Automated Chatbot Self-Help Program for Well-Being
Author Information
Author(s): McCall Terika, Dinh Dai, Kaphingst Kimberly, Foran Heather M, Kubb Christian, Mueller Janina, Poff Spencer, Ung Megan, Li Margaret, Smith Eric Michael, Akinyemi Akinniyi, Kambadur Melanie, Waller Franziska, Graf Mario, Boureau Y-Lan
Primary Institution: Department of Health Psychology University of Klagenfurt
Hypothesis
The intervention group will show significant improvements in well-being and psychological flourishing at the 1-month postassessment compared with the control group.
Conclusion
The free conversational agent wellness self-help program was as effective as evidence-based web resources.
Supporting Evidence
- Both groups showed significant improvements in well-being.
- Engagement with the chatbot was linked to greater improvements in well-being.
- User satisfaction was associated with better outcomes.
- Participants in both groups reported similar levels of improvement.
Takeaway
This study tested a chatbot that helps people feel better, and it worked just as well as other online resources.
Methodology
Participants were randomly assigned to either a self-help program via a chatbot or an active control group with online wellness resources, with outcomes measured at baseline and 1 month later.
Potential Biases
Participants were not blinded to their group assignment, which may introduce bias.
Limitations
The study's reliance on WhatsApp may have limited participation, and the chatbot was still under development during data collection.
Participant Demographics
Participants were primarily women (80.5%) with a mean age of 47.22 years.
Statistical Information
P-Value
P<.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website