A Framework for Automatic Topic Discovery on subWebs

As the amount of available information on the Internet has become huge, it has become increasingly difficult for users to find information that is relevant to their needs. This has necessitated automated tools that can help users find information they need quickly and easily. In this paper, we propose a methodology for automatically finding topics of interest to users through related subWebs (subdirectories of a Web site). The methodology consists of a subWeb mining framework that performs parsing, clustering, and analysis of subWebs, and a ranking algorithm for the clusters.