Web page classification: Features and algorithms Export

@article{citeulike:4214865, 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.}, address = {New York, NY, USA}, author = {Qi, Xiaoguang and Davison, Brian D.}, citeulike-article-id = {4214865}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1459352.1459357}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1459352.1459357}, doi = {10.1145/1459352.1459357}, issn = {0360-0300}, journal = {ACM Comput. Surv.}, keywords = {classification\_features, heeii, text\_classification, web, web\_directories}, number = {2}, pages = {1--31}, posted-at = {2009-10-07 20:04:07}, priority = {2}, publisher = {ACM}, title = {Web page classification: Features and algorithms}, url = {http://dx.doi.org/10.1145/1459352.1459357}, volume = {41}, year = {2009} }

TY - JOUR ID - citeulike:4214865 L3 - citeulike-article-id:4214865 N2 - 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. IS - 2 JF - ACM Comput. Surv. SN - 0360-0300 AD - New York, NY, USA EP - 31 TI - Web page classification: Features and algorithms PB - ACM VL - 41 SP - 1 KW - classification_features KW - heeii KW - text_classification KW - web KW - web_directories AU - Qi, Xiaoguang AU - Davison, Brian PY - 2009/// UR - http://dx.doi.org/10.1145/1459352.1459357 ER -