WebSIFT : The Web Site Information Filter

Web Usage Mining is the application of data mining techniques to large Web data repositories in order to extract usage patterns. As with many data mining application domains, the identiication of patterns that are considered interesting is a problem that must be solved in addition to simply generating them. A necessary step in identifying interesting results is quantifying what is considered uninteresting in order to form a basis for comparison. Several research eeorts have relied on manually generated sets of uninteresting rules. However, manual generation of a comprehensive set of evidence about beliefs for a particular domain is impractical in many cases. Generally, domain knowledge can be used to automatically create evidence for or against a set of beliefs. For Web Usage Mining, there are three types of domain information available; usage, content, and structure. The Web Site Information Filter (WebSIFT) system uses the content and structure information from a Web site in order to identify potentially interesting results from mining usage data. This paper gives a brief overview of the WebSIFT systems and presents examples of interesting frequent itemsets automatically discovered from real Web data.