Warning: This is an author submission that is not peer-reviewed or edited.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.
Designing Co-Interpretive AI Support for Personal Wellbeing Reflection: Qualitative Prototype Study
ABSTRACT
Background:
Personal wellbeing applications commonly summarize steps, sleep, and activity through dashboards, goals, and reminders. These features support progress tracking but offer limited support for interpreting why personal data vary across everyday contexts.
Objective:
This study examined how college students perceived the clarity, anticipated usefulness, and appropriateness of co-interpretive interaction strategies in KRIYA, an envisioned AI-supported interface for personal wellbeing reflection.
Methods:
We conducted semi-structured remote interviews with 20 college students. Participants discussed their existing health-tracking practices and completed a guided walkthrough of a high-fidelity prototype using hypothetical wellbeing scenarios and pre-authored conversational responses. The prototype instantiated range-based framing, context-aware discrepancy interpretation, and speculative low-stakes planning. We analyzed interview transcripts using reflexive thematic analysis and descriptively summarized post-walkthrough System Usability Scale (SUS) and Intervention Appropriateness Measure (IAM) scores.
Results:
Participants perceived range-based framing as a more flexible way to consider daily variation, valued context-linked explanations as starting points for interpretation, and viewed small, revisable actions as manageable. They expected envisioned AI interpretations to remain legible, bounded, and open to correction. Perceived value diminished when ranges felt arbitrary, explanations were generic, or numerical outputs lacked clear provenance. The median SUS score was 76.25 (SD 11.18), and the median IAM score was 14.0 (SD 2.78). These scores describe perceptions of the facilitated walkthrough and proposed interaction concept.
Conclusions:
The findings identify design considerations for AI-supported personal wellbeing interfaces: contextual explanations should remain tentative and revisable, ranges should be plausible and adjustable, and speculative planning should communicate uncertainty and predictive limits. The study provides formative qualitative evidence about user perceptions; it does not establish behavior change, clinical benefit, or forecasting accuracy.
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.