Presentation 2004/7/7
Analyzing Feature of Web Communities Max-Flow vs HITS
Noriko IMAFUJI, Masaru KITSUREGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A web community is a set of web pages created by individuals or associations with a common interest on a topic. Various graph theoretical approaches for extracting web communities from the web have been proposed. Each approach specifies a web community by each distinct graph structure, which is well-founded in the context of the link behavior in the web. In this paper, we focus on the web communities extracted by the two approaches; Max-Flow algorithm based and HITS related algorithm based and identify the feature distinction between them. We first analyze a potential feature on the analogy of the graph structure. Next, we verify it by examining two sets of web communities; approximately 1.32 million Max-Flow communities and 1.2 million HITS based communities. Those communities are extracted from the web graph based on Japanese archives in February 2002.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Web community / maximum flow algorithm / HITS
Paper # DE2004-73
Date of Issue

Conference Information
Committee DE
Conference Date 2004/7/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analyzing Feature of Web Communities Max-Flow vs HITS
Sub Title (in English)
Keyword(1) Web community
Keyword(2) maximum flow algorithm
Keyword(3) HITS
1st Author's Name Noriko IMAFUJI
1st Author's Affiliation Institute of Industrial Science, University of Tokyo()
2nd Author's Name Masaru KITSUREGAWA
2nd Author's Affiliation Institute of Industrial Science, University of Tokyo
Date 2004/7/7
Paper # DE2004-73
Volume (vol) vol.104
Number (no) 177
Page pp.pp.-
#Pages 6
Date of Issue