Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article 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.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.vaccine.2025.127018 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Correction of Tricuspid Regurgitation in Pulmonary Arterial Hypertension.
JACC Case Rep
September 2025
Department of Cardiology, Monaldi Hospital, Naples, Italy. Electronic address:
Background: Pulmonary hypertension is a contraindication to correction of tricuspid regurgitation.
Case Summary: A 75-year-old Italian woman with previous episodes of right heart failure was diagnosed with World Health Organization (WHO) functional class IV pulmonary arterial hypertension (PAH) complicated by torrential tricuspid regurgitation. After 6 months of treatment with diuretic agents, macitentan, and tadalafil, she improved to WHO functional class III, with a pulmonary vascular resistance (PVR) decreasing from 5.
Prebunking and credible source corrections increase election credibility: Evidence from the US and Brazil.
Sci Adv
August 2025
Department of Politics and International Relations, University of Southampton, Murray Building (B58), University Road, Southampton SO17 1BJ, UK.
We investigate how to counter misinformation about voter and election fraud using data from the US and Brazil. Our study first compares two types of messages countering claims of widespread fraud: (i) retrospective corrections from credible sources speaking against interest and (ii) prebunking messages that prospectively warn of false claims about future elections and provide information about election security practices. In the US, each approach immediately increased election confidence and reduced fraud beliefs, with prebunking showing somewhat more durable effects.
View Article and Find Full Text PDFDifferent vaccination debunking interventions: a randomized, controlled experiment estimating "backfiring" and positive effects.
Vaccine
August 2025
Perelman School of Medicine, University of Pennsylvania, United States; Annenberg School for Communication, University of Pennsylvania, United States. Electronic address:
Background: Misinformation about vaccines can hinder efforts to increase immunization rates. Attempts to correct misinformation often use one of three common message structures. The effectiveness of these message structures is unclear, and concerns have been raised that some can "backfire" by weakening vaccination intentions.
View Article and Find Full Text PDFA comprehensive qualitative analysis of patient dialogue summarization using large language models applied to noisy, informal, non-English real-world data.
Sci Rep
August 2025
Computer Science Department, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil.
This study evaluates the ability of Large Language Models (LLMs) to summarize real-world dialogues between patients and the healthcare team of an e-health company that provides digital healthcare services, primarily communicating via WhatsApp. The team needs quick access to patient information to deliver accurate and personalized responses. Summarizing past messages is the approach examined here, aiming for concise, non-redundant, and truthful summaries that capture the main dialogue characteristics despite facing (real-world) noisy and informal content in an under-represented language - Portuguese.
View Article and Find Full Text PDFUsing narrative and informational messages to improve correctional professionals' attitudes toward medications for opioid use disorder.
Health Justice
August 2025
Schar School of Public Policy, George Mason University, Fairfax, USA.
Background: Criminal legal involved (CLI) individuals face a heightened risk of opioid misuse and overdose, yet access to medications for opioid use disorder (MOUD) is limited, particularly in criminal legal settings. Negative attitudes and misinformation about MOUD are prevalent among legal system actors, creating a barrier to MOUD access. This study examines the effectiveness of informational and narrative messages in correcting misinformation and promoting positive attitudes toward MOUD among criminal legal system (CLS) professionals.
View Article and Find Full Text PDF