MASim: Multilingual Agent-Based Simulation for Social Science
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917132413960192 |
|---|---|
| author | Zhang, Xuan Zhang, Wenxuan Wang, Anxu Ng, See-Kiong Deng, Yang |
| author_facet | Zhang, Xuan Zhang, Wenxuan Wang, Anxu Ng, See-Kiong Deng, Yang |
| contents | Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual and fail to model cross-lingual interaction, an essential property of real societies. We introduce MASim, the first multilingual agent-based simulation framework that supports multi-turn interaction among generative agents with diverse sociolinguistic profiles. MASim offers two key analyses: (i) global public opinion modeling, by simulating how attitudes toward open-domain hypotheses evolve across languages and cultures, and (ii) media influence and information diffusion, via autonomous news agents that dynamically generate content and shape user behavior. To instantiate simulations, we construct the MAPS benchmark, which combines survey questions and demographic personas drawn from global population distributions. Experiments on calibration, sensitivity, consistency, and cultural case studies show that MASim reproduces sociocultural phenomena and highlights the importance of multilingual simulation for scalable, controlled computational social science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07195 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MASim: Multilingual Agent-Based Simulation for Social Science Zhang, Xuan Zhang, Wenxuan Wang, Anxu Ng, See-Kiong Deng, Yang Computation and Language Artificial Intelligence Computers and Society Multiagent Systems Social and Information Networks Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual and fail to model cross-lingual interaction, an essential property of real societies. We introduce MASim, the first multilingual agent-based simulation framework that supports multi-turn interaction among generative agents with diverse sociolinguistic profiles. MASim offers two key analyses: (i) global public opinion modeling, by simulating how attitudes toward open-domain hypotheses evolve across languages and cultures, and (ii) media influence and information diffusion, via autonomous news agents that dynamically generate content and shape user behavior. To instantiate simulations, we construct the MAPS benchmark, which combines survey questions and demographic personas drawn from global population distributions. Experiments on calibration, sensitivity, consistency, and cultural case studies show that MASim reproduces sociocultural phenomena and highlights the importance of multilingual simulation for scalable, controlled computational social science. |
| title | MASim: Multilingual Agent-Based Simulation for Social Science |
| topic | Computation and Language Artificial Intelligence Computers and Society Multiagent Systems Social and Information Networks |
| url | https://arxiv.org/abs/2512.07195 |