@inproceedings{ntoulas2006spam,
	title = {Detecting spam web pages through content analysis},
	address = {New York, NY, USA},
	author = {Alexandros Ntoulas and Marc Najork and Mark Manasse and Dennis Fetterly},
	booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web},
	pages = {83--92},
	publisher = {ACM},
	url = {http://portal.acm.org/citation.cfm?id=1135794},
	year = {2006},
	biburl = {http://www.bibsonomy.org/bibtex/2c93f4228fd8552bede071569cdaa1ad9/beate},
	description = {Detecting spam web pages through content analysis},
	abstract = {In this paper, we continue our investigations of "web spam": the injection of artificially-created pages into the web in order to influence the results from search engines, to drive traffic to certain pages for fun or profit. This paper considers some previously-undescribed techniques for automatically detecting spam pages, examines the effectiveness of these techniques in isolation and when aggregated using classification algorithms. When combined, our heuristics correctly identify 2,037 (86.2%) of the 2,364 spam pages (13.8%) in our judged collection of 17,168 pages, while misidentifying 526 spam and non-spam pages (3.1%).},
	location = {Edinburgh, Scotland}, isbn = {1-59593-323-9}, doi = {http://doi.acm.org/10.1145/1135777.1135794},
	keywords = {features spam web }
}