Tie Persistence in Academic Social Networks

This paper attempts to shed light on the importance of some social academic-related factors in determining the strength of links in academic social networks. Our purpose is to assess the extent to which the frequency of the tie, the academic closeness between its actors, and the scientific contributions of the actors in the tie can affect the scientific collaboration relationship between them. We propose a model that relies on this three link strength indicators in order to predict the tie persistence in academic social networks. We experimented the model on a social network extracted from the DBLP computer science bibliographic network. We compared the output of the model with that of the link prediction baseline methods. The results show better performance of the proposed model.