Understanding Online Polarization Through Human-Agent Interaction in a Synthetic LLM-Based Social Network

TL;DR

This paper introduces a controlled experimental framework using human interactions with LLM-based agents to study online polarization, providing causal insights and a new methodology for social media research.

Contribution

It presents a novel experimental setup that simulates polarized online environments, enabling causal analysis of user responses and behaviors in social media dynamics.

Findings

Polarized environments increase perceived emotionality.

Polarized environments heighten group identity salience.

Polarized environments reduce expressed uncertainty.

Abstract

The rise of social media has fundamentally transformed how people engage in public discourse and form opinions. While these platforms offer unprecedented opportunities for democratic engagement, they have been implicated in increasing social polarization and the formation of ideological echo chambers. Previous research has primarily relied on observational studies of social media data or theoretical modeling approaches, leaving a significant gap in our understanding of how individuals respond to and are influenced by polarized online environments. Here we present a novel experimental framework for investigating polarization dynamics that allows human users to interact with LLM-based artificial agents in a controlled social network simulation. Through a user study with 122 participants, we demonstrate that this approach can successfully reproduce key characteristics of polarized online discourse while enabling precise manipulation of environmental factors. Our results provide empirical validation of theoretical predictions about online polarization, showing that polarized environments significantly increase perceived emotionality and group identity salience while reducing expressed uncertainty. These findings extend previous observational and theoretical work by providing causal evidence for how specific features of online environments influence user perceptions and behaviors. More broadly, this research introduces a powerful new methodology for studying social media dynamics, offering researchers unprecedented control over experimental conditions while maintaining ecological validity.