Characterizing LLM-driven Social Network: The Chirper.ai Case

2025-04-14

AI Summary

Existing research lacks empirical comparisons of behavioral differences between LLM agents and human users in online social networks. This paper presents the first large-scale, cross-platform study comparing a fully LLM-driven microblogging platform, Chirper.ai (65K agents, 7.7M posts), with a human-dominated decentralized platform, Mastodon (117K users, 16M posts). Leveraging multidimensional behavioral log analysis, social network topology modeling, and cross-platform data alignment, we find that LLM agents exhibit more uniform posting distributions, lower prevalence of harmful content, yet significantly higher homogeneity; their networks display greater centrality concentration, looser community structures, and fuzzier community boundaries. This work fills a critical gap in empirical research on AI-driven social systems, establishing a foundational benchmark for understanding the sociability of LLMs and informing human-AI collaborative governance in digital societies.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• Comparing LLM-driven and human-driven online social networks
• Analyzing differences in posting behaviors and abusive content
• Examining social network structures of LLM agents vs humans

Innovation

• LLM agents simulate human decision-making processes
• Large-scale analysis of Chirper.ai social network
• Comparison with human-driven Mastodon dataset