Previously submitted to: JMIR Formative Research (no longer under consideration since Dec 07, 2025)
Date Submitted: Feb 8, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
"The Use of AI Chatbot Therapy as a Stress Management Intervention In Non-Clinical Populations": An Experimental Study
ABSTRACT
Background:
Mental health concerns are rising in the Philippines, yet access to psychological services remains limited due to a shortage of mental health professionals and financial barriers. AI chatbot therapy presents a potential solution by providing accessible and scalable mental health support. While previous research has explored AI chatbots in clinical populations, their effectiveness in stress management among non-clinical populations remains underexplored.
Objective:
This study aims to evaluate the effectiveness of AI chatbot therapy in reducing perceived stress among non-clinical populations. Specifically, it examines whether AI chatbot therapy significantly decreases stress levels compared to a control group.
Methods:
An experimental pretest-posttest design was utilized. A total of 100 undergraduate students from Metro Manila (aged 18-25) were randomly assigned to either the intervention group (n=50), which used AI chatbot therapy for 40 minutes to 1 hour daily over seven days, or the control group (n=50), which did not receive the intervention. Stress levels were measured using the Perceived Stress Scale (PSS) before and after the intervention. Statistical analyses, including paired and independent t-tests, were conducted to compare within-group and between-group differences.
Results:
The intervention group demonstrated a significant reduction in stress levels from pre-test (M = 31.36, SD = 4.25) to post-test (M = 20.86, SD = 5.10), with a large effect size (Cohen’s d = 2.43, p < .001). The control group also showed a reduction in stress (M = 32.00, SD = 4.17 to M = 24.20, SD = 8.65), but with a smaller effect size (Cohen’s d = 0.96, p < .001). A comparison of post-test scores between groups revealed a statistically significant difference (p = .021), favoring the intervention group.
Conclusions:
The findings suggest that AI chatbot therapy is an effective stress management tool for non-clinical populations, demonstrating significant reductions in perceived stress. Given the accessibility and scalability of AI chatbots, they hold promise as a supplementary mental health intervention, particularly in resource-limited settings. Further research should explore long-term effects, usability across diverse populations, and integration with traditional mental health care.
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.