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 describe our submission to SemEval 2023 Task 3, specifically the subtask on persuasion technique detection. In this work, our team NLUBot101 tackled a novel task of classifying persuasion techniques in online news articles at a paragraph level. The low-resource multilingual datasets, along with the imbalanced label distribution, make this task challenging. Our team presented a cross-lingual data augmentation approach and leveraged a recently proposed multilingual natural language inference model to address these challenges. Our solution achieves the highest macro-F1 score for the English task, and top 5 micro-F1 scores on both the English and Russian leaderboards.