Go to ACL ARR 2025 May homepageMOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations
Abstract: We present a novel, open-source social network simulation framework \frameworknamecolor~where generative language agents predict user behaviors such as liking, sharing, and flagging content. This simulation combines LLM agents with a directed social graph to analyze emergent deception behaviors and gain a better understanding of how users determine the veracity of online social content. By constructing user representations from diverse fine-grained personas, our system enables multi-agent simulations that model content dissemination and engagement dynamics at scale. Within this framework, we evaluate three different content moderation strategies with simulated misinformation dissemination, and we find that they not only mitigate the spread of non-factual content but also increase user engagement. In addition, we analyze the trajectories of popular content in our simulations, and explore whether simulation agents' articulated reasoning for their social interactions truly aligns with their collective engagement patterns.
Paper Type: Long
Research Area: Special Theme (conference specific)
Research Area Keywords: AI/LLM Agents, Human-AI Interaction/Cooperation, Computational Social Science
Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data analysis
Languages Studied: English
Submission Number: 4416
Loading