Scalable Observed Correction With Generative AI: How Motivationally Relevant Message Features and Design Choices Boost Communicative Engagement

Science Communication 2026

View at publisher
Authors: Yibing Sun, Ji Soo Choi, Xiaohui Cao, Liwei Shen, Porismita Borah, Michael W. Wagner, Dhavan V. Shah, Sijia Yang
DOI: 10.1177/10755470261438828
Cited by: 1
References: 89

Abstract

To address the challenge of scalability in fact-checking, we report two parallel experiments examining which message features may boost communicative engagement with AI-facilitated observed correction of misinformation related to human papillomavirus (HPV) vaccination. Study 1 ( N = 1,789) found that expert endorsement enhanced AI-generated visual exemplars’ effects on engagement. Study 2 ( N = 1,765) showed that the advantage of adopting an empathetic tone for AI (vs. human) fact-checkers was dependent on participants’ baseline perceived anthropomorphism in a nonlinear pattern. These findings highlight the importance of strategically selecting motivationally relevant messages and design features to improve the scalability of AI-powered observed correction.

Fields of Study & Subjects

Misinformation and Its Impacts Psychology of Moral and Emotional Judgment Vaccine Coverage and Hesitancy

Publication details

Journal / source
Science Communication
Publisher
SAGE Publications
Volume
48
Issue
3
Pages
402–437
Publication date
11 May 2026
Language
EN