A Framework for Measuring the Impact of Web Spam

Abstract Web spam potentially causes three deleterious effects: unnecessary work for crawlers and search engines; diversion of traffic away from legitimate businesses; and annoyance to search engine users through poorer results. Past research on web spam has focused on spamming techniques, spam suppression techniques, and methods for classifying web content as spam or non-spam. Here we focus on the deterioration of search result quality caused by the presence of spam in a countryscale web. We present a framework for measuring the degradation in quality of search results caused by the presence of web spam. We index the 80 million page UK2006 web spam collection on one machine. We trial the proposed framework in an experiment with the UK2006 collection and demonstrate that simple removal of spam pages from result sets can increase result quality. We conclude that the framework is a reasonable vehicle for research in this area and outline changes necessary for planned future experiments