How will the reputations of individuals in a social network be in uenced by their communities in a quantitative way? This work attempts to observe the collaborative events occurring at individuals involved in a social network to obtain such crucial knowledge. We propose a Factorization Machine approach to nd out the latent social in uence among the individuals based on their collaborations. Experiments conducted on a real-world DBLP dataset verify that the proposed approach can discover the latent social in uence among individuals and provide a better predictive model than several baselines.
Proceedings of the 2015 ACM Web Science (WebSci '15), 2015