Previously submitted to: JMIR Mental Health (no longer under consideration since Sep 24, 2025)
Date Submitted: Sep 24, 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Warning: This is an author submission that is not peer-reviewed or edited.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 Effectiveness of AI-Driven Chatbots in Providing Emotional Support in Mental Health Interventions
ABSTRACT
Mental health disorders such as anxiety and depression are globally prevalent, affecting millions. Barriers like stigma, resource limitations, and a shortage of professionals impede access to adequate care. AI-driven chatbots have emerged as a promising tool for mental health interventions, offering accessible and cost-effective support. This study aimed to evaluate the effectiveness of AI-driven chatbots in delivering emotional support compared to traditional human therapy. A mixed-methods approach was employed, with 200 participants experiencing symptoms of anxiety and depression randomized into AI Chatbot or Human Therapy groups. The interventions spanned 12 weeks, utilizing surveys and interviews to assess symptom reduction, user satisfaction, and perceived empathy. Both groups showed significant reductions in anxiety and depression symptoms, with no notable differences in efficacy. While participants appreciated the accessibility and anonymity of chatbots, they reported lower empathy compared to human therapists. Satisfaction levels were high across both groups. AI-driven chatbots are effective supplementary tools in mental health care, addressing accessibility barriers and reducing stigma. However, further improvements are needed to enhance their empathetic capabilities. Future research should focus on long-term outcomes, demographic diversity, and ethical guidelines for AI integration in mental health services..
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.