# Agent-Based Simulations of Online Political Discussions: A Case Study on Elections in Germany

arXiv: https://arxiv.org/abs/2503.24199 · HTML: https://mlsanity.com/paper/2503.24199/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 7 of 7)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [Simulating Rumor Spreading in Social Networks using LLM Agents](https://mlsanity.com/paper/2502.01450/) (2025)
- [A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses](https://mlsanity.com/paper/2501.01849/) (2025)
- [Measuring user influence on Twitter: A survey](https://mlsanity.com/paper/1508.07951/) (2015)
- [Performant LLM Agentic Framework for Conversational AI](https://mlsanity.com/paper/2503.06410/) (2025)

## Built on by (most cited first, 1 of 1)

- [Predicting, Evaluating, and Explaining Top Misinformation Spreaders via Archetypal User Behavior](https://mlsanity.com/paper/2608.16323/) (2026)

## Abstract (arXiv)

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.