Website clustering from query graph using social network analysis

Along with informationization advancement thorough and Internet rapid development, there exists millions of websites on the Internet. Search engines become a mediator to connect web users and websites. The query logs in which recorded daily contains a wealth of knowledge about the actions of the users of search engines, and as such they contain valuable information about the interests, the preferences, and the behavior of the users, as well as their implicit feedback to search-engine results. By constructing a novel query graph, considering for the classification of queries, which is utilized to build multi-dimensional vector, we adopt social network analysis method to detect communities in the graph to implement website clustering. Website clustering can contribute to spam website, pornographic website and political sensitive website detection. So it can be applied to websites supervision.