Adaptive Web Search based on User Web Log

Abstract Web usage mining is a method to extract meaningful patterns based on the web users' log data. Most existing patterns of web usage mining, however, do not consider the users' diverse inclination but create general models. Web users' keywords can have a variety of meanings regarding their tendency and background knowledge. This study evaluated the extraction web-user’s pattern after collecting and analyzing the web usage information onthe users' keywords of interest. Web-user’s pattern can supply a web page network with various inclination information based on the users' keywords of interest. In addition, the Web-user’s pattern can be used to recommendthe most appropriate web pages and the suggested method of this experiment was confirmed to be useful. Key Words : Web Mining, User Modeling, Pattern extraction 본 논문은 2013년 서일대학교 교내연구과제로 수행되었음. * Corresponding Author : Taebok Yoon(Seoil Univ.)Tel: +82-2-490-7441 email: tbyoon@seoil.ac.krReceived August 26, 2014 Revised September 11, 2014 Accepted November 6, 2014