An empirical study on selectiviey of retweeting behaviors under multiple exposures in social networks

摘要

Retweeting is an important behavior in social networks. A user might be exposed to a message multiple times by different followees before retweeting it. Selecting a followee as the predecessor of this message has a direct impact on the formation of retweeting relationships. In this paper, we perform an empirical study on Sina Weibo to understand the selectivity of retweeting behaviors. We find that social influence is more important than homophily in a user's selection decision. We then propose an individual interaction model to infer which followee user will choose. Experimental results show that our model achieves better precision compared with other existing models. (C) 2017 Published by Elsevier B.V.