C-Rank: A Contribution-Based Ranking Approach Exploiting Links and Content

Abstract

This paper addresses the problem in Web page ranking of effectively combining link and content information with efficiency high enough to be applicable to real-world search engines. Unlike previous surfer models, our approach is based on the viewpoint of a Web page author. Based on this viewpoint, we formulate the concept of contribution score, which indicates the amount to which a term in each page is utilized by other pages. To improve efficiency without loss of effectiveness, we exploit the expectations of both a Web page author and a Web search engine user on retrieval results, and restrict candidate terms that can contribute to other pages to a set of keywords of each page. In this paper, we propose three contribution-based models: C-Rank, PC-Rank and HC-Rank. Experimental results show that C-Rank provides the best precision among the models and is very effective for topic distillation tasks on the .GOV collection in TREC. Most importantly, the proposed models are efficient enough to be applicable to real-world search engines.