Hybrid Query Session and Content-based Recommendations for Enhanced Search

This paper presents a simple and intuitive method for mining search engine query logs to get fast query recommendations on a large scale industrial-strength search engine. In order to get a comprehensive solution, we combine two methods together. First, we study and model search engine users´ sequential search behavior, and interpret this consecutive search behavior as client-side query refinement, that should form the basis for the search engine´s own query refinement process. This query refinement process is exploited to learn useful relations and build fuzzy associative memories that help generate related queries via a fuzzy inference process. Second, we combine this method with a traditional content based similarity method to compensate for the high sparsity of real query log data, and more specifically, the shortness of most query sessions.