Knowledge Commons of National Science Library,CAS
Predictive Characteristics of Co-authorship Networks: Comparing the Unweighted, Weighted, and Bipartite Cases | |
Raf Guns; Raf Guns (E-mail: raf.guns@uantwerpen.be). | |
2016-09-18 | |
Source Publication | Journal of Data and Information Science
![]() |
Volume | 1Issue:3Pages:59-78 |
Abstract |
Purpose: This study aims to answer the question to what extent different types of networks can be used to predict future co-authorship among authors. ; Design/methodology/approach: We compare three types of networks: unweighted networks, in which a link represents a past collaboration; weighted networks, in which links are weighted by the number of joint publications; and bipartite author-publication networks. The analysis investigates their relation to positive stability, as well as their potential in predicting links in future versions of the co-authorship network. Several hypotheses are tested. Findings: Among other results, we find that weighted networks do not automatically lead to better predictions. Bipartite networks, however, outperform unweighted networks in almost all cases. Research limitations: Only two relatively small case studies are considered. Practical implications: The study suggests that future link prediction studies on co-occurrence networks should consider using the bipartite network as a training network. Originality/value: This is the first systematic comparison of unweighted, weighted, and bipartite training networks in link prediction.
Purpose: This study aims to answer the question to what extent different types of networks can be used to predict future co-authorship among authors. Design/methodology/approach: We compare three types of networks: unweighted networks, in which a link represents a past collaboration; weighted networks, in which links are weighted by the number of joint publications; and bipartite author-publication networks. The analysis investigates their relation to positive stability, as well as their potential in predicting links in future versions of the co-authorship network. Several hypotheses are tested. Findings: Among other results, we find that weighted networks do not automatically lead to better predictions. Bipartite networks, however, outperform unweighted networks in almost all cases. Research limitations: Only two relatively small case studies are considered. Practical implications: The study suggests that future link prediction studies on co-occurrence networks should consider using the bipartite network as a training network. Originality/value: This is the first systematic comparison of unweighted, weighted, and bipartite training networks in link prediction. |
Subtype | Research Papers |
Keyword | Network Evolution Link Prediction Weighted Networks Bipartite Networks Two-mode Networks |
Subject Area | 新闻学与传播学 ; 图书馆、情报与文献学 |
DOI | 10.20309/jdis.201620 |
URL | 查看原文 |
Indexed By | 其他 |
Language | 英语 |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.las.ac.cn/handle/12502/8732 |
Collection | Journal of Data and Information Science_Journal of Data and Information Science-2016 |
Corresponding Author | Raf Guns (E-mail: raf.guns@uantwerpen.be). |
Affiliation | Centre for R&D Monitoring (ECOOM), University of Antwerp, Antwerp 2020, Belgium |
Recommended Citation GB/T 7714 | Raf Guns,Raf Guns . Predictive Characteristics of Co-authorship Networks: Comparing the Unweighted, Weighted, and Bipartite Cases[J]. Journal of Data and Information Science,2016,1(3):59-78. |
APA | Raf Guns,&Raf Guns .(2016).Predictive Characteristics of Co-authorship Networks: Comparing the Unweighted, Weighted, and Bipartite Cases.Journal of Data and Information Science,1(3),59-78. |
MLA | Raf Guns,et al."Predictive Characteristics of Co-authorship Networks: Comparing the Unweighted, Weighted, and Bipartite Cases".Journal of Data and Information Science 1.3(2016):59-78. |
Files in This Item: | Download All | |||||
File Name/Size | DocType | Version | Access | License | ||
20160305.pdf(1258KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Download |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment