Agent-Based Simulations of Online Political Discussions: A Case Study on Elections in Germany
This work addresses the problem of understanding online political discourse dynamics for researchers and policymakers, but it is incremental as it applies existing simulation methods to a specific case study.
The study tackled modeling user engagement in online political discussions by developing an agent-based simulation that incorporates historical context, motivation, and constraints, using German Twitter data to fine-tune AI models for generating posts and replies. The results showed the impact of historical context on AI-generated responses and how engagement evolves under varying constraints, though no concrete numbers were provided.
User engagement on social media platforms is influenced by historical context, time constraints, and reward-driven interactions. This study presents an agent-based simulation approach that models user interactions, considering past conversation history, motivation, and resource constraints. Utilizing German Twitter data on political discourse, we fine-tune AI models to generate posts and replies, incorporating sentiment analysis, irony detection, and offensiveness classification. The simulation employs a myopic best-response model to govern agent behavior, accounting for decision-making based on expected rewards. Our results highlight the impact of historical context on AI-generated responses and demonstrate how engagement evolves under varying constraints.