Accepted for/Published in: JMIR Formative Research
Date Submitted: Jan 30, 2025
Date Accepted: May 26, 2025
Generative Artificial Intelligence Powered Mental Wellness Chatbot for College Student Mental Wellness: An Open Trial
ABSTRACT
Background:
Colleges have turned to digital mental health interventions to meet the increasing mental health treatment needs of their students. Among these, chatbots stand out as artificial intelligence (AI)-driven tools capable of engaging in human-like conversations that have demonstrated some effectiveness in reducing depression and anxiety symptoms.
Objective:
The current study aimed to assess the feasibility and acceptability of using Wayhaven, an AI chatbot among college students with elevated depression and/or anxiety symptoms. We also aimed to examine the preliminary effectiveness of Wayhaven in improving symptoms of anxiety and depression, hopelessness, agency, and self-efficacy among students.
Methods:
Participants were 50 ethnoracially diverse college students with elevated depression and/or anxiety symptoms (80% female, mean age = 22.12 [SD=4.42]). Students were asked to use Wayhaven over the course of one week and completed assessments at pre-intervention, after one session, and one week.
Results:
Wayhaven use was associated with a significant decrease in depression (b= -1.62, P<.001), anxiety (b= -2.15, P<.001), and hopelessness (b= -.64, P<.001) and a significant increase in agency (b= .64, P=0.32), self-efficacy (b= .53, P=.021), and well-being (t=2.90, P<.01, d=.45) across the study period. Most students also reported being satisfied with Wayhaven and it being a tool they would recommend to their peers.
Conclusions:
Findings suggest that Wayhaven may be a viable mental wellness resource for diverse students with elevated depression/anxiety symptoms. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.