Blocking Blog Spam with Language Model Disagreement

@inproceedings{citeulike:336504, abstract = {We present an approach for detecting link spam common in blog comments by comparing the language models used in the blog post, the comment, and pages linked by the comments. In contrast to other link spam filtering approaches, our method requires no training, no hard-coded rule sets, and no knowledge of complete-web connectivity. Preliminary expe riments with identification of typical blog spam show promising results.}, author = {Mishne, Gilad and Carmel, David and Lempel, Ronny }, booktitle = {Proceedings of the First International Workshop on Adversarial Information Retrieval on the Web}, citeulike-article-id = {336504}, keywords = {blog, link-spam, web-graph}, month = {May}, posted-at = {2005-09-30 11:49:42}, priority = {0}, title = {Blocking Blog Spam with Language Model Disagreement}, year = {2005} }

TY - CONF ID - citeulike:336504 L3 - citeulike-article-id:336504 N2 - We present an approach for detecting link spam common in blog comments by comparing the language models used in the blog post, the comment, and pages linked by the comments. In contrast to other link spam filtering approaches, our method requires no training, no hard-coded rule sets, and no knowledge of complete-web connectivity. Preliminary expe riments with identification of typical blog spam show promising results. TI - Blocking Blog Spam with Language Model Disagreement T2 - Proceedings of the First International Workshop on Adversarial Information Retrieval on the Web KW - blog KW - link-spam KW - web-graph AU - Mishne, Gilad AU - Carmel, David AU - Lempel, Ronny PY - 2005/05// ER -