Subigya Nepal, PhD
Assistant Professor of Computer Science, University of Virginia
Subigya Nepal is an assistant professor of computer science at the University of Virginia, where he leads research on AI-driven mental health sensing and intervention. His group uses AI to understand how people actually behave outside the lab — and to deliver personalized support at moments when it might help. This includes systems that detect early signs of depression from smartphone data and AI companions that know when and how to reach out.
Subigya led the longest continuous mobile sensing study of college students to date, tracking over 200 students across five years through the COVID-19 pandemic (College Experience Study). He developed MoodCapture, which detects depression from naturalistic smartphone images, and MindScape, a journaling app that uses behavioral sensing and large language models to generate personalized prompts based on sleep, activity, and social patterns. He has also built context-aware mobile interventions for people with serious mental illness. His work has received ACM UbiComp’s Distinguished Paper Award and the Neukom Outstanding Graduate Research Award, and has been covered by the Washington Post, Financial Times, and Bloomberg.
Subigya grew up in Kathmandu, Nepal, where he co-founded a technology startup before moving to the US for graduate school. He received his PhD in computer science (2024) from Dartmouth College, where he worked closely with CTBH. Before joining UVA, he was a postdoctoral fellow at Stanford’s Institute for Human-Centered AI and spent two summers at Microsoft Research studying workplace wellbeing.
Subigya is a founding board member of a nonprofit in New Hampshire that supports orphaned children in Nepal with housing, education, and healthcare. Outside of work, he’s trying to perfect his latte art.
Selected Publications
- Nepal S, Pillai A, Campbell W, Massachi T, Heinz MV, Kunwar A, Choi ES, Xu X, Kuc J, Huckins JF, Holden J, Preum SM, Depp C, Jacobson N, Czerwinski MP, Granholm E, Campbell AT. MindScape study: Integrating LLM and Behavioral sensing for personalized AI-driven journaling experiences. Proc ACM Interact Mob Wearable Ubiquitous Technol. 2024 Nov;8(4):186. doi: 10.1145/3699761.PMID: 39664112; PMCID: PMC11634059.
- Xu X, Liu X, Zhang H, Wang W, Nepal S, Sefidgar YS, Seo W, Kuehn KS, Huckins JF, Morris ME, Nurius PS, Riskin EA, Patel S, Althoff T, Campbell A, Dey AK, Mankoff J. GLOBEM: Cross-dataset generalization of longitudinal human behavior modeling. GetMobile: Mobile Computing and Communications. 2024 Jul 31;28(2), 23-30.
- Nepal S, Pillai A, Wang W, Griffin T, Collins AC, Heinz M, Lekkas D, Mirjafari S, Nemesure M, Price G, Jacobson NC, Campbell AT. MoodCapture: Depression detection using in-the-wild smartphone images. Proc SIGCHI Conf Hum Factor Comput Syst. 2024 May;2024:996. doi: 10.1145/3613904.3642680. PMID: 39100498; PMCID: PMC11296678.
- Nepal S, Liu W, Pillai A, Wang W, Vojdanovski V, Huckins JF, Rogers C, Meyer ML, Campbell AT. Capturing the college experience: A four-year mobile sensing study of mental health, resilience and behavior of college students during the pandemic. Proc ACM Interact Mob Wearable Ubiquitous Technol. 2024 Mar;8(1):38. doi: 10.1145/3643501. PMID: 39086982; PMCID: PMC11290409.
- Pillai A, Nepal SK, Wang W, Nemesure M, Heinz M, Price G, Lekkas D, Collins AC, Griffin T, Buck B, Preum SM, Cohen T, Jacobson NC, Ben-Zeev D, Campbell A. Investigating generalizability of speech-based suicidal ideation detection using mobile phones. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2024 Jan12; 7(4), Article 174.
- Nepal S, Pillai A, Parrish EM, Holden J, Depp C, Campbell AT, Granholm E. Social isolation and serious mental illness: The role of context-aware mobile interventions. IEEE Pervasive Comput. 2024 Jan-Mar;23(1):46-56. doi: 10.1109/mprv.2024.3377200. PMID: 39092185; PMCID: PMC11290146.
- Ben-Zeev D, Chander A, Tauscher J, Buck B, Nepal S, Campbell A, Doron G. A smartphone intervention for people with serious mental illness: Fully remote randomized controlled trial of CORE. J Med Internet Res. 2021 Nov 12;23(11):e29201. doi: 10.2196/29201. PMID: 34766913.