Looking into the past to better classify web spam Export

@inproceedings{Dai09, abstract = {Web spamming techniques aim to achieve undeserved rankings in search results. Research has been widely conducted on identifying such spam and neutralizing its influence. However, existing spam detection work only considers current information. We argue that historical web page information may also be important in spam classification. In this paper, we use content features from historical versions of web pages to improve spam classification. We use supervised learning techniques to combine classifiers based on current page content with classifiers based on temporal features. Experiments on the WEBSPAM-UK2007 dataset show that our approach improves spam classification F-measure performance by 30\% compared to a baseline classifier which only considers current page content.}, address = {New York, NY, USA}, author = {Dai, Na and Davison, Brian D. and Qi, Xiaoguang}, booktitle = {AIRWeb '09: Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web}, citeulike-article-id = {4434474}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1531914.1531916}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1531914.1531916}, doi = {10.1145/1531914.1531916}, isbn = {978-1-60558-438-6}, keywords = {related, spam, temporal, webir}, location = {Madrid, Spain}, pages = {1--8}, posted-at = {2009-04-29 14:47:49}, priority = {2}, publisher = {ACM}, title = {Looking into the past to better classify web spam}, url = {http://dx.doi.org/10.1145/1531914.1531916}, year = {2009} }

TY - CONF ID - Dai09 L3 - citeulike-article-id:4434474 N2 - Web spamming techniques aim to achieve undeserved rankings in search results. Research has been widely conducted on identifying such spam and neutralizing its influence. However, existing spam detection work only considers current information. We argue that historical web page information may also be important in spam classification. In this paper, we use content features from historical versions of web pages to improve spam classification. We use supervised learning techniques to combine classifiers based on current page content with classifiers based on temporal features. Experiments on the WEBSPAM-UK2007 dataset show that our approach improves spam classification F-measure performance by 30% compared to a baseline classifier which only considers current page content. CY - Madrid, Spain SN - 978-1-60558-438-6 AD - New York, NY, USA EP - 8 TI - Looking into the past to better classify web spam PB - ACM T2 - AIRWeb '09: Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web SP - 1 KW - related KW - spam KW - temporal KW - webir AU - Dai, Na AU - Davison, Brian AU - Qi, Xiaoguang PY - 2009/// UR - http://dx.doi.org/10.1145/1531914.1531916 ER -