Query Recommendation Using Large-scale Web Access Logs and Web Page Archive

Abstract. Query recommendation suggests related queries for search engine users when they are not satisfied with the results of an initial in-put query, thus assisting users in improving search quality. Conventional approaches to query recommendation have been focused on expanding a query by terms extracted from various information sources such as a thesaurus like WordNet1, the top ranked documents and so on. In this paper, we argue that past queries stored in query logs can be a source of additional evidence to help future users. We present a query recom-mendation system based on large-scale Web access logs and Web page archive, and evaluate three query recommendation strategies based on different feature spaces (i.e., noun, URL, and Web community). The ex-perimental results show that query logs are an effective source for query recommendation, and the Web community-based and noun-based strate-gies can extract more related search queries than the URL-based one.