Jina Suh
University of Washington/Microsoft Research
jinasuh@cs.washington.edu
Bio
Jina Suh is a fourth year PhD student at Paul G. Allen School of Computer Science and Engineering at the University of Washington advised by James Fogarty and Tim Althoff. She is also a Principal Research Software Engineer in the Human Understanding and Empathy group at Microsoft Research. Her current interests lie in the design of technologies and application of data science and ML for improving mental health and well-being. She works with clinicians to deliver evidence-based interventions collaborates with product groups to improve workplace wellbeing and works with large datasets to quantify population-level shifts in wellbeing. She previously worked as an engineer in Xbox and in the Machine Teaching group at MSR where she grew her passion for HCI and ML. She received an MS in Human-Centered Design and Engineering from the University of Washington an MA in Physics from Harvard and a BA in Physics from Columbia.
Designing Mental Health and Wellbeing Interventions through Computational and Contextual Understanding
Designing Mental Health and Wellbeing Interventions through Computational and Contextual Understanding
As many as 20% of Americans suffer from diagnosable mental health disorders but those that are overwhelmed with physiological and economic burdens are still unable to prioritize seeking support for their mental health and wellbeing. Despite an abundance of promising technology-facilitated wellbeing solutions that exist today symptoms of stress anxiety and depression are often overlooked in constant tension with life demands and disruptions making it challenging to integrate such solutions into everyday life. My research focus is positioned at this intersection between everyday life and mental wellbeing where I design systems that integrate mental health and wellbeing interventions into everyday contexts to promote engagement. First I approach this design challenge by examining the specific human contexts where problems occur. In my prior work I examined cancer-depression comorbidities in multi-stakeholder clinic environments shifts of human needs during the pandemic for US subpopulations and workplace stress dynamics for information workers. Then to highlight where and how the resource tensions and challenges occur I employ a combination of qualitative and quantitative methods to obtain and analyze a spectrum of big and small data of different population sizes (individuals to countries) temporal scales (momentary to longitudinal) and types (subjective to passively observed). In my prior work I characterized the challenges at the seams of parallel cancer and psychosocial care journeys widening digital disparities for low socioeconomic subpopulations during the pandemic and contextual and behavioral contributors for workplace stress. Finally with this computational and contextual understanding I design and deploy intervention systems into these targeted contexts and evaluate their effectiveness in promoting engagement in wellbeing. Systems include clinician-facing patient registry and patient-facing tracking app to facilitate collaborative care and behavioral intervention loop as well as a chatbot to deliver just-in-time micro-interventions to alleviate workplace stress.