Mining a web citation database for document clustering

The World Wide Web has become an important medium for disseminating scientific publications. Many publications are now made available over the Web. However, existing search engines are ineffective in searching these publications, as they do not index Web publications that normally appear in PDF (Portable Document Format) or PostScript formats. One way to index Web publications is through citation indices, which contain the references that the publications cite. Web Citation Database is a data warehouse to store the citation indices. In this paper, we propose a mining process to extract document cluster knowledge from the Web Citation Database to support the retrieval of Web publications. The mining techniques used for document cluster generation are based on Kohonen's Self-Organizing Map (KSOM) and Fuzzy Adaptive Resonance Theory (Fuzzy ART). The proposed techniques have been incorporated into a citation-based retrieval system known as PubSearch for Web scientific publications.