Comparing the persuasiveness of role-playing large language models and human experts on polarized US political issues
Authors: K Hackenburg, L Ibrahim, BM Tappin, M Tsakiris
Published: 2025
Publication: AI & SOCIETY, 2025 - Springer
GPT-4's ability to generate persuasive messages rivaled human experts on polarized US political issues, suggesting AI tools may have significant implications for political campaigns and democracy.
Methods: Pre-registered experiment where GPT-4 generated partisan role-playing persuasive messages, which were compared to those from human persuasion experts.
Key Findings: Persuasive impact of GPT-4-generated messages versus human expert messages on U.S. political issues.
Limitations: Role-playing offered limited persuasive advantage, and findings pertain only to current LLM capabilities.
Institution: Oxford Internet Institute, University of Oxford
Research Area: Political Communication and Persuasion, LLM
Discipline: Political Science , Artificial Intelligence
Sample Size: 4955 participants
Citations: 35