%0 Journal Article %1 qi2009classification %A Qi, Xiaoguang %A Davison, Brian D. %C New York, NY, USA %D 2009 %I ACM %J ACM Comput. Surv. %K classification page web %N 2 %P 12:1--12:31 %R 10.1145/1459352.1459357 %T Web Page Classification: Features and Algorithms %U http://doi.acm.org/10.1145/1459352.1459357 %V 41 %X 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. 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.

@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. 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}, added-at = {2014-06-03T10:23:04.000+0200}, address = {New York, NY, USA}, articleno = {12}, author = {Qi, Xiaoguang and Davison, Brian D.}, biburl = {https://www.bibsonomy.org/bibtex/2897141deb7178910a0cc70c133eec8b9/thoni}, description = {Web page classification}, doi = {10.1145/1459352.1459357}, interhash = {3e1f5f696040766fa9c1993748cdc465}, intrahash = {897141deb7178910a0cc70c133eec8b9}, issn = {0360-0300}, issue_date = {February 2009}, journal = {ACM Comput. Surv.}, keywords = {classification page web}, month = feb, number = 2, numpages = {31}, pages = {12:1--12:31}, publisher = {ACM}, timestamp = {2016-09-06T08:23:07.000+0200}, title = {Web Page Classification: Features and Algorithms}, url = {http://doi.acm.org/10.1145/1459352.1459357}, volume = 41, year = 2009 }