Extracting Topic Maps from Web Histories by Clustering with Web Structure and Contents
Motohiro Mase, Seiji Yamada · 2006
In this paper, we propose a clustering method to extract topic maps from the Web browsing history. We improve the structure-based hierarchical clustering method using the contents similarity of the pages and the weight by the types of links and the hierarchical difference of the directories in which the pages are located. The topic maps show the topics that user has seen or not in Web browsing and the relationships between the topics. Using the Web browsing history, we experimentally extract the topic map and evaluate it