Exploring Protest-Related Social Network Dynamics: Combining the Power of Big-Data with Agent-Based Simulation

Abstract

While social media usage has taken a prominent role in large social movements, societal constraints are catching up with privacy and transparency in preparation and coordination. To cope with this problem, we propose a method combining agent-based simulation and big data analysis to gain insight into upcoming protests while ensuring a well-weighted and clean analysis process. This simulation method aims to strengthen the information position of governmental officials in advance of a large-scale protest to allocate resources better and take suitable measures to ensure public safety while reducing the preliminary privacy invasive interventions. The proposed method is tested on a real-world case study where posts from Black Lives Matter protests are used to simulate social interaction in advance. Results show that behavioural constructs such as the spillover effect can be predicted based on previous data, contributing to gaining information from a wider perspective.