Combating Web Spam with TrustRank Export

@article{citeulike:843689, abstract = {Web spam pages use various techniques to achieve higher-than-deserved rankings in a search engine's results. While human experts can identify spam, it is too expensive to manually evaluate a large number of pages. Instead, we propose techniques to semi-automatically separate reputable, good pages from spam. We first select a small set of seed pages to be evaluated by an expert. Once we manually identify the reputable seed pages, we use the link structure of the web to discover other pages that are likely to be good. In this paper we discuss possible ways to implement the seed selection and the discovery of good pages. We present results run on the World Wide Web indexed by AltaVista and evalutae the performance of our techniques. Our results show that we can effectively filter out spam from a significant fraction of the web, based on a good seed set of less than 200 sites.}, author = {Gyongyi, Zoltan and Garcia-Molina, Hector and Pedersen, Jan}, booktitle = {Proceedings of the 30th International VLDB Conference}, citeulike-article-id = {843689}, citeulike-linkout-0 = {http://i.stanford.edu/~zoltan/publications/gyongyi2004combating.pdf}, keywords = {networks, reputation}, posted-at = {2006-09-15 01:25:16}, priority = {0}, title = {Combating Web Spam with TrustRank}, url = {http://i.stanford.edu/~zoltan/publications/gyongyi2004combating.pdf}, year = {2004} }

TY - JOUR ID - citeulike:843689 L3 - citeulike-article-id:843689 N2 - Web spam pages use various techniques to achieve higher-than-deserved rankings in a search engine's results. While human experts can identify spam, it is too expensive to manually evaluate a large number of pages. Instead, we propose techniques to semi-automatically separate reputable, good pages from spam. We first select a small set of seed pages to be evaluated by an expert. Once we manually identify the reputable seed pages, we use the link structure of the web to discover other pages that are likely to be good. In this paper we discuss possible ways to implement the seed selection and the discovery of good pages. We present results run on the World Wide Web indexed by AltaVista and evalutae the performance of our techniques. Our results show that we can effectively filter out spam from a significant fraction of the web, based on a good seed set of less than 200 sites. TI - Combating Web Spam with TrustRank T2 - Proceedings of the 30th International VLDB Conference KW - networks KW - reputation AU - Gyongyi, Zoltan AU - Garcia-Molina, Hector AU - Pedersen, Jan PY - 2004/// UR - http://i.stanford.edu/~zoltan/publications/gyongyi2004combating.pdf ER -