Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?

2025-02-09

AI Summary

This paper investigates whether generative agent-based modeling (GABM) can naturally reproduce the friendship paradox (FP)—a global network phenomenon—as an emergent property in social media simulations, thereby validating its capacity to capture macro-level social dynamics. Method: We propose the first LLM-driven GABM framework explicitly designed to evaluate FP emergence, calibrated using real-world Twitter data to ground agent behavior and network topology. Our approach integrates generative agent modeling, LLM-based behavioral generation, and empirical network statistical analysis. Contribution/Results: FP robustly emerges across simulations; low-degree connections are identified as the core mechanism driving FP emergence; simulated networks exhibit empirically consistent hierarchical connectivity structures and activity-degree correlations. Critically, this work introduces FP as a novel, theoretically grounded metric for assessing GABM validity—successfully demonstrated in two complex sociopolitical contexts: the 2020 U.S. presidential election and the QAnon movement—thereby substantially extending the theoretical foundations and practical applicability of generative ABM in modeling complex social systems.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Generative Agent-Based Modeling (GABM) is an emerging simulation paradigm that combines the reasoning abilities of Large Language Models with traditional Agent-Based Modeling to replicate complex social behaviors, including interactions on social media. While prior work has focused on localized phenomena such as opinion formation and information spread, its potential to capture global network dynamics remains underexplored. This paper addresses this gap by analyzing GABM-based social media simulations through the lens of the Friendship Paradox (FP), a counterintuitive phenomenon where individuals, on average, have fewer friends than their friends. We propose a GABM framework for social media simulations, featuring generative agents that emulate real users with distinct personalities and interests. Using Twitter datasets on the US 2020 Election and the QAnon conspiracy, we show that the FP emerges naturally in GABM simulations. Consistent with real-world observations, the simulations unveil a hierarchical structure, where agents preferentially connect with others displaying higher activity or influence. Additionally, we find that infrequent connections primarily drive the FP, reflecting patterns in real networks. These findings validate GABM as a robust tool for modeling global social media phenomena and highlight its potential for advancing social science by enabling nuanced analysis of user behavior.

Problem

• Replicate Friendship Paradox
• Global network dynamics
• Social media simulations

Innovation

• Generative Agent-Based Modeling
• Friendship Paradox analysis
• Twitter datasets simulation