Fast Pattern Discovery Method of Clustering for Web Personalization

Abstract

The World Wide Web is the largest distributed information space and has grown to encompass diverse information resources. Although the web is growing exponentially, the individual's capacity to read and digest content is essentially fixed. The precise analysis of web structure can facilitate data processing and enhance the accuracy of results in the procedures of web personalization. In this paper, an effective and systematic method of Fast Pattern Discovery Method (FPD) to analyze and deal with two steps is discussed. At first, web usage mining satisfies the challenging requirements of web personalization applications. For online and anonymous web personalization to be effective, clustering of personalized data must be accomplished in real time as accurately as possible. On the other hand, Fast Pattern Discovery method should allow a compromise between scalability and accuracy to be applicable to real-life websites with numerous visitors. The personalization of documented information is necessary to mine typical user profiles from vast amount of data stored in access logs and it also defines the temporary compact sequence of web access by a user captured by FPD through personalization information. At the same time, the number of users and the diversity of their interests increase. As a result, providers are seeking ways to infer the users’ interests and to adapt their web sites to make the content of interest more easily accessible. Pattern mining is a promising approach in support of this goal. The past behaviour integrator of the user and the records are kept in the form of access logs, which can be mined to dynamically generate information faster then existing adaptive discovery methods in time.