location: Current position: Home >> Scientific Research >> Paper Publications

A novel soft clustering algorithm

Hits:

Indexed by:会议论文

Date of Publication:2011-01-01

Included Journals:CPCI-S、Scopus

Volume:15

Page Number:5536-5540

Key Words:citation network; complex priority; soft clustering; thegrouth theorem

Abstract:Paper clustering problems in citation network is one of the hottest spots in data mining. However, traditional paper clustering algorithm stresses on the keywords analysis while ignores the "refer-to" relationship, which results in the problem of high time complexity and low accuracy. In this paper, we come up with a novel soft clustering algorithm in accordance with the complex priority and thegrouth theorem, and classify our algorithm into two steps: refer-to relationship analysis and keywords comparison. Experimental results show that our algorithm is able to greatly improve the search accuracy and efficiency. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of [CEIS 2011]

Pre One:关于高水平本科生培养的一点思考

Next One:Role assorted community discovery for weighted networks