Previously submitted to: JMIR Mental Health (no longer under consideration since Oct 22, 2025)
Date Submitted: Oct 22, 2025
Open Peer Review Period: Oct 22, 2025 - Oct 22, 2025
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited.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.
Key Factors Influencing Adolescent Satisfaction with an LLM-Based Mental Health Chatbot: A Mixed-Methods Study of the "Xinyu" System
ABSTRACT
Background:
Adolescent mental health problems are increasingly prevalent globally, yet accessible and timely mental health support for this group remains insufficient. Large language model (LLM)-based conversational agents present a promising avenue for scalable mental health interventions, but evidence regarding their acceptance and effectiveness among adolescent students is limited.
Objective:
This study aimed to identify the key factors influencing user satisfaction and word of mouth (WOM) intention among adolescent students. To achieve this, we proposed and evaluated "Xinyu," an LLM-based multi-agent conversational system for adolescent mental health.
Methods:
We employed a sequential mixed-methods approach. The qualitative phase involved 41 middle school students who interacted with Xinyu and provided feedback via semi-structured questionnaires and in-depth interviews (n=10). The quantitative phase surveyed 101 students (15 primary, 86 secondary) using a structured questionnaire after interaction with the refined system. Data were analyzed using inductive thematic analysis and partial least squares structural equation modeling (PLS-SEM).
Results:
Overall, 67.3% of participants reported being satisfied or very satisfied with Xinyu, and 64.4% indicated a willingness to recommend it. The qualitative phase identified key factors influencing user satisfaction and systematically categorized them into hygiene factors (personalized advice, ease of use, timeliness) and motivators (empathy, warmth, aesthetics). Subsequent quantitative analysis validated this framework, revealing that personalized advice (β=0.306, P=0.047), empathy (β=0.300, P=0.033), and interface aesthetics (β=0.245, P=0.054) were major predictors of user satisfaction. Satisfaction, in turn, strongly influenced WOM intention (β=0.712, P<.001). In contrast, ease of use, timeliness, and warmth were not statistically significant predictors.
Conclusions:
The Xinyu system demonstrates feasibility and user acceptance among adolescent students. Key factors driving satisfaction include personalized advice, empathy, and aesthetics. These findings provide empirical support for the design of LLM-based mental health chatbots for adolescents and highlight specific features to prioritize for enhancing user experience and engagement.
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.