关键词: Web日志 Web用户 概率潜在语义分析 聚类

Abstract:

With the rapid increase of web pages on the Intemet, we can improve the efficiency of information searching and personalized services by performing a clustering analysis of the browsed records. Based on the information theory, the local weight and global weight are considered in the calculation of the weights in the session-page matrix. Based on the probabilistic latent semantic analysis, the conditional probability of the latent variable Z to page P  is transformed into the conditional probability of the latent variable Z to session S. And then the transformed results are used in similarity calculat ion. The k-medoids algorithm is adopted to further improve the clursting results. Experimental results verify the validity and limitation of this algori  thm.

Key words: web log, web user, PLSA, clustering