Semiautomatic Extraction of Topic Maps from Web Pages Using Clustering with Web Contents and Structure

摘要

In this paper, we describe a method to semi-automatically extract Topic Maps from a set of Web pages. We introduce the following two points to the existing clustering method: The first is merging only the linked Web pages, to extract the underlying relationship of the topics. The second is introducing the similarity by contents of Web pages and the types of links, and the distance between the directories in which the pages are located, to generate dense clusters. We generate the topic map by assuming the clusters as topics, the edges as associations, the Web pages related to the topic as occurrences from the result of clustering. We experimentally extracted the topic map and evaluated it.