Abstract

As a powerful gatekeeper, social media platforms face significant challenges from coordinated disinformation campaigns. Despite the growing challenges, little is known about malicious actors that participate in these campaigns and how they operate and leverage the propagation of the content. Building upon network theory, we analyzed a corpus of about thirty million tweets from malicious actors, flagged by the social media platform, across twelve different campaigns. Our analysis of behavioral and network features of the malicious users revealed seven user clusters. We intend to extend our analysis by investigating the propagation impact of these seven user types, the effectiveness of their messaging strategies, and the features of their user network interactions. Our work provides an in-depth and comprehensive definition and features of malicious actors in social media platform that not only enriches our current understanding but also guide the platform to develop effective strategies to mitigate their impact.

Share

COinS