Characterizing LLM-driven Social Network: The Chirper.ai Case
This provides insights for researchers and practitioners in social network analysis and AI simulation, though it is incremental as it extends existing work on LLM agents to empirical comparisons.
The paper tackled the lack of empirical comparisons between LLM-driven and human-driven online social networks by analyzing Chirper.ai (65,000 agents, 7.7 million posts) versus Mastodon (117,000 users, 16 million posts), finding key differences in posting behaviors, abusive content, and network structures.
Large language models (LLMs) demonstrate the ability to simulate human decision-making processes, enabling their use as agents in modeling sophisticated social networks, both offline and online. Recent research has explored collective behavioral patterns and structural characteristics of LLM agents within simulated networks. However, empirical comparisons between LLM-driven and human-driven online social networks remain scarce, limiting our understanding of how LLM agents differ from human users. This paper presents a large-scale analysis of Chirper.ai, an X/Twitter-like social network entirely populated by LLM agents, comprising over 65,000 agents and 7.7 million AI-generated posts. For comparison, we collect a parallel dataset from Mastodon, a human-driven decentralized social network, with over 117,000 users and 16 million posts. We examine key differences between LLM agents and humans in posting behaviors, abusive content, and social network structures. Our findings provide critical insights into the evolving landscape of online social network analysis in the AI era, offering a comprehensive profile of LLM agents in social simulations.