Generative AI for vaccine misbelief correction: Insights from targeting extraversion and pseudoscientific beliefs

IF 4.5 3区医学 Q2 IMMUNOLOGY Vaccine Pub Date : 2025-03-13 DOI:10.1016/j.vaccine.2025.127018

Hang Lu

{"title":"Generative AI for vaccine misbelief correction: Insights from targeting extraversion and pseudoscientific beliefs","authors":"Hang Lu","doi":"10.1016/j.vaccine.2025.127018","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Misinformation about vaccines is a significant barrier to public health, fueling hesitancy and resistance. Generative AI offers a scalable tool for assisting public health communicators in crafting targeted correction messages tailored to audience characteristics. This study investigates the effectiveness of AI-generated messages targeting extraversion and pseudoscientific beliefs compared to high-quality generic and non-vaccine-related messages.</div></div><div><h3>Method</h3><div>In a between-subjects experiment, 1435 U.S. adults were randomly assigned to one of four conditions: control, generic correction, extraversion-targeting correction, or pseudoscientific-belief-targeting correction. Participants rated their agreement with vaccine misbelief statements before and after exposure to a correction message. AI was used to generate the targeted correction messages, while the generic and control messages were sourced from real-world examples.</div></div><div><h3>Results</h3><div>Extraversion-targeting messages significantly reduced vaccine misbeliefs, performing comparably to high-quality generic messages, particularly among participants with higher extraversion levels. However, these effects did not extend to general vaccination attitudes. Pseudoscientific-belief-targeting messages were ineffective and, in some cases, backfired, reinforcing negative attitudes among individuals with strong pseudoscientific beliefs.</div></div><div><h3>Conclusion</h3><div>This study demonstrates the potential of AI-assisted message generation for crafting effective correction messages, particularly when targeting personality traits like extraversion. However, the findings suggest that certain AI-generated messages may be less effective or even counterproductive when targeting entrenched beliefs, underscoring the need for human oversight in refining AI-generated messages. Future research should explore additional audience characteristics and optimize human-AI collaboration to enhance the effectiveness of AI-generated correction messages in public health communication.</div></div>","PeriodicalId":23491,"journal":{"name":"Vaccine","volume":"54 ","pages":"Article 127018"},"PeriodicalIF":4.5000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Vaccine","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0264410X25003159","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"IMMUNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Misinformation about vaccines is a significant barrier to public health, fueling hesitancy and resistance. Generative AI offers a scalable tool for assisting public health communicators in crafting targeted correction messages tailored to audience characteristics. This study investigates the effectiveness of AI-generated messages targeting extraversion and pseudoscientific beliefs compared to high-quality generic and non-vaccine-related messages.

Method

In a between-subjects experiment, 1435 U.S. adults were randomly assigned to one of four conditions: control, generic correction, extraversion-targeting correction, or pseudoscientific-belief-targeting correction. Participants rated their agreement with vaccine misbelief statements before and after exposure to a correction message. AI was used to generate the targeted correction messages, while the generic and control messages were sourced from real-world examples.

Results

Extraversion-targeting messages significantly reduced vaccine misbeliefs, performing comparably to high-quality generic messages, particularly among participants with higher extraversion levels. However, these effects did not extend to general vaccination attitudes. Pseudoscientific-belief-targeting messages were ineffective and, in some cases, backfired, reinforcing negative attitudes among individuals with strong pseudoscientific beliefs.

Conclusion

This study demonstrates the potential of AI-assisted message generation for crafting effective correction messages, particularly when targeting personality traits like extraversion. However, the findings suggest that certain AI-generated messages may be less effective or even counterproductive when targeting entrenched beliefs, underscoring the need for human oversight in refining AI-generated messages. Future research should explore additional audience characteristics and optimize human-AI collaboration to enhance the effectiveness of AI-generated correction messages in public health communication.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

求助全文

约1分钟内获得全文去求助

来源期刊

Vaccine 医学-免疫学

CiteScore

8.70

自引率

5.50%

发文量

992

审稿时长

131 days

期刊介绍： Vaccine is unique in publishing the highest quality science across all disciplines relevant to the field of vaccinology - all original article submissions across basic and clinical research, vaccine manufacturing, history, public policy, behavioral science and ethics, social sciences, safety, and many other related areas are welcomed. The submission categories as given in the Guide for Authors indicate where we receive the most papers. Papers outside these major areas are also welcome and authors are encouraged to contact us with specific questions.