Ubicomp Health and Wellness Lab
Our goal is to design technology to improve health and wellness outcomes. We address major challenges in health management, including patient engagement, continuity of care and point-of-care interaction. We do this by leveraging gold standards of care to design, build, and deploy ecological computational systems.
We conduct research at the intersection of mental health management and computer science. Our project, Prolonged Exposure Collective Sensing System (PECSS) addresses some of the pressing clinical challenges inherent in PTSD therapy; it leverages ubiquitous computing, human computer interaction and machine learning.
Representative Papers:
Perspectives on Integrating Trusted Other Feedback in Therapy for Veterans with PTSDHI Evans, CR Deeter, J Zhou, K Do, AM Sherrill, RI Arriaga
CHI Conference on Human Factors in Computing Systems, 1-16
Veteran Critical Theory as a Lens to Understand Veterans' Needs and Support on Social Media
J Zhou, K Saha, IM Lopez Carron, DW Yoo, CR Deeter… - Proceedings of the ACM on Human-Computer …, 2022
Understanding the Care Ecologies of Veterans with PTSDH Evans, U Lakshmi, H Watson, A Ismail, AM Sherrill, N Kumar, RI Arriaga Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
Diabetes effects about 1 in 10 Americans. Managing diabetes requires knowledge about a wide range of topics including nutrition, exercise and foot health. We are designing a Diabetes Ubiquitous Computational Sensing System (DUCSS) to streamline this information and to make it widely available in a manner that is useful and useable.
Representative Papers:
Intelligent Care Management for Diabetic Foot Ulcers: A Scoping Review of Computer Vision and Machine Learning Techniques and Applications, Baseman et al., 2023, Journal of Diabetes Science and Technology.
A pilot randomized trial of text-messaging for symptom awareness and diabetes knowledge in adolescents with type 1 diabetesY Han, MS Faulkner, H Fritz, D Fadoju, A Muir, GD Abowd, L Head, ...Journal of Pediatric Nursing 30 (6), 850-861
Turing Experiment?
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
Gati V. Aher, Rosa I. Arriaga, Adam Tauman Kalai Proc. of the 40th Intrl Conf on Machine Learning, 2023
We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model’s simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TEs and illustrate its use to compare how well different language models are able to reproduce classic economic, psycholinguistic, and social psychology experiments: Ultimatum Game, Garden Path Sentences, Milgram Shock Experiment, and Wisdom of Crowds. In the first three TEs, the existing findings were replicated using recent models, while the last TE reveals a “hyper-accuracy distortion” present in some language models (including ChatGPT and GPT-4), which could affect downstream applications in education and the arts.
VR for Meditation
ZenVR: Design Evaluation of a Virtual Reality Learning System for Meditation
ZenVR is an interactive system that delivers an 8-lesson meditation curriculum to support learners’ progress. A 6-week longitudinal lab-based evaluation with 15 novice meditation led to statistically significant improvements in mindfulness and self-reported meditation ability. Their insights from a self-managed practice, two weeks after the study ended, offered opportunities to understand how technology can be designed to provide progressive support without creating dependence in technology-mediated meditation practice
Asthma Apps for children & their caregivers
Simple interventions can IMPROVE children's lung function
A text message a day keeps the pulmonologist awayTJ Yun, RI Arriaga Proceedings of the SIGCHI Conference on Human Factors in Computing Systems …
SMS is my BFF: positive impact of a texting intervention on low-income children with asthmaTJ Yun, RI Arriaga, Proceedings of the 10th EAI International Conference on Pervasive Computing
Interfaces must be designed for children
Using an ecological framework to design mobile technologies for pediatric asthma managementHY Jeong, RI Arriaga Proceedings of the 11th International Conference on Human-Computer …
Even when icons are not worth a thousand words they are helpful in designing asthma mHealth toolsM Lefco, J Gise, B Lesnick, RI Arriaga
IFIP Conference on Human-Computer Interaction, 23-33
Join US us at the Health and Wellness Lab!
We are conducting impactful research at the intersection of health and wellness and having a LOT of FUN! Contact Dr. Arriaga (arriaga at cc.gatech.edu) if you are an undergrad or MS student interested in conducting research in our lab. Research opportunities are for credit (only).