Agent-Based Simulations of Online Political Discussions: A Case Study on Elections in Germany
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915236665098240 |
|---|---|
| author | Sittar, Abdul Münker, Simon Sartori, Fabio Reitenbach, Andreas Rettinger, Achim Mäs, Michael Guček, Alenka Grobelnik, Marko |
| author_facet | Sittar, Abdul Münker, Simon Sartori, Fabio Reitenbach, Andreas Rettinger, Achim Mäs, Michael Guček, Alenka Grobelnik, Marko |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_24199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agent-Based Simulations of Online Political Discussions: A Case Study on Elections in Germany Sittar, Abdul Münker, Simon Sartori, Fabio Reitenbach, Andreas Rettinger, Achim Mäs, Michael Guček, Alenka Grobelnik, Marko Artificial Intelligence Computers and Society 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. |
| title | Agent-Based Simulations of Online Political Discussions: A Case Study on Elections in Germany |
| topic | Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2503.24199 |