Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Randomized Controlled Trial
. 2025 Aug 8:27:e72637.
doi: 10.2196/72637.

Effects of a Theory- and Evidence-Based, Motivational Interviewing-Oriented Artificial Intelligence Digital Assistant on Vaccine Attitudes: A Randomized Controlled Trial

Yan Li  1   2   3 , Mengqi Li  1   2 , Janelle Yorke  1   4 , Daniel Bressington  5 , Joyce Chung  1 , Yao-Jie Xie  1   6 , Lin Yang  1 , Mengting He  1 , Tsz-Ching Sun  1 , Angela Y M Leung  1
Affiliations
Randomized Controlled Trial

Effects of a Theory- and Evidence-Based, Motivational Interviewing-Oriented Artificial Intelligence Digital Assistant on Vaccine Attitudes: A Randomized Controlled Trial

Yan Li et al. J Med Internet Res. .

Abstract

Background: Attitude-targeted interventions are important approaches for promoting vaccination. Educational approaches alone cannot effectively cultivate positive vaccine attitudes. Artificial intelligence (AI)-driven chatbots and motivational interviewing (MI) techniques show high promise in improving vaccine attitudes and facilitating readiness for vaccination.

Objective: This study aimed to evaluate the effectiveness of a theory and evidence-based, MI-oriented AI digital assistant in improving COVID-19 vaccine attitudes among adults in Hong Kong.

Methods: This 2 parallel-armed randomized controlled trial was conducted from October 2022 to June 2024. Hong Kong adults (N=177) who were vaccine-hesitant were randomly assigned into 2 study groups. The intervention group (n=91) interacted with the AI digital assistant over 5 weeks, including receiving a web-based education program comprising 5 educational modules and communicating with an AI-driven chatbot equipped with MI techniques. The control group (n=86) received WhatsApp (Meta) messages directing them to government websites for COVID-19 vaccine information and knowledge, with the same dosage as the intervention group. Primary outcomes included vaccine hesitancy. Secondary outcomes included vaccine readiness, confidence, trust in government, and health literacy. Outcomes were measured at baseline, postintervention, 3-month, and 6-month follow-up. Focus group interviews were conducted postintervention. Intervention effects were analyzed using the generalized estimating equation model. Interview data were content analyzed.

Results: Decreases in vaccine hesitancy were observed while no statistically significant time-by-group interaction effects were found. The intervention showed significant time-by-group interaction effects on vaccine readiness (P=.04), confidence (P=.02), and trust in government (P=.04). Significant between-group differences with medium effect sizes were identified for vaccine readiness (Cohen d=0.52) and trust in government (Cohen d=0.54) postintervention, respectively. Increases in vaccine-related health literacy were observed, and a significant time effect was found (P=.01). In total, three categories were summarized from interview data: (1) improved vaccine literacy, confidence, and trust in government; (2) hesitancy varied while readiness improved; and (3) facilitators, barriers, and recommendations of modifications on the intervention.

Conclusions: The intervention indicated promising yet significant effects on vaccine readiness while the effects on vaccine hesitancy require further confirmation. The qualitative findings; however, further consolidate the significant effects on participants' attitudes toward vaccines. The findings provide novel evidence to encourage the adoption and refinement of a MI-oriented AI digital assistant in vaccine promotion.

Keywords: COVID-19; artificial intelligence; attitude; chatbot; motivational interviewing; vaccine hesitancy.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1.
Figure 1.. The interface of the artificial intelligence digital assistant.
Figure 2.
Figure 2.. Participant flow chart. AI: artificial intelligence.
Figure 3.
Figure 3.. Changes in vaccine attitudes among participants in the intervention group.
Figure 4.
Figure 4.. Changes in the scores of outcomes among 4 time points.
See this image and copyright information in PMC

References

    1. Vaccines and immunization. World Health Organization. 2024. [16-02-2024]. https://www.who.int/health-topics/vaccines-and-immunization#tab=tab_1 URL. Accessed.
    1. Watson OJ, Barnsley G, Toor J, Hogan AB, Winskill P, Ghani AC. Global impact of the first year of COVID-19 vaccination: a mathematical modelling study. Lancet Infect Dis. 2022 Sep;22(9):1293–1302. doi: 10.1016/S1473-3099(22)00320-6. doi. Medline. - DOI - PMC - PubMed
    1. Xiong X, Li J, Huang B, et al. Economic value of vaccines to address the COVID-19 pandemic in Hong Kong: a cost-effectiveness analysis. Vaccines (Basel) 2022 Mar 23;10(4):495. doi: 10.3390/vaccines10040495. doi. Medline. - DOI - PMC - PubMed
    1. Li Y, Zhao IY, Lu W, et al. Are people willing to take regular vaccinations? A qualitative study among diverse ethnic groups in Hong Kong. PLoS ONE. 2023 Jun 15;20(5):e0318631. doi: 10.1371/journal.pone.0318631. doi. Medline. - DOI - PMC - PubMed
    1. Candio P, Violato M, Clarke PM, Duch R, Roope LS. Prevalence, predictors and reasons for COVID-19 vaccine hesitancy: results of a global online survey. Health Policy. 2023 Nov;137:104895. doi: 10.1016/j.healthpol.2023.104895. doi. Medline. - DOI - PubMed

Publication types

Substances

LinkOut - more resources