Simulating hashtag dynamics with networked groups of generative agents

TL;DR

This paper develops an agent-based simulation framework using large language models to study how hashtag dynamics and narrative interactions influence group beliefs, polarization, and consensus in networked social environments.

Contribution

It introduces a novel simulation framework of networked LLM agents, benchmarking their behavior against human data and Twitter hashtags to analyze narrative evolution and social influence mechanisms.

Findings

LLMs can mimic human group coherence in controlled domains

Effective narrative simulation requires careful prompting for complex topics

The framework enables analysis of social influence and polarization dynamics

Abstract

Networked environments shape how information embedded in narratives influences individual and group beliefs and behavior. This raises key questions about how group communication around narrative media impacts belief formation and how such mechanisms contribute to the emergence of consensus or polarization. Language data from generative agents offer insight into how naturalistic forms of narrative interactions (such as hashtag generation) evolve in response to social rewards within networked communication settings. To investigate this, we developed an agent-based modeling and simulation framework composed of networks of interacting Large Language Model (LLM) agents. We benchmarked the simulations of four state-of-the-art LLMs against human group behaviors observed in a prior network experiment (Study 1) and against naturally occurring hashtags from Twitter (Study 2). Quantitative metrics of network coherence (e.g., entropy of a group's responses) reveal that while LLMs can approximate human-like coherence in sanitized domains (Study 1's experimental data), effective integration of background knowledge and social context in more complex or politically sensitive narratives likely requires careful and structured prompting.