A rough set approach to identify content and navigational pages at a website

摘要

Web Usage Mining also known as Web Log Mining provides immense information about user traffic and behavior at a web site. In a web site, the users may spend different time for viewing different pages. The aim of this paper is to identify the content and navigational pages in a web site based on rough set approach to identify potential pages. Identifying content pages is useful in target advertising which may bring increased revenue to the advertisers. The reference length on each page also leads to the discovery of most preferred content by a user. We also intend to see whether the content pages varies with time.