Alleviating negative group polarization with the aid of social bots

Abstract

When group polarization is combined with intense negative emotions, it can have detrimental consequences such as online and offline riots. To address this issue, this paper proposes a framework called MNGP (Mitigating Negative Group Polarization) that utilizes both human guidance and social robot assistance. MNGP comprises three main modules: data collection, data mining, and robot embedding. In the data collection module, relevant data capturing group polarization with negative emotions is collected, filtered, and stored. Subsequently, in the data mining module, user and comment characteristics that can help mitigate group polarization are extracted using a novel depolarization index. Finally, in the robot embedding module, a set of social bots are deployed to emulate these characteristics and post neutral or positive comments under manual supervision. Experimental results demonstrate that, over a span of 28 days, with the assistance of 20 social bots across four topics, there were a total of 1039 user interactions and 2349 comments received. Furthermore, the presence of social bots led to a 20 percent reduction in group polarization compared to scenarios where no bots were utilized.