Incremental C-Rank: An effective and efficient ranking algorithm for dynamic Web environments

Abstract

Abstract Web page ranking is one of the core components of search engines. Given a user query, ranking aims to provide a ranked list of Web pages that the user is likely to prefer the most. By and large, the ranking algorithms can be categorized into content-based approaches, link-based approaches, and hybrid approaches. Hybrid ranking algorithms, which exploit both the content and link information, are the most popular and extensively studied techniques. Among the hybrid algorithms, C-Rank combines content and link information in a very effective way using the concept of contribution. This algorithm is known to provide high performance in terms of both accurate and prompt responses to user queries. However, C-Rank suffers from very high costs to reflect the highly dynamic and extremely frequent changes in the World Wide Web, because it re-computes all of the C-Rank scores used for ranking from scratch to reflect the changes. As a result, C-Rank may be considered inappropriate to provide users with accurate and up-to-date search results. This paper aims to remedy this limitation of C-Rank. We propose incremental C-Rank, which is designed to update the C-Rank scores of only a carefully chosen portion of the Web pages rather than those of all of the Web pages without any accuracy loss. Our experimental results on a real-world dataset confirm both the effectiveness and efficiency of our proposed method.