Web mining based on user access patterns for web personalization
Wang Xiao-Gang, Yue Li · 2009
It is usually necessary to model users' Web access behavior to provide intelligent personalized online services such as Web recommendations. One of the promising approaches is Web usage mining, which mines Web logs for user models and recommendations. Different from most Web recommender systems that are mainly based on clustering and association rule mining, this paper proposes an Web personalization system that uses sequential access pattern mining. In the proposed system an efficient sequential pattern-mining algorithm is used to identify frequent sequential Web access patterns. The access patterns are then stored in a compact tree structure, called pattern-tree, which is then used for matching and generating Web links for recommendations. In this paper, the proposed system is described, and its performance is evaluated.