Abstrato

A Novel Approach for Restructuring Web Search Results by Feedback Sessions Using Fuzzy clustering

R.Dhivya, R.Rajavignesh

Ambiguous queries are submitted in search engine by different users with different search goals. The analysis of user click through logs can be useful in finding the precise search results. The user click through logs contains the information about the user search information. By analyzing the user click through logs the feedback sessions are constructed. The pseudo documents are generated by representing the feedback sessions for clustering. The fuzzy c-means clustering algorithm is used for clustering those pseudo- documents. A novel approach for user and query dependent feedback sessions for user search results. The CAP is formulated to evaluate the performance of user search goal inference. This can be very useful in improving search engine efficiency.