Measuring author influence in scientific collaboration networks
CHEN Weijing; ZHENG Ying; Zheng Ying (E-mail: zhengy@clas.ac.cn)
2013-12-25
Source PublicationChinese Journal of Library and Information Science
ISSN1674-3393
Volume6Issue:4Pages:55-65
Abstract
Purpose: The purpose of this paper is to measure author influence in scientific collaboration networks by considering the combined effects of multiple indexes. In the meanwhile, we intend to explore a method to avoid assigning subjective weights.

Design/methodology/approach: We applied four centrality measures (degree centrality, betweenness centrality, closeness centrality and eigenvector centrality) and authors' published papers to the scientific collaboration network. The grey relational analysis (GRA) method based on information entropy was used to measure an author's impact in the collaboration network. The weight of each evaluation index was determined based on information entropy. The ACM SIGKDD collaboration network was selected as an example to demonstrate the practicality and effectiveness of our method.

Findings: Author influence was not always positively correlated with evaluation indexes such as degree centrality and betweenness centrality. This implies that combined effects of multiple indexes should be considered in author impact analysis. The introduction of the GRA method based on information entropy can reduce the interference of human factors in the evaluation process.

Research limitations: We only analyzed author influence from the perspective of scientific collaboration, but the impact of citation on author influence was ignored.

Practical implications: The proposed method can be also applied to detect influential authors in bibliographic co-citation network, author co-citation network, bibliographic coupling network or author coupling network. It would help facilitate scientific collaboration and enhance scholarly communication.

Originality/value: This paper proposes an analytical method of evaluating author influence in scientific collaboration networks, in which combined effects of multiple indexes are considered and the interference of human factors is reduced in the evaluation process.
;
Purpose: The purpose of this paper is to measure author influence in scientific collaboration networks by considering the combined effects of multiple indexes. In the meanwhile, we intend to explore a method to avoid assigning subjective weights.

Design/methodology/approach: We applied four centrality measures (degree centrality, betweenness centrality, closeness centrality and eigenvector centrality) and authors' published papers to the scientific collaboration network. The grey relational analysis (GRA) method based on information entropy was used to measure an author's impact in the collaboration network. The weight of each evaluation index was determined based on information entropy. The ACM SIGKDD collaboration network was selected as an example to demonstrate the practicality and effectiveness of our method.

Findings: Author influence was not always positively correlated with evaluation indexes such as degree centrality and betweenness centrality. This implies that combined effects of multiple indexes should be considered in author impact analysis. The introduction of the GRA method based on information entropy can reduce the interference of human factors in the evaluation process.

Research limitations: We only analyzed author influence from the perspective of scientific collaboration, but the impact of citation on author influence was ignored.

Practical implications: The proposed method can be also applied to detect influential authors in bibliographic co-citation network, author co-citation network, bibliographic coupling network or author coupling network. It would help facilitate scientific collaboration and enhance scholarly communication.

Originality/value: This paper proposes an analytical method of evaluating author influence in scientific collaboration networks, in which combined effects of multiple indexes are considered and the interference of human factors is reduced in the evaluation process.
KeywordScientific Collaboration Networks Academic Influence Entropy Weight Method Grey Relational Analysis (Gra)
Subject Area编辑出版
URL查看原文
Document Type期刊论文
Identifierhttp://ir.las.ac.cn/handle/12502/6706
CollectionJournal of Data and Information Science_Chinese Journal of Library and Information Science-2013
Corresponding AuthorZheng Ying (E-mail: zhengy@clas.ac.cn)
Recommended Citation
GB/T 7714
CHEN Weijing,ZHENG Ying,Zheng Ying . Measuring author influence in scientific collaboration networks[J]. Chinese Journal of Library and Information Science,2013,6(4):55-65.
APA CHEN Weijing,ZHENG Ying,&Zheng Ying .(2013).Measuring author influence in scientific collaboration networks.Chinese Journal of Library and Information Science,6(4),55-65.
MLA CHEN Weijing,et al."Measuring author influence in scientific collaboration networks".Chinese Journal of Library and Information Science 6.4(2013):55-65.
Files in This Item: Download All
File Name/Size DocType Version Access License
Weijing CHEN.pdf(2942KB) 开放获取View Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[CHEN Weijing]'s Articles
[ZHENG Ying]'s Articles
[Zheng Ying (E-mail: zhengy@clas.ac.cn)]'s Articles
Baidu academic
Similar articles in Baidu academic
[CHEN Weijing]'s Articles
[ZHENG Ying]'s Articles
[Zheng Ying (E-mail: zhengy@clas.ac.cn)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[CHEN Weijing]'s Articles
[ZHENG Ying]'s Articles
[Zheng Ying (E-mail: zhengy@clas.ac.cn)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Weijing CHEN.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.