Skip site navigation
University of Maryland Division of Research
Who We Are Capabilities Partnerships Resources News
Analytical Nuclear Magnetic Resonance (NMR) Service & Research Center Biomolecular Nuclear Magnetic Resonance (NMR) Facility Biosciences Cores: Genomics, Imaging, and Flow Cytometry BioWorkshop Brain & Behavior Institute - Advanced Genomic Technologies Core CALCE Test Services and Failure Analysis Laboratory Center For Innovative Biomedical Resources (CIBR) Clarice Smith Performing Arts Center Daikin Energy Innovation Lab DLAR Imaging Core Exposome Small Molecule Core Facility Glenn L. Martin Wind Tunnel Herschel S. Horowitz Center for Health Literacy KIT-Maryland MEG Lab Maryland Fire and Rescue Institute (MFRI) Maryland NanoCenter Maryland Neuroimaging Center Mass Spectrometry Facility Michelle Smith Collaboratory for Visual Culture Neutral Buoyancy Research Facility (NBRF) Surface Analysis Center The Laboratory for Biological Ultrastructure The University of Maryland Center for Health Equity The University of Maryland Prevention Research Center X-ray Crystallographic Center (XCC)
Africa Through Language and Area Studies (ATLAS) Anti-Black Racism Initiative Effective and Equitable Weather Forecasting in a Changing Climate with Machine Learning Encuentros: A University-Community Partnership to Mitigate the Mental Health Crisis for Latino Immigrant Youth Fostering Inclusivity through Technology (FIT) Helping Our Bodies Clear Respiratory Infections The Maryland Safe Drinking WATER Study Modeling the Evolution of Avian Influenza Viruses Music Education for All Through Personalized AI and Digital Humanities Observing Wildfires Through UAVs and Fire Imaging Technologies Programmable Design of Sustainable, All-Natural Plastic Substitutes Racial and Social Justice Research-Practice Partnership Collaborative Remediation of Methane, Water, and Heat Waste Seizing Opportunities: Social Capital, Businesses, and Communities Using Machine Learning to Measure and Improve Equity in K-12 Mathematics Classrooms Water Emergency Team
Accurate, Equitable, and Transparent Genetic Ancestry Inference Advancing Environmental Justice By Evaluating Climate-Ready Urban Street Trees In Historically Redlined Neighborhoods AFTER: A Hospital Violence Intervention Program For Youth Victims of Gunshot Injury An Innovative Intervention to Help Asian American Families Cope with Racism and Mental Health Difficulties Bridging the Gaps in Satellite Observations of Earth Systems to Support Climate Monitoring and Prediction Climate Change and Political Conflict Climate Mitigation and Land-Use Digital Equity Mapping Research and Training Program Establishing a Role for Psilocybin in Frontal Lobe Function Fetal Mammary Stem Cell Programming and Hormone Dysfunction Forecasting Acute Malnutrition for Anticipatory Action Genetic and Lifestyle Risk Factors of Accelerated Brain Aging in Severe Mental Illness How Does Statistical Learning Interact with Socioeconomic Status to Shape Literacy Development? Human Rights Politics and Policies: Lessons from Latin America Increasing Sustainability, Accessibility, and Equity in Urban Mobility with A Self-driving E-Scooter Increasing Participation of Minorities and Women In STEM Through Sports Performance Analytics Research Market Design, Energy Storage, and Interconnection to the U.S. Power Grid On-board Energy Harvesting for Long-endurance Earth Observation UAVs Promoting Youth Mental Wellbeing in Rural Honduras by Engaging Teachers as Catalysts Relating Attitudes on Democracy to Attitudes on Race and Ethnicity An Innovative Approach to Remove Emerging Organic Contaminants from the Environment Role of Mitochondria Dynamics in Opioid Addiction Towards an Early Warning System for Increased Probability of Community Infection by SARS-Cov-2 Variants Understanding the Impact of Wind on Fire Dynamics in Mass-Timber Compartment Visualizing Urban Flooding Due To Climate Change
Search
Who We Are Capabilities Partnerships Resources News
AI and Data Science

Could a Virtual Friend Improve Your Mental Health?

UMD Researcher Pioneers AI-Driven Virtual Reality "Emotional Assistant"

November 18, 2021

You’re feeling nervous as finals week approaches. A friend passing you on McKeldin Mall stops to ask how you’re feeling. “Good,” you reply with wince and a shrug.

The friend can plainly see from your facial expression and body language that “good” alone doesn’t capture the truth about your emotional state. Now, a UMD computer scientist has created a virtual “friend”—an artificial intelligence-driven virtual conversational assistant—which also can understand the subtleties about how you convey emotion.

Project Dost (named for the Hindi word for “friend”) combines data about gait, gesture, facial expression and speech intonation to generate the assistant that can interact in culturally sensitive contexts by perceiving, interpreting and responding to your emotions.

A Brain and Behavior Institute seed grant launched the project led by Aniket Bera, an assistant research professor of computer science with an appointment at the University of Maryland Institute for Advanced Computer Studies.

“In our daily lives, many of us use chatbots like Amazon Alexa, Google Home or Apple Siri, but these conversational voice agents feel impersonal,” said Bera. “Alexa doesn’t have empathy. It isn’t expressive. Dost feels more human.”

“If you’re going to put a human touch on it, you might as well make sure that it’s human.”

Such virtual friends, he said, could help bridge the gap between the high demand for mental health services and a low supply of practitioners, a gap that has grown wider during the pandemic. An AI program that understands human affect can help deploy medical practitioners to those in greatest need or provide information to a therapist. The real-time nature of Project Dost’s emotional sensitivity and expression both elicits and registers better information about emotional states, just as a friend would.

“When I say that Dost is an emotional friend, I mean that it engages not primarily with the content of a conversation but rather with how that conversation is happening,” said Bera. “The combination of speech, gesture, body language and facial expression is in itself an engineering marvel.”

Beyond the continued testing of Dost to ensure its clinical validation, Bera hopes that the project will generate undergraduate enthusiasm for a course in virtual reality crossed with artificial intelligence.

“Maryland is well-known for its expertise in AI, and there are exciting opportunities to strengthen partnerships between AI, neuroscience and computer science—particularly in a course that fully blends AI with virtual reality,” said Bera.

Original news story written by Nathaniel Underland