User Mining to Find Important Facebook Users

Abstract

Social media website such as Facebook have become even more popular. Receiving information from Facebook and generating or spreading information on Facebook every day has become a general lifestyle. The civil movements led by college students were across the globe through the Internet in the past years. In Taiwan, on March 18 2014, some students occupied the Taiwanese Parliament Building in order to resume the negotiation for the Cross-Strait Service Trade Agreement. These students shared information on some social media websites such as Facebook. In this paper, we work on the data of the sunflower student movement and our goal is to mine important users on Facebook. Existing network based approaches proposed to mine important Facebook users in civil movements cannot be applied to our data, because there is no network structure in our data. We use cross-analysis in the mining task. We mine users who change the speed of diffusion of posts as well as find users who share and comment on the maximal posts. We think that these users are important Facebook users. We find that three users are active and important users through sharing-reaction, and we also find that other three users are important users, and they handle comments and draw conclusions.