In this study, we propose a novel method of mining web usage within a local area network (LAN). The proposed method makes use of Taiwanese Yahoo! (i.e. Yahoo! Kimo) to create a topic hierarchy and classifies the most visited websites for users within a LAN into the hierarchy. Each of the websites will have a unique category path. According to the category path, web usage statistics can be accumulated from the bottommost level, i.e. a single website, to the topmost level, i.e. the set of all

more »

... ites. Thus, web surfing demands of users within the LAN can be analyzed at various levels of detail. Experimental results strongly support the effectiveness of the proposed method. Index Terms-Web usage mining, Yahoo! Directory, Yahoo! Search.