COMPARISON OF DECISION AND RANDOM TREE ALGORITHMS ON A WEB LOG DATA FOR FINDING FREQUENT PATTERNS

A.Jameela, P.Revathy

Abstract: Web mining is the process of analyzing and extracting useful knowledge from web data. Web mining is divided into three categories namely web content mining, web structure mining and web usage mining. Web content mining is the process of extracting useful information from the web document. Web structure mining is used to identify the relationship between the web pages. Web usage mining is the process of extracting knowledge from the web log data. Web log data is classified into three, namely Client Log, Proxy Log and Web Server Log. In this paper NASA Web log data for the first 10 days are considered which consist of attributes like date, time, client and server IP address, user authentication, server port and method and URI. The web log data is preprocessed. Two more attributes user and session are added. The preprocessed data is classified using classification algorithms like decision and random tree. The useful information like frequently used web pages and no. of unique users are mined. The unique users and web pages in the forenoon and afternoon are classified. The performance evaluation between decision tree and random tree are drawn graphically.

Keywords: web mining, web usage mining, classification.

DOI: https://doi.org/10.15623/ijret.2014.0319029