Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910098449760256 |
|---|---|
| author | Composta, Elisa Fontana, Nicolo' Corso, Francesco Pierri, Francesco |
| author_facet | Composta, Elisa Fontana, Nicolo' Corso, Francesco Pierri, Francesco |
| contents | Online social networks offer a valuable lens to analyze both individual and collective phenomena. Researchers often use simulators to explore controlled scenarios, and the integration of Large Language Models (LLMs) makes these simulations more realistic by enabling agents to understand and generate natural language content. In this work, we investigate the behavior of LLM-based agents in a simulated microblogging social network. We initialize agents with realistic profiles calibrated on real-world online conversations from the 2022 Italian political election and extend an existing simulator by introducing mechanisms for opinion modeling. We examine how LLM agents simulate online conversations, interact with others, and evolve their opinions under different scenarios. Our results show that LLM agents generate coherent content, form connections, and build a realistic social network structure. However, their generated content displays less heterogeneity in tone and toxicity compared to real data. We also find that LLM-based opinion dynamics evolve over time in ways similar to traditional mathematical models. Varying parameter configurations produces no significant changes, indicating that simulations require more careful cognitive modeling at initialization to replicate human behavior more faithfully. Overall, we demonstrate the potential of LLMs for simulating user behavior in social environments, while also identifying key challenges in capturing heterogeneity and complex dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18985 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data Composta, Elisa Fontana, Nicolo' Corso, Francesco Pierri, Francesco Social and Information Networks Online social networks offer a valuable lens to analyze both individual and collective phenomena. Researchers often use simulators to explore controlled scenarios, and the integration of Large Language Models (LLMs) makes these simulations more realistic by enabling agents to understand and generate natural language content. In this work, we investigate the behavior of LLM-based agents in a simulated microblogging social network. We initialize agents with realistic profiles calibrated on real-world online conversations from the 2022 Italian political election and extend an existing simulator by introducing mechanisms for opinion modeling. We examine how LLM agents simulate online conversations, interact with others, and evolve their opinions under different scenarios. Our results show that LLM agents generate coherent content, form connections, and build a realistic social network structure. However, their generated content displays less heterogeneity in tone and toxicity compared to real data. We also find that LLM-based opinion dynamics evolve over time in ways similar to traditional mathematical models. Varying parameter configurations produces no significant changes, indicating that simulations require more careful cognitive modeling at initialization to replicate human behavior more faithfully. Overall, we demonstrate the potential of LLMs for simulating user behavior in social environments, while also identifying key challenges in capturing heterogeneity and complex dynamics. |
| title | Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data |
| topic | Social and Information Networks |
| url | https://arxiv.org/abs/2509.18985 |