Understanding potential cyber-armies in elections: A study of Taiwan

Currently, online social networks are essential platforms for political organizations to monitor public opinion, disseminate information, argue with the opposition, and even achieve spin control. However, once such purposeful/aggressive articles flood social sites, it would be more difficult for users to distinguish which messages to read or to trust. In this paper, we aim to address this issue by identifying potential "cyber-armies/professional users" during election campaigns on social platforms. We focus on human-operated accounts who try to influence public discussions, for instance, by publishing hundreds/thousands of comments to show their support or rejection of particular candidates. To achieve our objectives, we collected activity data over six months from a prominent Taiwan-based social forum before the 2018 national election and applied a series of statistical analyses to screen out potential targets. From the results, we successfully identified several accounts according to distinctive characteristics that corresponded to professional users. According to the findings, users and platforms could realize potential information manipulation and increase the transparency of the online society.