SpamRank ­ Fully Automatic Link Spam Detection Work in progress

@inproceedings{citeulike:336501, abstract = {Spammers intend to increase the PageRank of certain spam pages by creating a large number of links pointing to them. We propose a novel method based on the concept o f personalized PageRank that detects pages with an undeserved high PageRank value without the need of any kind of white or blacklists or other means of human intervention. We assume that spammed pages have a biased distribution of pages that contribute to the undeserved high PageRank value. We define SpamRank by penalizing pages that originate a suspicious PageRank share and personalizing PageRank on the penalties. Our method is tested on a 31 M page crawl of the .de domain with a manually classified 1000-page strati fied random sample with bias towards large PageRank values.}, author = {Bencz\'{u}r, Andr\'{a}s A. and Csalog\'{a}ny, K\'{a}roly and Sarl\'{o}s, Tam\'{a}s and Uher, M\'{a}t\'{e} }, booktitle = {Proceedings of the First International Workshop on Adversarial Information Retrieval on the Web}, citeulike-article-id = {336501}, keywords = {link-spam, web-graph}, month = {May}, posted-at = {2005-09-30 11:46:06}, priority = {0}, title = {SpamRank ­ Fully Automatic Link Spam Detection Work in progress}, year = {2005} }

TY - CONF ID - citeulike:336501 L3 - citeulike-article-id:336501 N2 - Spammers intend to increase the PageRank of certain spam pages by creating a large number of links pointing to them. We propose a novel method based on the concept o f personalized PageRank that detects pages with an undeserved high PageRank value without the need of any kind of white or blacklists or other means of human intervention. We assume that spammed pages have a biased distribution of pages that contribute to the undeserved high PageRank value. We define SpamRank by penalizing pages that originate a suspicious PageRank share and personalizing PageRank on the penalties. Our method is tested on a 31 M page crawl of the .de domain with a manually classified 1000-page strati fied random sample with bias towards large PageRank values. TI - SpamRank ­ Fully Automatic Link Spam Detection Work in progress T2 - Proceedings of the First International Workshop on Adversarial Information Retrieval on the Web KW - link-spam KW - web-graph AU - Benczúr, András AU - Csalogány, Károly AU - Sarlós, Tamás AU - Uher, Máté PY - 2005/05// ER -