Applications of link prediction in social networks: A review

Abstract Link prediction methods anticipate the likelihood of a future connection between two nodes in a given network. The methods are essential in social networks to infer social interactions or to suggest possible friends to the users. Rapid social network growth trigger link prediction analysis to be more challenging especially with the significant advancement in complex social network modeling. Researchers implement numerous applications related to link prediction analysis in different network contexts such as dynamic network, weighted network, heterogeneous network and cross network. However, link prediction applications namely, recommendation system, anomaly detection, influence analysis and community detection become more strenuous due to network diversity and complex and dynamic network contexts. In the past decade, several reviews on link prediction were published to discuss the algorithms, state-of-the-art, applications, challenges and future directions of link prediction research. However, the discussion was limited to physical domains and had less focus on social network perspectives. To reduce the gap of the existing reviews, this paper aims to provide a comprehensive review and discuss link prediction applications in different social network contexts and analyses, focusing on social networks. In this paper, we also present conventional link prediction measures based on previous researches. Furthermore, we introduce various link prediction approaches and address how researchers combined link prediction as a base method to perform other applications in social networks such as recommender systems, community detection, anomaly detection and influence analysis. Finally, we conclude the review with a discussion on recent researches and highlight several future research directions of link prediction in social networks.