Identifying link farm spam pages Export

@inproceedings{citeulike:359677, abstract = {With the increasing importance of search in guiding today's web traffic, more and more effort has been spent to create search engine spam. Since link analysis is one of the most important factors in current commercial search engines' ranking systems, new kinds of spam aiming at links have appeared. Building link farms is one technique that can deteriorate link-based ranking algorithms. In this paper, we present algorithms for detecting these link farms automatically by first generating a seed set based on the common link set between incoming and outgoing links of Web pages and then expanding it. Links between identified pages are re-weighted, providing a modified web graph to use in ranking page importance. Experimental results show that we can identify most link farm spam pages and the final ranking results are improved for almost all tested queries.}, address = {New York, NY, USA}, author = {Wu, Baoning and Davison, Brian D.}, booktitle = {WWW '05: Special interest tracks and posters of the 14th international conference on World Wide Web}, citeulike-article-id = {359677}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1062762}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1062745.1062762}, doi = {10.1145/1062745.1062762}, isbn = {1-59593-051-5}, keywords = {hits, link-analysis, pagerank, spam}, location = {Chiba, Japan}, pages = {820--829}, posted-at = {2009-10-21 04:42:55}, priority = {2}, publisher = {ACM}, title = {Identifying link farm spam pages}, url = {http://dx.doi.org/10.1145/1062745.1062762}, year = {2005} }

TY - CONF ID - citeulike:359677 L3 - citeulike-article-id:359677 N2 - With the increasing importance of search in guiding today's web traffic, more and more effort has been spent to create search engine spam. Since link analysis is one of the most important factors in current commercial search engines' ranking systems, new kinds of spam aiming at links have appeared. Building link farms is one technique that can deteriorate link-based ranking algorithms. In this paper, we present algorithms for detecting these link farms automatically by first generating a seed set based on the common link set between incoming and outgoing links of Web pages and then expanding it. Links between identified pages are re-weighted, providing a modified web graph to use in ranking page importance. Experimental results show that we can identify most link farm spam pages and the final ranking results are improved for almost all tested queries. CY - Chiba, Japan SN - 1-59593-051-5 AD - New York, NY, USA EP - 829 TI - Identifying link farm spam pages PB - ACM T2 - WWW '05: Special interest tracks and posters of the 14th international conference on World Wide Web SP - 820 KW - hits KW - link-analysis KW - pagerank KW - spam AU - Wu, Baoning AU - Davison, Brian PY - 2005/// UR - http://dx.doi.org/10.1145/1062745.1062762 ER -