cs.HCApr 8, 2026
SaveGenerative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study
Organizations: Stanford University, Stanford, California, USA · University of Toronto Mississauga, Mississauga, Ontario, Canada
Abstract
Digital mental health (DMH) tools have extensively explored personalization of interventions to users' needs and contexts. However, this personalization often targets what support is provided, not how it is experienced. Even well-matched content can fail when the interaction format misaligns with how someone can engage. We introduce generative experience as an approach to DMH support, where the intervention experience is composed at runtime. We instantiate this in GUIDE, a system that generates personalized intervention content and multimodal interaction structure through rubric-guided generation of modular components. In a preregistered study with N=237 participants, GUIDE significantly reduced stress (p=.02) and improved user experience (p=.04) compared to an LLM-based cognitive restructuring control. GUIDE also supported diverse forms of reflection and action through varied interaction flows, while revealing tensions around personalization across the interaction sequence. This work lays the foundation for interventions that dynamically shape how support is experienced and enacted in digital settings.
Figures & tables
Figure 1. GUIDE generates intervention experiences at runtime by composing interaction structures from user context and selected interventions. The system elicits context, selects an intervention, and constructs a multimodal experience using elements such as visual guidance and timed activities. The interfaces shown are illustrative snippets of generated UX.
Figure 2. System overview of GUIDE. The system first elicits user context through a structured conversation and produces a concise summary. It then generates multiple candidate interventions from this context and selects one using rubric-guided evaluation. Given user context and the selected intervention, the system composes candidate UX realizations from a set of interaction modules (e.g., audio, text, timer) and selects the final experience through a second rubric-based selection process.
| Primitive ( ) | Parameters ( ) | Interaction Type |
| Text Input | prompt question; response hint; intervention purpose | Text |
| Choice Input | prompt question; response options; multiple selection; intervention purpose | Text |
| Audio Message | audio script; delivery tone; speaking rate; intervention purpose | Text/Audio |
| Guided Sequence | timed cue steps; audio cue script; intervention purpose | Text/Audio/Temporal |
| Image Display | image description prompt; intervention purpose | Text/Visual |
| Timer | duration; timer text; reflection prompt; intervention purpose | Text/Temporal |
Table 1. Representative interaction primitives used to construct generated intervention experiences. The full set of primitives is shown in Table 4 .
| Outcome | Measure and Scoring |
| Primary outcomes | |
| Stress reduction | “How stressful is the situation you are thinking about?” measured before and after the activity ( Bhattacharjee et al., 2024a ) . Rated 1–5; . |
| User experience | UEQ-8 user experience scale measured after the activity ( Hinderks, 2017 ) . Mean of 8 items, rescaled to . |
| Exploratory outcomes | |
| Stress mindset improvement | 8-item stress mindset scale measured before and after the activity ( Crum et al., 2013 ) . Rated 0–4; . |
| Perceived personalization | “The suggested activity felt personalized to my specific situation.” (post, 1–5 agreement) |
Table 2. Outcome measures used in the study.
| Outcome | GUIDE | Control | p | Cohen’s |
| (M SD) | (M SD) | |||
| Primary outcomes | ||||
| Stress reduction* | 0.65 0.7 | 0.35 0.8 | .02 | 0.39 |
| User experience* | 0.49 0.6 | 0.33 0.6 | .04 | 0.27 |
| Exploratory outcomes | ||||
| Stress mindset improvement | 1.44 3.1 | 0.75 3.5 | .09 | 0.21 |
Table 3. Summary of outcome measures for participants in the GUIDE and Control conditions.
Figure 3. (a) Co-occurrence of interaction types across generated intervention experiences (diagonal = total usage; off-diagonal = pairwise co-occurrence). (b) Interaction type usage across intervention combinations. Values represent the proportion of sessions within each combination that include the interaction type; CR = Cognitive restructuring, BA = Behavioral activation, RS = Regulation strategies.
Appendix figures & tables13 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 4. Ablation study results across four conditions defined by the presence or absence of rubric guidance in intervention and UX generation
| Primitive ( ) | Parameters ( ) | Interaction Type |
| Choice Input | prompt question; response options; multiple selection setting; intervention purpose | Text |
| Text Input | prompt question; response hint; intervention purpose | Text |
| List Entry Input | list prompt; item labels; item response hints; intervention purpose | Text |
| Chatbot | prompt question; system persona; intervention purpose; conversation history | Text/Audio |
| Audio Message | audio script; delivery tone; voice pitch; speaking rate; intervention purpose; guidance rationale | Text/Audio |
| Guided Sequence | timed cue steps; audio cue script; intervention purpose | Text/Audio/ Temporal |
Table 4. Overview of interaction primitives, their parameters, and interaction types.
Figure 5. Illustrative examples of interaction types used to construct intervention experiences. In practice, each type can take many forms and be combined in different ways depending on the intervention and user context (See Figures 7 , 8 , and 9 ).
| Rubric | Description | Rationale |
| Narrative Flow | Whether the reflective and action oriented steps form a clear and continuous experience where each step connects naturally to the next. | Supports coherence in multi-step interventions (prior work ( Persson et al., 2025 ) ) |
| Small Progress | Whether the sequence ends with a concrete outcome such as a clarified sentence, named emotion, reframe, or small action. | Emphasizes actionable outcomes (expert feedback) |
| Safe Sequencing | Whether the steps remain low intensity, clearly bounded, and easy to pause, avoiding heavy emotional processing. | Reduces risk in brief interventions (prior work ( Persson et al., 2025 ) ; expert feedback) |
| Explicit Alignment with Psychology Principles | Whether the activity clearly names the psychological principle and demonstrates how the steps enact it. | Improves transparency and learning (prior work ( Mohr et al., 2014 ; Persson et al., 2025 ; Paredes et al., 2014 ) ) |
| Specificity | Whether the activity reuses the user’s phrases, routines, or constraints so the activity clearly belongs to their situation. | Enhances perceived relevance (prior work ( Yardley et al., 2015 ) ) |
| Non-retrievability | Whether the activity depends on the user’s specific context and would not easily apply to another person. | Avoids generic responses (expert feedback) |
Table 5. Intervention judge rubrics used to evaluate the quality of generated interventions.
| Rubric | Description | Rationale |
| Intervention-Interface Alignment | Whether the overall structure of the interface reflects the user’s request and presents modules in a clear, stepwise progression. | Ensures alignment between user intent and interaction flow (prior work ( Nielsen, 1994 ; Hartmann et al., 2008 ) ) |
| Task Efficiency | Whether the activity can be completed with minimal friction, limited typing, and within the intended time window. | Reduces effort and supports short, feasible interventions (expert feedback) |
| Usability | Whether interactive controls are clear, visible, and actionable, with consistent navigation and feedback. | Improves interaction reliability and ease of use (prior work ( Nielsen, 1994 ; Hartmann et al., 2008 ; Brooke and others, 1996 ) ) |
| Information Clarity | Whether content is structured, concise, and easy to scan, reducing cognitive load. | Supports comprehension and reduces overload (prior work ( Nielsen, 1994 ; Hartmann et al., 2008 ) ) |
| Interaction Satisfaction | Whether the experience ends with a clear sense of completion, visual consistency, and smooth transitions. | Reinforces completion and overall experience quality (prior work ( Nielsen, 1994 ; Hartmann et al., 2008 ) ; expert feedback) |
| Specificity | Whether the interface incorporates the user’s specific situation through wording, examples, or UI elements. | Enhances contextual relevance and personalization (prior work ( Yardley et al., 2015 ) ) |
Table 6. UX judge rubrics used to evaluate the quality of generated interaction experiences.
Figure 6. Rubric-guided selection of intervention candidates. Given a user context, multiple candidate interventions are generated and evaluated across rubric criteria, and the highest-scoring intervention is selected. UX structure is also generated in a similar process.
| Outcome | Condition (GUIDE) | Pre-stress | PSS | Stress mindset (pre) | Age | Race (White) | Race (PNA) | Gender (Male) |
| Post-stress | -0.28** (0.10) | 0.59*** (0.08) | 0.01 (0.01) | -0.01 (0.01) | 0.08* (0.04) | -0.15 (0.16) | -0.28* (0.11) | -0.09 (0.13) |
Table 7. Regression predicting post-intervention stress controlling for pre-stress and demographic variables
| Outcome | Condition (GUIDE) | Pre-stress | PSS | Stress mindset (pre) | Age | Race (White) | Race (PNA) | Gender (Male) |
| UEQ mean | 0.12 (0.09) | 0.08 (0.06) | -0.01 (0.01) | 0.01 (0.01) | 0.01 (0.03) | -0.03 (0.15) | 0.01 (0.20) | -0.05 (0.10) |
Table 8. Regression predicting post-intervention user experience (UEQ) controlling for pre-stress and demographic variables
| Outcome | Condition (GUIDE) | Pre-stress | Log-transformed time |
| Post-stress | -0.30** (0.10) | 0.67*** (0.07) | 0.02 (0.07) |
Table 9. Regression predicting post-intervention stress controlling for pre-stress and time spent
| Outcome | Pre-stress | Audio | Visual | Temporal |
| Post-stress | 0.22** (0.08) | -0.18 (0.18) | -0.08 (0.20) | 0.06 (0.15) |
Table 10. Regression predicting post-intervention stress within the GUIDE condition using interaction type presence
Figure 7. Example of a generated support experience for a user stressed about an exam, composed of a timer-based activity and list entry input. The two screens show consecutive steps in the same interaction flow, illustrating how the experience unfolds through structured guidance and user input.
Figure 8. Example of a generated support experience for a user stressed about a recent meeting, composed of a list entry input, an audio message, and text-based questions. The two screens show consecutive steps in the same interaction flow.
Figure 9. Example of a generated support experience for a user stressed about a family member, composed of a visual card pair and text-based questions. The two screens show consecutive steps in the same interaction flow.