Issue No. 03 - March (2002 vol. 35)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/2.989932
<p>Millions of individuals operating independently author the Web's information. Despite its decentralized nature, the authors' work shows that the Web self-organizes and its link structure allows efficient identification of communities. This is significant because no central authority or process governs hyperlink formation and structure.A Web community is a collection of Web pages in which each member page has more hyperlinks within the community than outside it. Compared to previous methods of finding related Web pages,the authors describe an approach that retains the transparency of methods such as cocitation and bibliographic coupling in explaining why pages belong to a community,yet can identify Web communities of arbitrary dimensions. Applications of their method include creating improved search engines, content filtering, and objective analysis of Web content and the relationships between Web communities.</p>
C. L. Giles, G. W. Flake, F. M. Coetzee and S. Lawrence, "Self-Organization and Identification of Web Communities," in Computer, vol. 35, no. , pp. 66-71, 2002.