Contextual AI Journaling: Integrating LLM and Time Series Behavioral Sensing Technology to Promote Self-Reflection...

Area of Science:

• Artificial Intelligence
• Human-Computer Interaction
• Digital Well-being

Background:

• Current journaling methods lack personalization and context.
• Integrating behavioral data can offer deeper self-insight.
• Large Language Models (LLMs) show potential for advanced AI applications.

Purpose of the Study:

• To explore the benefits of combining time series behavioral patterns with LLMs for AI journaling.
• To introduce the MindScape application, a novel contextual AI journaling tool.
• To assess the effectiveness of AI journaling in promoting college student well-being.

Main Methods:

• Developing the MindScape app integrating LLMs and behavioral sensing (conversational engagement, sleep, location).
• Designing personalized journaling prompts to foster self-reflection and emotional development.
• Conducting user studies with college students to evaluate the app's impact.

Main Results:

• Preliminary user study indicates potential for enhanced self-reflection.
• Upcoming study will quantitatively assess well-being improvements.
• MindScape demonstrates a new class of AI applications embedding behavioral intelligence.

Conclusions:

• Integrating behavioral sensing with LLMs offers a new frontier in AI for personalized well-being.
• Contextual AI journaling shows promise for improving self-reflection and emotional development.
• MindScape represents a significant step towards AI-driven mental health support.