Searching Queries Using Feedback Sessions

For a very large query, different users have different search goals when they submit it to a search engine. To improve search engine relevance and user experience, the inference and analysis of user search goals can be convenient, relevance and user experience. Here we provide an overview of the system architecture of proposed feedback session framework with their advantages. Also we have detail deliberate the literature survey. First, we propose a framework based on clustering the proposed feedback sessions to detect different user search goals for a query. Using user click -through logs Feedback sessions are constructed and these sessions can efficiently show the needed information for user. Information needs of users. Second, we propose a novel approach to generate pseudo-documents for better representation of the feedback sessions for clustering second, we propose a novel approach to generate pseudo-documents to better represent the feedback sessions for clustering. Finally, to evaluate the performance of inferring user search goals we propose a new criterion Classified Average Precision (CAP).