Date Added: Mar 2012
Analyzing users' internet log information and extracting their interests of Web-watching behaviors are vital and challenging analysis topics of internet usage mining. Users visit their favorite sites and generally search new sites by performing keyword search on search engines. Users' Web-watching behaviors is considered a graph since visited websites and entered search keywords are connected with one another in an exceedingly time sequence. The authors call this graph a site-keyword graph. This paper describes a method for clarifying users' interests primarily based on an analysis of the site-keyword graph. The strategy is for extracting sub-graphs representing users' main interests from a site-keyword graph that is generated from augmented internet audience measurement information(Weblog data).