Constructing multi-granular and topic-focused web site maps

Abstract

Site maps are essential to assist users in navigating a Web site. Most of the site maps are constructed manually and are static. However, di erent users may have di erent preferences and purposes for using a Web site. For example, a user may want to see a more detailed map while another user prefers a more abstract map. Two users looking for di erent topics at a large portal site would bene t more from two site maps with di erent focuses than a single map. In this paper, we present a technique for automatically constructing multi-granular and topic-focused site maps by utilizing directory paths, page contents, and link structures. In these site maps, the Web site topology is preserved and document importance, indicated by citation and semantic relevancy to user's topics of interest, is used for prioritizing the presentation of pages and directories. Experiments on real Web data have been conducted to validate the usefulness of the technique.