Extracting Query Expansion Terms Based on User's Search Behavior

Abstract

Search engine(SE) can obtains rich information from the Internet as a powerful tool, but most of them are not relevant to the searcher’s intended requirements. The main factor is query terms can not depict the user’s personality with the ambiguity of the language. To solve this problem, a method of extracting query expansion terms based on user’s behavior is proposed in this paper. The method analyzes their potential relevance of the user's search history and click history. The search return sequence and the user clicks sequence are considered as well. So we can extract terms which can depict the user’s requirements. An experiment illustrates that our method can effectively extract the relevant terms and improves the quality.