MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations
This work addresses the challenge of understanding and regulating misinformation in social networks for researchers in AI and social sciences, though it is incremental as it builds on existing agent-based simulation methods.
The authors tackled the problem of modeling online content dissemination and moderation by developing MOSAIC, a social network simulation framework using generative language agents, and found that three tested moderation strategies reduced misinformation spread and increased user engagement.
We present a novel, open-source social network simulation framework, MOSAIC, 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. We open-source our simulation software to encourage further research within AI and social sciences.