Embracing Dialectic Intersubjectivity: Coordination of Different Perspectives in Content Analysis with LLM Persona Simulation
This addresses the need for more nuanced and integrity-driven AI-assisted social science research, though it is incremental as it builds on existing LLM methods for content analysis.
The study tackled the problem of moving content analysis from consensus to coordination by using GPT-4o configurations to analyze sentiment in Fox News and MSNBC transcripts, finding that partisan persona LLMs show stronger ideological biases with politically congruent content and higher intercoder reliability among same-partisan pairs.
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.