Predicting happiness contagion on online social networks

In the real world, emotions guide the minds of human beings, which further influences their behaviors. During the recent years, with the increasing popularity of the internet, Online Social Networks (OSNs) have been attracting increasing number of users. It is confirmed that the emotional contagion phenomenon exists in OSNs similar to the real world. This was mostly studied through texts in current researches. Apart from the texts, however, OSNs provide their users several other interaction functions. To understand whether these interaction functions generate various levels of emotional influences to their users, this study investigates Facebook users, through interactions including the posts, number of likes, number of shares, number of fans, and number of comments, to speculate the relevant levels of user happiness. Furthermore, we propose an algorithm to identify the top-n users with the most happiness influences. According to the experimental results, among the Facebook users, various interactions generate different levels of happiness influences on members in its community. The members with a higher level of happiness are also better known in the community. In addition, we experimentally confirm that the proposed algorithm can effectively determine the top-n users of the most happiness influences.