Collaboration prediction based on multilayer all-author tripartite citation networks: A case study of gene editing. Issue 1 (February 2023)

• Record Type: Journal Article
• Authors: Wang, Feifei; Dong, Jiaxin; Lu, Wanzhao; Xu, Shuo
• Is Part Of: Journal of informetrics. Volume 17:Issue 1(2023)
• Publication Date: 2023-02
• Subjects: Collaboration prediction -- All-author tripartite citation networks -- Multilayer-node2vec -- Gene editing; Library statistics -- Periodicals; Information science -- Statistical methods -- Periodicals; Bibliometrics -- Periodicals; Bibliothèques -- Statistiques -- Périodiques; Sciences de l'information -- Méthodes statistiques -- Périodiques; Bibliométrie -- Périodiques; 020.727
• DOI: 10.1016/j.joi.2022.101374
• Languages: English
• ISSNs: 1751-1577

Abstract

Highlights: Combining three typical citation relationships (including direct citation, co-citation, and coupling) to predict prospective collaborations based on citation information that reflects the characteristics of scholars' knowledge structure and research habits, is supposed to provide a supplement and extension for traditional implementation. All the traditional link-prediction indexes except RA (Resource Allocation) are lower in accuracy than the similarity collaboration prediction after obtaining the feature vectors by the network representation learning method (Node2vec); the prediction accuracy of multilayer networks is higher than that of the single-layer networks. The multilayer all-author tripartite citation network (Multi-ANWDC) can reveal more of the network topology structure and thus convey more information, making itself an effective method to predict collaboration and inform interdisciplinary cooperation. This paper has attempted the feasible and accurate method for collaboration prediction in the field of gene editing, which can be further applied and generalized to other full-fledged research areas with available comprehensive citation information. Abstract: Academic collaboration prediction is considered to be an important way to help scholars expand their research horizons and explore a vast and suitable range of partners. However, existing studies mainly rely on historical collaborations for future predictions, which has limitations in digging into credible collaboration possibilities in a wide range of cross-disciplinary contexts. In view of this, this study tries to combine three typical citation relationships (including direct citation, co-citation, and coupling) to predict prospective collaborations based on citation information that reflects the characteristics of scholars' knowledge structure and research habits, which is supposed to provide supplement and extension for traditional implementation. To this end, we construct all-author tripartite citation networks based on the bibliographic data in the field of gene editing, and apply the Node2vec and Multi-node2vec algorithms to predict collaborations between authors in both single and multiple layers. According to compare with that of link prediction indicators (including CN, AA, PA and RA, etc.) commonly used for traditional collaboration networks, it is found that the prediction results in the multilayer all-author tripartite citation network should be relatively more accurate. The results will be helpful for scholars in the field of gene editing to explore potential collaborators with an implicit research connection.