https://doi.org/10.1140/epjds/s13688-025-00593-3
Research
Simulating conversations on social media with generative agent-based models
1
School of Industrial and Information Engineering, Politecnico di Milano, Milan, Italy
2
Institute of Mathematical and Computational Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile
3
Department of Computer Science, School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile
4
National Center of Artificial Intelligence (CENIA), Santiago, Chile
5
Millennium Institute for Foundational Research on Data (IMFD), Santiago, Chile
6
School of Informatics Engineering, Universidad de Valparaíso, Valparaíso, Chile
7
École Polytechnique, Paris, France
8
Department of Computer Science, Universidad de Chile, Santiago, Chile
Received:
2
January
2025
Accepted:
4
October
2025
Published online:
11
November
2025
Large Language Models (LLMs) can generate realistic text resembling human-produced content. However, the ability of these models to simulate conversations on social media is still less explored. To investigate the potential and limitations of simulated text in this domain, we introduce network-simulator, a system to simulate conversations on social media. First, we simulate the macro structure of a conversation using Agent-Based Modeling (ABM). The generated structure defines who interacts with whom, the type of interaction, and the agent’s stance on the topic of the conversation. Subsequently, using the simulated interaction structure, our system generates prompts conditioned on the simulation variables, producing texts that are conditioned on the parameters of the predefined structure, guiding a micro simulation process. We compare human conversations with those simulated by our system. Based on stylistic and model-based metrics, we found that our system can simulate conversations on social media in various dimensions. However, we detected differences in metrics related to the predictability of text production. Furthermore, we examine the effect of true and false framings within simulated conversations, revealing that simulated discussions surrounding false information exhibit a more negative collective sentiment bias than those based on true content.
Key words: Large language Models / Agent-based Modeling / Online Conversations
Supplementary Information The online version contains supplementary material available at https://doi.org/10.1140/epjds/s13688-025-00593-3.
© The Author(s) 2025
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
