AI-Powered Episodic Future Thinking
🤖 AI Summary
Obese adults exhibit heightened delay discounting and struggle to sustain health behaviors. Method: This study introduces a novel AI-powered intervention paradigm grounded in episodic future thinking (EFT), developing EFTeacher—a clinical-grade AI chatbot that deeply integrates GPT-4-Turbo into EFT training. Through human-in-the-loop prompt engineering, it generates personalized, vivid future-event cues; it also establishes an interpretable framework for EFT prompt generation and interactive design. Contribution/Results: A user study—including content feature questionnaires and semi-structured interviews—demonstrated high usability and perceived credibility: participants reported more vivid, engaging, and sustainable EFT experiences. The project yields a reusable AI-EFT design guideline, offering both methodological foundations and practical implementation pathways for leveraging large language models (LLMs) in behavioral medicine interventions.
Application Category
📝 Abstract
Episodic Future Thinking (EFT) is an intervention that involves vividly imagining personal future events and experiences in detail. It has shown promise as an intervention to reduce delay discounting - the tendency to devalue delayed rewards in favor of immediate gratification - and to promote behavior change in a range of maladaptive health behaviors. We present EFTeacher, an AI chatbot powered by the GPT-4-Turbo large language model, designed to generate EFT cues for users with lifestyle-related conditions. To evaluate the chatbot, we conducted a user study that included usability assessments and user evaluations based on content characteristics questionnaires, followed by semi-structured interviews. The study provides qualitative insights into participants' experiences and interactions with the chatbot and its usability. Our findings highlight the potential application of AI chatbots based on Large Language Models (LLMs) in EFT interventions, and offer design guidelines for future behavior-oriented applications.
Problem
Research questions and friction points this paper is trying to address.
AI chatbot generates EFT cues for obesity intervention
Evaluates feasibility of AI-driven Episodic Future Thinking
Addresses repetitive dialogue in personalized health chatbots
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI chatbot for generating EFT cues
GPT-4-Turbo powers personalized dialogues
Mixed-methods study evaluates usability
🔎 Similar Papers
No similar papers found.
