Measuring coordinated versus spontaneous activity in online social movements

Abstract

Social media platforms provide people all over the world with an unprecedented ability to organize around social and political causes. However, these same platforms enable organized actors to engineer fabricated social movements to advance their agenda. Such movements leverage a variety of tools and techniques, ranging from simple spam operations to sophisticated efforts involving numerous orchestrated accounts coordinated across linguistic and cultural clusters. While the former category is straightforward to analyze via data mining methods, campaigns in the latter category are engineered to mask their true nature from the public. We build on existing work to formalize a framework to detect coordination phenomena in the second category, based on anomalies in three key dimensions of participant behavior: network, temporal, and semantic. We test this framework on three case studies and find that, in all three cases, the framework enables us to detect coordination as behavioral anomaly.