A Relational Based Fuzzy Clustering to Mine user Profiles for Web Directory Personalization
R. Lokesh Kumar1, T. Gopalakrishnan2, P. Sengottuvelan3
1R. Lokesh Kumar, Department of Information Technology, Bannari Amman Institute of Technology, Sathyamagalam, Tamil Nadu ,India.
2T. Gopalakrishnan, Dept. of Information Technology, Bannari Amman Institute of Technology, Sathyamagalam, Tamil Nadu ,India.
3P. Sengottuvelan ,Dept. of Information Technology, Bannari Amman Institute of Technology, Sathyamagalam, Tamil Nadu ,India.
Manuscript received on May 17, 2012. | Revised Manuscript received on June 12, 2012. | Manuscript published on June 30, 2012. | PP: 228-232 | Volume-1 Issue-5, June 2012. | Retrieval Number: E0484061512/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The log data at a search engine can be used to analyze users’ search behavior and to develop search technologies to improve users’ search experiences. Web usage mining performs mining on web usage data or web logs. A web log is a listing of page reference data/clickstream data. The behavior of the web page readers is imprint in the web server log files. By using the sequence of pages a user accesses, a user profile could be developed thus used in personalization. With personalization, web access or the contents of web page are modified to better fit the desires of the user and also to identify the browsing behavior of the user can improve system performance, enhance the quality and delivery of Internet Information services to the end user, and identify the population of potential customers. For this purpose a new clustering based approach is used, The proposed algorithm finds the meaningful behavior patterns extracted by applying efficient clustering algorithm, to log data. It is proved that performance of the proposed system is better than that of the existing algorithm. The proposed algorithm can provide popular information from web page visitors for web personalization.
Keywords: User profiles, web log data, clustering, Web Personalization.