A Extraction Method of Overlapping Cluster based on Network Structure Analysis

  • TAKAKI MAKOTO
    Graduate School of Information Sciences, Hiroshima City University JSPS Research Fellow
  • TAMURA KEIICHI
    Graduate School of Information Sciences. Hiroshima City Unievrsity
  • MORI YASUMA
    Graduate School of Information Sciences. Hiroshima City Unievrsity
  • KITAKAMI HAJIME
    Graduate School of Information Sciences. Hiroshima City Unievrsity

Bibliographic Information

Other Title
  • ネットワーク構造解析に基づく重複クラスタ抽出法(セッション3:データマイニング)

Search this article

Description

In this paper, we propose a method of overlapping cluster based on network structure analysis which improves the clustering algorithm proposed by Newman et al. Newman's clustering algorithm is the crisp clustering algorithm. In the proposed technique, first, we cluster the nodes using the Newman's algorithm. Then, we make the contraction graph which is considered a cluster as a node. In addition, we cluster the created contraction graph by using the Newman's clustering algorithm again and identify the overlapping nodes. Overlapping clustering is more flexible than crisp clustering. The experimental results using the trackback data based on blog represented efficacy of proposed technique.

Journal

  • IPSJ SIG Notes

    IPSJ SIG Notes 2007 (54), 39-45, 2007-05-31

    Information Processing Society of Japan (IPSJ)

Details 詳細情報について

  • CRID
    1574231877046935424
  • NII Article ID
    110006292337
  • NII Book ID
    AN10114171
  • Text Lang
    ja
  • Data Source
    • CiNii Articles

Report a problem

Back to top