用生成式体验让心理干预更贴合用户互动方式，效果优于传统AI支持。
Generative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study
- 运行时动态生成个性化内容与多模态交互结构。
- 237人研究显示压力降低显著（p=0.02），用户体验提升（p=0.04）。
- 适合关注交互设计与心理干预融合的研究者与开发者。
数字心理健康（DMH）工具常聚焦于内容个性化，却忽视支持的体验形式。即使内容匹配，若交互方式不契合用户参与能力，仍可能失效。本文提出生成式体验方法，将干预体验在运行时动态组合。我们构建了GUIDE系统，通过规则引导生成模块化组件，实现内容与多模态交互结构的个性化生成。在一项预注册研究中，237名参与者显示，与基于LLM的认知重构对照组相比，GUIDE显著降低压力（p=0.02），改善用户体验（p=0.04）。系统支持多样化反思与行动路径，同时揭示了个性化在交互流程中引发的张力。本工作为数字环境中动态塑造支持体验奠定了基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。