MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences
Mental health concerns are prevalent among college students, highlighting the need for effective interventions that promote self-awareness and holistic well-being. MindScape pioneers a novel approach to AI-powered journaling by integrating passively collected behavioral patterns such as conversation...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ACM
2024
|
| Online Access: | https://hdl.handle.net/1721.1/157901 |
| _version_ | 1824457990132989952 |
|---|---|
| author | Nepal, Subigya Pillai, Arvind Campbell, William Massachi, Talie Heinz, Michael Kunwar, Ashmita Choi, Eunsol Soul Xu, Xuhai "Orson" Kuc, Joanna Huckins, Jeremy Holden, Jason Preum, Sarah M. Depp, Colin Jacobson, Nicholas Czerwinski, Mary Granholm, Eric Campbell, Andrew |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Nepal, Subigya Pillai, Arvind Campbell, William Massachi, Talie Heinz, Michael Kunwar, Ashmita Choi, Eunsol Soul Xu, Xuhai "Orson" Kuc, Joanna Huckins, Jeremy Holden, Jason Preum, Sarah M. Depp, Colin Jacobson, Nicholas Czerwinski, Mary Granholm, Eric Campbell, Andrew |
| author_sort | Nepal, Subigya |
| collection | MIT |
| description | Mental health concerns are prevalent among college students, highlighting the need for effective interventions that promote self-awareness and holistic well-being. MindScape pioneers a novel approach to AI-powered journaling by integrating passively collected behavioral patterns such as conversational engagement, sleep, and location with Large Language Models (LLMs). This integration creates a highly personalized and context-aware journaling experience, enhancing self-awareness and well-being by embedding behavioral intelligence into AI. We present an 8-week exploratory study with 20 college students, demonstrating the MindScape app's efficacy in enhancing positive affect (7%), reducing negative affect (11%), loneliness (6%), and anxiety and depression, with a significant week-over-week decrease in PHQ-4 scores (-0.25 coefficient), alongside improvements in mindfulness (7%) and self-reflection (6%). The study highlights the advantages of contextual AI journaling, with participants particularly appreciating the tailored prompts and insights provided by the MindScape app. Our analysis also includes a comparison of responses to AI-driven contextual versus generic prompts, participant feedback insights, and proposed strategies for leveraging contextual AI journaling to improve well-being on college campuses. By showcasing the potential of contextual AI journaling to support mental health, we provide a foundation for further investigation into the effects of contextual AI journaling on mental health and well-being. |
| first_indexed | 2025-02-19T04:18:46Z |
| format | Article |
| id | mit-1721.1/157901 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:18:46Z |
| publishDate | 2024 |
| publisher | ACM |
| record_format | dspace |
| spelling | mit-1721.1/1579012025-02-14T16:26:17Z MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences Nepal, Subigya Pillai, Arvind Campbell, William Massachi, Talie Heinz, Michael Kunwar, Ashmita Choi, Eunsol Soul Xu, Xuhai "Orson" Kuc, Joanna Huckins, Jeremy Holden, Jason Preum, Sarah M. Depp, Colin Jacobson, Nicholas Czerwinski, Mary Granholm, Eric Campbell, Andrew Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Mental health concerns are prevalent among college students, highlighting the need for effective interventions that promote self-awareness and holistic well-being. MindScape pioneers a novel approach to AI-powered journaling by integrating passively collected behavioral patterns such as conversational engagement, sleep, and location with Large Language Models (LLMs). This integration creates a highly personalized and context-aware journaling experience, enhancing self-awareness and well-being by embedding behavioral intelligence into AI. We present an 8-week exploratory study with 20 college students, demonstrating the MindScape app's efficacy in enhancing positive affect (7%), reducing negative affect (11%), loneliness (6%), and anxiety and depression, with a significant week-over-week decrease in PHQ-4 scores (-0.25 coefficient), alongside improvements in mindfulness (7%) and self-reflection (6%). The study highlights the advantages of contextual AI journaling, with participants particularly appreciating the tailored prompts and insights provided by the MindScape app. Our analysis also includes a comparison of responses to AI-driven contextual versus generic prompts, participant feedback insights, and proposed strategies for leveraging contextual AI journaling to improve well-being on college campuses. By showcasing the potential of contextual AI journaling to support mental health, we provide a foundation for further investigation into the effects of contextual AI journaling on mental health and well-being. 2024-12-19T22:30:52Z 2024-12-19T22:30:52Z 2024-11-21 2024-12-01T08:55:26Z Article http://purl.org/eprint/type/JournalArticle 2474-9567 https://hdl.handle.net/1721.1/157901 Nepal, Subigya, Pillai, Arvind, Campbell, William, Massachi, Talie, Heinz, Michael et al. 2024. "MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8 (4). PUBLISHER_POLICY en https://doi.org/10.1145/3699761 Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. The author(s) application/pdf ACM Association for Computing Machinery |
| spellingShingle | Nepal, Subigya Pillai, Arvind Campbell, William Massachi, Talie Heinz, Michael Kunwar, Ashmita Choi, Eunsol Soul Xu, Xuhai "Orson" Kuc, Joanna Huckins, Jeremy Holden, Jason Preum, Sarah M. Depp, Colin Jacobson, Nicholas Czerwinski, Mary Granholm, Eric Campbell, Andrew MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences |
| title | MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences |
| title_full | MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences |
| title_fullStr | MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences |
| title_full_unstemmed | MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences |
| title_short | MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences |
| title_sort | mindscape study integrating llm and behavioral sensing for personalized ai driven journaling experiences |
| url | https://hdl.handle.net/1721.1/157901 |
| work_keys_str_mv | AT nepalsubigya mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT pillaiarvind mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT campbellwilliam mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT massachitalie mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT heinzmichael mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT kunwarashmita mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT choieunsolsoul mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT xuxuhaiorson mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT kucjoanna mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT huckinsjeremy mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT holdenjason mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT preumsarahm mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT deppcolin mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT jacobsonnicholas mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT czerwinskimary mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT granholmeric mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences AT campbellandrew mindscapestudyintegratingllmandbehavioralsensingforpersonalizedaidrivenjournalingexperiences |