Web clustering using social bookmark data regarding user network

Social bookmark services are Web services which enable users to share their personal bookmark data with other users. In our research, we propose a web clustering method in a social bookmark service using bookmark data modified with user network data. We define bookmark data as pairs consisting of a user and a web page with bookmarks, and user network data as links between users and their favorite users. In more detail, we use probabilistic latent semantic indexing (PLSI), which makes it possible to project social bookmark data on a latent semantic space and classify them by their semantic attributes. Using PLSI, we can classify web pages according to their topics, and for a user network, we can append all bookmark data of users who are reachable by a given user to that user's bookmark data. To confirm the effectiveness of our proposed clustering method, we evaluated a clustering examination using real social bookmark data. The results confirmed that our proposed method is capable of producing comparable results in the classification of web pages by topic. © 2013 Wiley Periodicals, Inc. Electron Comm Jpn, 96(3): 24–30, 2013; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ecj.11450