MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · 21.11.2024 · 8 (4) · 1-44
DOI: 10.1145/3699761 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, online erschienen am 21.11.2024. Verfasst von Subigya Nepal und 16 weiteren Autor:innen. Beteiligte Einrichtung: Dartmouth College, USA. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIMH NIH HHS, NIMH.
Abstract (Originalsprache)
Mental health concerns are prevalent among college students, highlighting the need for effective interventions that promote self-awareness and holistic well-being. MindScape explores 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). 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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Dartmouth College, USA.
- Colby College, USA.
- Brown University, USA.
- Cornell Tech, USA.
- Massachusetts Institute of Technology, USA.
- University College London, UK.
Förderung
- NIMH NIH HHS
- NIMH
Zitieren
APA
Nepal, S., Pillai, A., Campbell, W., Massachi, T., Heinz, M. V., Kunwar, A., Choi, E. S., Xu, X., Kuc, J., Huckins, J. F., Holden, J., Preum, S. M., Depp, C., Jacobson, N., Czerwinski, M. P., Granholm, E., & Campbell, A. T. (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), 1-44. https://doi.org/10.1145/3699761
Vancouver
Nepal S, Pillai A, Campbell W, Massachi T, Heinz MV, Kunwar A, et al. MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 2024;8(4):1-44. doi:10.1145/3699761
BibTeX
@article{Nepal2024,
author = {Nepal, Subigya and Pillai, Arvind and Campbell, William and Massachi, Talie and Heinz, Michael V and Kunwar, Ashmita and Choi, Eunsol Soul and Xu, Xuhai and Kuc, Joanna and Huckins, Jeremy F and Holden, Jason and Preum, Sarah M and Depp, Colin and Jacobson, Nicholas and Czerwinski, Mary P and Granholm, Eric and Campbell, Andrew T},
title = {MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiences},
journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
year = {2024},
volume = {8},
number = {4},
pages = {1--44},
doi = {10.1145/3699761}
}
EUVIMED