Self-organizing map based web pages clustering using web logs

A Web-based business always wants to have the ability to track users’ browsing behavior history. This ability can be achieved by using Web log mining technologies. In this paper, we introduce a Self-Organizing Map (SOM) based approach to mining Web log data. The SOM network maps the web pages into a two-dimensional map based on the users’ browsing history. Web pages with the similar browsing patterns are clustered together. Together with associate rules, the cluster generated by the SOM network has significant meaning to web browsing behavior. The experimental results demonstrate the feasibility and the effectiveness of this approach.

• Type: Conference
• Year: 2007
• Where: SEDE
• Authors: Dehu Qi, Chung-Chih Li
• Keywords: SEDE 2007, Software Engineering, SOM Network, Web Log, Web Pages