- Mental Health via Writing
- Digital Mental Health Interventions
- Topic Modeling
- Mental Health Research Topics
- Innovations in Medical Education
- Mental Health and Patient Involvement
- Health Sciences Research and Education
- Human-Automation Interaction and Safety
- Gender, Feminism, and Media
- Text Readability and Simplification
- Online Learning and Analytics
- Simulation-Based Education in Healthcare
- Mental Health Treatment and Access
- Social Media in Health Education
- Gender Studies in Language
- Intelligent Tutoring Systems and Adaptive Learning
- Empathy and Medical Education
- Primary Care and Health Outcomes
- Migration, Health and Trauma
- Hate Speech and Cyberbullying Detection
- Radiology practices and education
- Sex and Gender in Healthcare
- Impact of Technology on Adolescents
- Clinical Reasoning and Diagnostic Skills
- Healthcare Systems and Technology
University of Washington
2021-2024
Mental Health America
2023
Allen Institute for Artificial Intelligence
2023
Stanford University
2023
Cornell University
2020-2021
Online peer-to-peer support platforms enable conversations between millions of people who seek and provide mental health support. If successful, web-based could improve access to treatment reduce the global disease burden. Psychologists have repeatedly demonstrated that empathy, ability understand feel emotions experiences others, is a key component leading positive outcomes in supportive conversations. However, recent studies shown highly empathic are rare online platforms.
Self-guided mental health interventions, such as "do-it-yourself" tools to learn and practice coping strategies, show great promise improve access care. However, these interventions are often cognitively demanding emotionally triggering, creating accessibility barriers that limit their wide-scale implementation adoption. In this paper, we study how human-language model interaction can support self-guided interventions. We take cognitive restructuring, an evidence-based therapeutic technique...
Ashish Sharma, Kevin Rushton, Inna Lin, David Wadden, Khendra Lucas, Adam Miner, Theresa Nguyen, Tim Althoff. Proceedings of the 61st Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2023.
The emergence of ChatGPT and other large language models (LLMs) has greatly increased interest in utilizing LLMs as therapists to support individuals struggling with mental health challenges. However, due the lack systematic studies, our understanding how LLM behave, i.e., ways which they respond clients, is significantly limited. Understanding their behavior across a wide range clients situations crucial accurately assess capabilities limitations high-risk setting health, where undesirable...
Background and Objectives: Prior research has successfully identified linguistic behavioral patterns associated with schizophrenia spectrum disorders (SSD) from user generated social media activity. Few studies, however, have explored the potential for image analysis to inform psychiatric care individuals SSD. Given popularity of image-based platforms, such as Instagram, investigating data could further strengthen associations between activity health. Methods: We collected 11,947 Instagram...
Mental health stigma prevents many individuals from receiving the appropriate care, and social psychology studies have shown that mental tends to be overlooked in men. In this work, we investigate gendered masked language models. doing so, operationalize by developing a framework grounded research: use clinical literature curate prompts, then evaluate models' propensity generate words. We find models capture societal about gender health: are consistently more likely predict female subjects...
Background Lifelong learning is embedded in the culture of medicine, but there are limited tools currently available for many clinicians, including hospitalists, to help improve their own practice. Although requirements continuing medical education, resources new clinical guidelines, and developing fields aimed at facilitating peer-to-peer feedback, a gap availability that enable clinicians learn based on patients decisions. Objective The aim this study was explore technologies or...
Online peer-to-peer support platforms enable conversations between millions of people who seek and provide mental health support. If successful, web-based could improve access to treatment reduce the global disease burden. Psychologists have repeatedly demonstrated that empathy, ability understand feel emotions experiences others, is a key component leading positive outcomes in supportive conversations. However, recent studies shown highly empathic are rare online platforms. In this paper,...
Navigating certain communication situations can be challenging due to individuals' lack of skills and the interference strong emotions. However, effective learning opportunities are rarely accessible. In this work, we conduct a human-centered study that uses language models simulate bespoke training provide just-in-time feedback support practice interpersonal effectiveness skills. We apply framework from Dialectical Behavioral Therapy (DBT), DEAR MAN, which focuses on both conversational...
A proven therapeutic technique to overcome negative thoughts is replace them with a more hopeful "reframed thought." Although therapy can help people practice and learn this Cognitive Reframing of Negative Thoughts, clinician shortages mental health stigma commonly limit people's access therapy. In paper, we conduct human-centered study how language models may assist in reframing thoughts. Based on psychology literature, define framework seven linguistic attributes that be used reframe...
Mental health stigma prevents many individuals from receiving the appropriate care, and social psychology studies have shown that mental tends to be overlooked in men. In this work, we investigate gendered masked language models. doing so, operationalize by developing a framework grounded research: use clinical literature curate prompts, then evaluate models' propensity generate words. We find models capture societal about gender health: are consistently more likely predict female subjects...
Advances in artificial intelligence (AI) are enabling systems that augment and collaborate with humans to perform simple, mechanistic tasks like scheduling meetings grammar-checking text. However, such Human-AI collaboration poses challenges for more complex, creative tasks, as carrying out empathic conversations, due difficulties of AI understanding complex human emotions the open-ended nature these tasks. Here, we focus on peer-to-peer mental health support, a setting which empathy is...
Online peer-to-peer support platforms enable conversations between millions of people who seek and provide mental health support. If successful, web-based could improve access to treatment reduce the global disease burden. Psychologists have repeatedly demonstrated that empathy, ability understand feel emotions experiences others, is a key component leading positive outcomes in supportive conversations. However, recent studies shown highly empathic are rare online platforms. In this paper,...
Self-guided mental health interventions, such as "do-it-yourself" tools to learn and practice coping strategies, show great promise improve access care. However, these interventions are often cognitively demanding emotionally triggering, creating accessibility barriers that limit their wide-scale implementation adoption. In this paper, we study how human-language model interaction can support self-guided interventions. We take cognitive restructuring, an evidence-based therapeutic technique...
<sec> <title>BACKGROUND</title> Lifelong learning is embedded in the culture of medicine, but there are limited tools currently available for many clinicians, including hospitalists, to help improve their own practice. Although requirements continuing medical education, resources new clinical guidelines, and developing fields aimed at facilitating peer-to-peer feedback, a gap availability that enable clinicians learn based on patients decisions. </sec> <title>OBJECTIVE</title> The aim this...