Can artificial intelligence debunk health misinformation more effectively than humans? A three-dimensional persuasion analysis

Abstract

Health misinformation presents significant challenges to public well-being, making effective debunking strategies crucial. While artificial intelligence (AI) shows potential in generating debunking texts, its persuasiveness compared to human-generated content remains underexplored. Drawing on Aristotle's three modes of persuasion, this study investigated the persuasive effectiveness of AI versus human-generated health debunking texts through three complementary studies. Our findings reveal a novel pattern: AI-generated texts significantly outperformed human texts in pathos (emotional appeal) and logos (logical argument) but underperformed in ethos (credibility), with all three dimensions serving as significant mediators of persuasiveness. More importantly, we demonstrate that source labeling effects are not uniform. While “AI-written” labels reduced perceived persuasiveness for both AI and human texts, this algorithmic aversion was attenuated when argument quality (logos) was made salient. These findings advance persuasion theory by revealing that classical rhetoric operates differently for AI versus human sources and that algorithmic aversion is context-dependent rather than universal. The results offer both theoretical insights into human-AI communication and practical guidance for deploying AI in health misinformation mitigation.