DreamDirector: Designing a Generative AI System to Aid Therapists in Treating Clients' Nightmares
Yijun Zhao, Zhengke Li, Yicheng Wang, Xueyan Cai, Xiaojing Zhou, Yifan Yan, Kecheng Jin, Shi-Ying Ding, Yilin Shao, Jia-Cheng Cao, Pin-Hao Wang, Cheng Yao, Ye Tao, Guanyun Wang
International Conference on Intelligent User Interfaces March 24, 2025 DOI: 10.1145/3708359.3712078 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Usability user study Peer reviewed |
|---|---|
| Sample size | 18 |
| Population | 2 therapists and 16 clients |
| Interventions | meditative texts based on Imagery Rehearsal Therapy (IRT) and Nightmare Deconstruction and Reprocessing (NDR) |
| Topics | Dreaming |
| Key points | The authors propose DreamDirector, a generative-AI system based on Imagery Rehearsal Therapy and Nightmare Deconstruction and Reprocessing that recollects a nightmare, interprets it with an LLM, and reprocesses it through AI-generated therapeutic visuals and meditative texts. In a usability study with 2 therapists and 16 clients, clients reported emotional relief and held a positive attitude toward the visual interaction. |
Abstract
Nightmares can adversely affect individuals’ mental health and well-being, necessitating timely psychological intervention. Current nightmare therapy has set high requirements for therapists, appeared abstract to clients, and showed poor interaction between them, due to its extensive information input, lack of sensory stimulation, and exclusive reliance on one-on-one conversation. We propose DreamDirector, a visual-interactive and narrative generative system powered by generative AI. Based on Imagery Rehearsal Therapy (IRT) and Nightmare Deconstruction and Reprocessing (NDR), the system can (1) recollect the nightmare scene, (2) interpret the dream with LLM, (3) reprocess the nightmare by generating therapeutic dream visuals using AI painting alongside meditative texts, and feedback with a picture book. Finally, we verified the usability of this system in terms of efficiency enhancement and interaction promotion through a user study with 2 therapists and 16 clients. The results revealed emotional relief among clients, with a positive and impressive attitude toward visual interaction.