LAUSR

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.