Truace
Subscribe
70/100

Moderate evidence

Cite
More
Export CSVExport JSONEmailLinkedInX

Chatbots shifted vaccine attitudes but not intentions, review of 12 studies finds

Study title: Effectiveness of chatbots in increasing uptake, intention, and attitudes related to any type of vaccination: A systematic review and meta‐analysis

Evidence type
Systematic review or meta-analysis
Sample
n = 12
Sources
1 sourcePeer-reviewed
Published
2 min read
Truvace record
TRV-2026-2722cite or check it

Study title: Effectiveness of chatbots in increasing uptake, intention, and attitudes related to any type of vaccination: A systematic review and meta‐analysis

A systematic review and meta-analysis published in June 2024 examined whether chatbots can increase vaccination uptake, intention and positive attitudes. It analysed 12 eligible studies published between 2019 and 2023, drawn from PubMed, Web of Science, MEDLINE, Global Health, APA PsycInfo and EMBASE.

Read the study abstract

This systematic review and meta-analysis analyzed and summarized the growing literature on the effectiveness of chatbot-delivered interventions in increasing uptake, intention, and attitudes related to any type of vaccination. We identified randomized controlled studies (RCTs), quasi-experimental studies, and non-experimental studies from the following platforms: PubMed, Web of Science, MEDLINE, Global Health, APA PsycInfo, and EMBASE databases. A total of 12 eligible studies published from 2019 to 2023 were ana…

57Gain side

How the two sides scoreClose call

56Problem side

The gain

A meta-analysis of six randomized trials found chatbot interventions improved vaccination attitudes (pooled SMD 0.34, 95% CI 0.13 to 0.55), and one trial found a tailored chatbot lifted flu vaccine uptake among older adults to 50.5% versus 35.3%.

The problem

The same meta-analysis of six randomized trials found no significant effect of chatbots on vaccination intentions (SMD 0.11, 95% CI -0.13 to 0.34, p = 0.38), so attitude gains did not clearly lead to intent to get vaccinated.

A fixed formula sets both scores from the evidence and its sources. Reader votes don’t move them.

What the scores mean

G is the gain side, out of 100. It goes up when the gain is specific, when it measurably helped people and when the sources behind it are strong.

P is the problem side, out of 100. It goes up when the problem is specific, when it measurably hurt people and when the sources behind it are strong.

In brief

Six randomized trials were pooled for the meta-analysis. Chatbots produced a pooled attitude change of 0.34 standard deviations (95% CI 0.13 to 0.55), but the effect on vaccination intentions was small and not statistically significant (0.11, 95% CI -0.13 to 0.34).

On actual uptake, one randomized trial found a tailored chatbot beat a non-tailored one for seasonal flu vaccination among older adults, 50.5% versus 35.3%. Participants reported high satisfaction and were likely to recommend the chatbot, though the authors say more evidence is needed for firmer conclusions.

Main points

  1. The review covered 12 eligible studies published from 2019 to 2023, including randomized, quasi-experimental and non-experimental designs.
  2. Six randomized trials were pooled to assess attitudes and intentions toward vaccination.
  3. Pooled attitude change was 0.34 SMD (95% CI 0.13 to 0.55, p = 0.001).
  4. The effect on vaccination intentions was 0.11 SMD (95% CI -0.13 to 0.34, p = 0.38), not significant.
  5. One trial found tailored chatbot messaging led to 50.5% flu vaccine uptake among older adults versus 35.3% for a non-tailored chatbot.
  6. Participants reported high satisfaction with chatbots and were likely to recommend them to others.

What the review found when it combined the studies

These are the review’s own pooled results, copied from its abstract. Truvace did not recalculate them.

  • Vaccination intention with chatbot interventions

    SMD 0.11 (95% CI -0.13 to 0.34)

    The review’s own words
    We found a non-significant trivial effect of chatbot interventions on improving intentions of vaccination (SMD: 0.11, 95% CI: -0.13, 0.34, p = 0.38).

  • Overall vaccination attitude change with chatbot interventions

    SMD 0.34 (95% CI 0.13 to 0.55)

    The review’s own words
    The pooled standard mean difference (SMD) of overall attitude change was 0.34 (95% confidence intervals [CI]: 0.13, 0.55, p = 0.001).

Code checks every number above against the review’s text before it is shown. The short labels are an AI model’s reading of that text, so the review’s own sentence sits under each one. A pooled figure is only as strong as the studies behind it. How Truvace uses pooled results

The full story

The authors searched six databases for randomized controlled, quasi-experimental and non-experimental studies of chatbot-delivered vaccination interventions and found 12 eligible studies published between 2019 and 2023.

Only six randomized trials had data suitable for pooling. They showed a statistically significant improvement in vaccination attitudes, but the improvement in intentions could not be distinguished from zero.

The clearest uptake result came from a single trial among older adults, where a tailored chatbot outperformed a non-tailored one for seasonal influenza vaccination (50.5% versus 35.3%, p = 0.002). The authors describe chatbot development as still nascent with room for improvement.

What this doesn’t fix

The authors say further evidence is needed for a more precise conclusion; only six randomized trials could be pooled and the intention estimate had a wide confidence interval spanning zero.

Sources

1 on file
  1. Applied Psychology: Health and Well-Beingdoi:10.1111/aphw.12564
    Peer-reviewed2024-06-17

Talk it over

Four questions to start onThis record found a gain and a problem in the same place. Which matters more to you, and who might answer differently?

Start with a question

Chatbots shifted vaccine attitudes but not intentions, review of 12 studies findshttps://truvace.com/item/effectiveness-of-chatbots-in-increasing-uptake-intention-and-attitudes-related-t

  1. This record found a gain and a problem in the same place. Which matters more to you, and who might answer differently?

    The gain A meta-analysis of six randomized trials found chatbot interventions improved vaccination attitudes (pooled SMD 0.34, 95% CI 0.13 to 0.55), and one trial found a tailored chatbot lifted flu vaccine uptake among older adults to 50.5% versus 35.3%.

    The problem The same meta-analysis of six randomized trials found no significant effect of chatbots on vaccination intentions (SMD 0.11, 95% CI -0.13 to 0.34, p = 0.38), so attitude gains did not clearly lead to intent to get vaccinated.

    Answer in the thread

  2. How do we know? What can this kind of evidence show, and what can’t it?

    The evidence This rests on a systematic review or meta-analysis with a sample of 12, from Applied Psychology: Health and Well-Being.

    Answer in the thread

  3. What does it leave open? What else would you want to know before acting on it?

    The record’s own caveat The authors say further evidence is needed for a more precise conclusion; only six randomized trials could be pooled and the intention estimate had a wide confidence interval spanning zero.

    Answer in the thread

  4. Have you seen AI used this way where you study, work or live? Did it go the same way?

    Answer in the thread

The questions are the same on every record. The details under them are taken from this record as written.

What readers say

More from Health