Use link-based clustering to improve Web search results

Abstract

While Web search engines can retrieve information on the Web for a specific topic, users have to step a long ordered list in order to locate the needed information, which is often tedious and less efficient. We propose a new link-based clustering approach to cluster search results returned from Web search engines by exploring both co-citation and coupling. Unlike document clustering algorithms in IR that are based on common words/phrases shared among documents, our approach is based on common links shared by pages. We also extend the standard clustering algorithm, K-means, to make it more natural to handle noise and apply it to Web search results. By filtering some irrelevant pages, our approach clusters high quality pages in Web search results into semantically meaningful groups to facilitate users accessing and browsing. Preliminary experiments and evaluations are conducted to investigate its effectiveness. The experimental results show that link-based clustering of Web search results is promising and beneficial.