Improving web search through collaborative query recommendation

Abstract. Search engines are the primary means by which people locate information on the Web. Unfortunately most Web users are not information retrieval experts and there is a tendency for Web queries to be ambiguous and under-specified. Query expansion and recom-mendation techniques offer one way to solve the ambiguous query problem in Web search, by automatically identifying and adding new terms to a vague query in order to focus the search. In this paper we describe and evaluate a novel query recommendation technique based on reusing previous search histories. This is achieved by select-ing, ranking, and then recommending previously successful queries to users. Its novelty stems from the way in which queries are scored and ranked using relevance and coverage factors in order to priori-tise those queries that are most likely to be successful in the current search context. We demonstrate that these recommendations can lead to improved search performance based on live-user data.