Web Usage Multi-Level Data Mining

Abstract

With the huge amount of information available online, the World Wide Web is a fertile area for data mining research. The web mining research is at the cross road of research from several research communities such as database, information retrieval etc. With the possibility of world wide access current Web applications have an almost unlimited amount of potential users. Methods of data mining can be used to classify the user groups and to learn from their behaviour. With the collected information changes and optimizations can be applied to the Web application to hit the user’s requirements. One already established method for data mining is Web usage mining. Web usage mining is based on the logging information that is generated by the Web server when the user clicks through the site. A new approach that offers more flexibility as presented in this paper is multi-level data mining. It takes advantage of the several layers in a Web application. Guidelines that may be regarded as good practice in the field of data tracking will be introduced in this paper.