, acmid = {511520}, added-at = {2011-11-30T17:29:57.000+0100}, address = {New York, NY, USA}, author = {Glover, Eric J. and Tsioutsiouliklis, Kostas and Lawrence, Steve and Pennock, David M. and Flake, Gary W.}, biburl = {https://www.bibsonomy.org/bibtex/2380ef8c1e445af95322ce9e36cd62c70/telekoma}, booktitle = {Proceedings of the 11th international conference on World Wide Web}, description = {Using web structure for classifying and describing web pages}, doi = {10.1145/511446.511520}, interhash = {b1b1e6b964cf53ea74720c7403b2473d}, intrahash = {380ef8c1e445af95322ce9e36cd62c70}, isbn = {1-58113-449-5}, keywords = {anchor bachelor:2011:bachmann classification webpage}, location = {Honolulu, Hawaii, USA}, numpages = {8}, pages = {562--569}, publisher = {ACM}, series = {WWW '02}, timestamp = {2011-11-30T17:29:57.000+0100}, title = {Using web structure for classifying and describing web pages}, url = {http://doi.acm.org/10.1145/511446.511520}, year = 2002 }