Research on Model of Web Pages Clustering

Web pages clustering is to divide different web pages into different classes according to traveling information of users so as to recommend relative pages to a user when the user is searching a website for his expectant information and to push relative pages to a user when the user is browsing one page. A similarity matrix, which shows similarity degree for any two pages in a website, is constructed according to users traveling paths to implement web pages clustering. A directional graph is created according to the users traveling paths at first and then a usage similarity matrix is constructed according to the directional graph. Structure disintegration model is adopted to analyze the similarity matrix and to transform the matrix into a catercorner matrix or a nether triangle matrix, which shows web pages clustering classes and relations among these classes.The original publication is available at JAIST Press http://www.jaist.ac.jp/library/jaist-press/index.htmlIFSR 2005 : Proceedings of the First World Congress of the International Federation for Systems Research : The New Roles of Systems Sciences For a Knowledge-based Society : Nov. 14-17, 2138, Kobe, JapanSymposium 6, Session 6 : Vision of Knowledge Civilization Society and Knowledg