ABSTRACT

Web logs take an important role to know about user behavior. Several pattern mining techniques were developed to understand the user behavior. A specific kind of preprocessing technique improves the quality and accuracy of the pattern mining algorithms. The existing algorithms have done the preprocessing activities for reducing the size of the log file and to identify the number of unique users and sessions. In order to identify the user interest level and group similar kind of users, User Interest Level Preprocessing (UILP) algorithm is newly proposed. This paper discusses the basics of web log preprocessing, existing preprocessing techniques, the proposed UILP algorithm and performance of the proposed UILP algorithm with existing algorithms to identify user interest level.