Theme-Based Query Expansion by Mining Log Data

Queries committed to the search engines are usually short. They usually contain insufficient information to the IR system. Previous research has proposed the utilization of query expansion to deal with this problem. However, expansion terms are usually determined on term co-occurrences within documents. Sometimes the expansion terms don´t represent the user´s real intent. In this study, we propose a novel method for query expansion based on mining the user´s intent through the click-through data. The users log builds the bridge between the queries and the user´s intent. The experimental results show that the theme-based query expansion method can produce much better results than the classical search method.