In recent years, online social networks have become vital platforms for political discussions as well as electoral campaigns. Political organizations have leveraged social media as a tool for distributing information, monitoring public opinion, promoting candidates, and even influencing the election outcomes. To achieve their goals, groups or organizations may purchase or register plenty of accounts, the so-called sockpuppets, to shape the opinion and influence the public atmosphere. In this article, we investigate sockpuppet accounts based on their activity behaviors. A series of user behavior based, network-based, content-based features, and temporal features are proposed and extracted for the classification task. To categorize users into sockpuppets and legitimate users, we employ ensemble learning as well as single classifiers and a thorough evaluation is presented. Experimental results on an officially verified dataset obtained from the largest social forum in Taiwan show that a maximum value of area under the curve score achieves 0.904 via an ensemble learning with feature engineering in our proposal.

Online social media platforms play an important role in political communication where users can freely express and exchange their political opinion. Political entities have leveraged social media platforms as essential channels to disseminate information, interact with voters, and even influence public opinion. For this purpose, some organizations may create one or more accounts to join online political discussions. Using these accounts, they could promote candidates and attack competitors. To avoid such misleading speeches and improve the transparency of the online society, spotting such malicious accounts and understanding their behaviors are crucial issues. In this paper, we aim to use network-based analysis to sense influential human-operated malicious accounts who attempt to manipulate public opinion on political discussion forums. To this end, we collected the election-related articles and malicious accounts from the prominent Taiwan discussion forum spanning from 25 May 2018 to 11 January 2020 (the election day). We modeled the discussion network as a multilayer network and used various centrality measures to sense influential malicious accounts not only in a single-layer but also across different layers of the network. Moreover, community analysis was performed to discover prominent communities and their characteristics for each layer of the network. The results demonstrate that our proposed method can successfully identify several influential malicious accounts and prominent communities with apparent behavior differences from others.

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.