Supervised Link Prediction in Co-Authorship Networks Based on Research Performance and Similarity of Research Interests and Affiliations

Abstract

Predicting the emergence of future research collaborations between authors in academic social network is a very effective example that demonstrates the link prediction problem. This problem refers to predicting the potential existence or absence of link between a pair of nodes in social networks (SN). Since the majority of previous research work on link prediction only considered predictor variables (i.e., features) extracted from SN structure, this paper aims to investigate the impact of using other types of predictor variables on solving link prediction problem in co-authorship network. It proposes a new method for supervised link prediction in co-authorship networks using predictors extracted by: computing the similarity between the research interests of each two author nodes in the network, the similarity between their affiliations, the sum of their research performance indices as well as the similarity between the two author nodes themselves. The preliminary results of our approach show that the sum of research performance indices of two author nodes has the most impact on the performance of supervised link prediction which motivates us to do further analysis on using such a predictor.