Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Contextual AI Journaling: Integrating LLM and Time Series Behavioral Sensing Technology to Promote Self-Reflection and Well-being using the MindScape App

Subigya Nepal, Arvind Pillai, William Campbell, Talie Massachi, Eunsol Soul Choi, Orson Xu, Joanna Kuc, Jeremy Huckins, Jason Holden, Colin Depp, Nicholas Jacobson, Mary Czerwinski, Eric Granholm, Andrew T. Campbell

TL;DR

This paper introduces MindScape, a context-aware journaling app that fuses time-series behavioral sensing with LLM-generated prompts to foster self-reflection and well-being among college students. It collects on-device data (activity, sleep, location, digital habits) and uses GPT-4 to generate personalized, context-sensitive journaling prompts and four daily check-ins. A qualitative Phase 1 study with Dartmouth undergraduates informs design, and a larger-scale Phase 2 study is proposed to assess outcomes on mindfulness, emotion regulation, resilience, and well-being using standardized surveys and NLP analysis of journal entries. The work presents a new AI-enabled journaling paradigm that embeds behavioral intelligence into daily life, with privacy-preserving data handling and on-device considerations to support broader deployment in university settings and beyond.

Abstract

MindScape aims to study the benefits of integrating time series behavioral patterns (e.g., conversational engagement, sleep, location) with Large Language Models (LLMs) to create a new form of contextual AI journaling, promoting self-reflection and well-being. We argue that integrating behavioral sensing in LLMs will likely lead to a new frontier in AI. In this Late-Breaking Work paper, we discuss the MindScape contextual journal App design that uses LLMs and behavioral sensing to generate contextual and personalized journaling prompts crafted to encourage self-reflection and emotional development. We also discuss the MindScape study of college students based on a preliminary user study and our upcoming study to assess the effectiveness of contextual AI journaling in promoting better well-being on college campuses. MindScape represents a new application class that embeds behavioral intelligence in AI.

Contextual AI Journaling: Integrating LLM and Time Series Behavioral Sensing Technology to Promote Self-Reflection and Well-being using the MindScape App

TL;DR

This paper introduces MindScape, a context-aware journaling app that fuses time-series behavioral sensing with LLM-generated prompts to foster self-reflection and well-being among college students. It collects on-device data (activity, sleep, location, digital habits) and uses GPT-4 to generate personalized, context-sensitive journaling prompts and four daily check-ins. A qualitative Phase 1 study with Dartmouth undergraduates informs design, and a larger-scale Phase 2 study is proposed to assess outcomes on mindfulness, emotion regulation, resilience, and well-being using standardized surveys and NLP analysis of journal entries. The work presents a new AI-enabled journaling paradigm that embeds behavioral intelligence into daily life, with privacy-preserving data handling and on-device considerations to support broader deployment in university settings and beyond.

Abstract

MindScape aims to study the benefits of integrating time series behavioral patterns (e.g., conversational engagement, sleep, location) with Large Language Models (LLMs) to create a new form of contextual AI journaling, promoting self-reflection and well-being. We argue that integrating behavioral sensing in LLMs will likely lead to a new frontier in AI. In this Late-Breaking Work paper, we discuss the MindScape contextual journal App design that uses LLMs and behavioral sensing to generate contextual and personalized journaling prompts crafted to encourage self-reflection and emotional development. We also discuss the MindScape study of college students based on a preliminary user study and our upcoming study to assess the effectiveness of contextual AI journaling in promoting better well-being on college campuses. MindScape represents a new application class that embeds behavioral intelligence in AI.
Paper Structure (12 sections, 2 figures, 1 table)

This paper contains 12 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Study Design
  5. Mobile Sensing based Behavioral Data
  6. Personalized Journaling Prompts
  7. Context-aware Check-ins
  8. Results
  9. Phase 1: User Study
  10. Phase 2: Expected Results from Larger-Scale Study
  11. Ethical Considerations
  12. Conclusion

Figures (2)

  • Figure 1: MindScape App Workflow: Users sign in, set preferences in four categories, and start journaling with a notification tap. Journaling workflow includes an emoji based mood assessment, a one-minute breathing exercise, followed by contextual prompts. The final screen showcases the daily context-aware check-in.
  • Figure 2: Prompt Template for Weekday Journaling: The input prompt to GPT-4 is composed of four parts: 1) System prompt 2) User context 3) Rules to optimize the prompt and 4) The strategy to generate the journaling prompt.