Embracing Dialectic Intersubjectivity: Coordination of Different Perspectives in Content Analysis with LLM Persona Simulation

TL;DR

This paper introduces a coordination-based content analysis method using multiple GPT-4 configurations to analyze political sentiment, revealing ideological biases and improving reliability in social science research.

Contribution

It advances content analysis by shifting from consensus to coordination practices, incorporating diverse perspectives and LLM persona simulation for nuanced insights.

Findings

Partisan LLMs show stronger ideological biases with politically aligned content.

Intercoder reliability is higher among same-partisan LLM pairs.

The approach improves understanding of LLM outputs in social science contexts.

Abstract

This study attempts to advancing content analysis methodology from consensus-oriented to coordination-oriented practices, thereby embracing diverse coding outputs and exploring the dynamics among differential perspectives. As an exploratory investigation of this approach, we evaluate six GPT-4o configurations to analyze sentiment in Fox News and MSNBC transcripts on Biden and Trump during the 2020 U.S. presidential campaign, examining patterns across these models. By assessing each model's alignment with ideological perspectives, we explore how partisan selective processing could be identified in LLM-Assisted Content Analysis (LACA). Findings reveal that partisan persona LLMs exhibit stronger ideological biases when processing politically congruent content. Additionally, intercoder reliability is higher among same-partisan personas compared to cross-partisan pairs. This approach enhances the nuanced understanding of LLM outputs and advances the integrity of AI-driven social science research, enabling simulations of real-world implications.