Related Experiment Video
Updated: Jun 26, 2025
14:02
Measuring Engagement of Spectators of Social Digital Games
Published on: July 3, 2021
3.5K
Detecting Social Contexts from Mobile Sensing Indicators in Virtual Interactions with Socially Anxious Individuals
Zhiyuan Wang1, Maria A Larrazabal2, Mark Rucker1
1Department of Systems and Information Engineering, University of Virginia, USA.
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
|May 13, 2024
Summary
Mobile sensing accurately detects virtual social contexts for social anxiety research. This technology can identify social situations and phases, aiding in understanding social avoidance patterns.
Area of Science:
- Digital Phenotyping
- Computational Social Science
- Mental Health Technology
Background:
- Mobile sensing offers insights into mental health via physiological and behavioral patterns.
- Detecting social contexts enhances understanding of social interactions, academic, work, and social lives.
- Passive social context detection is valuable for social anxiety research, potentially identifying avoidance and withdrawal patterns.
Purpose of the Study:
- To examine the feasibility of detecting experimentally manipulated virtual social contexts using wristband sensors in socially anxious students.
- To investigate the utility of passively sensed biobehavioral data for identifying social situation presence, group size, social evaluation, and situation phase.
- To inform the design of passive context detection systems for mental health applications.
Main Methods:
- Recruited 46 undergraduate students with high social anxiety.
- Employed a multitask machine learning pipeline utilizing passively sensed biobehavioral data streams.
- Experimentally manipulated virtual social contexts to serve as ground truth for detection.
Main Results:
- Demonstrated feasibility in detecting most virtual social contexts.
- Achieved higher accuracy in identifying the presence of social situations and their phases.
- Observed lower accuracy in detecting the degree of social evaluation.
- Identified differential importance of sensing streams for predicting various contexts.
- Provided insights into optimal sensing duration, modality utility, and personalization needs.
Conclusions:
- Passive mobile sensing can effectively detect key features of virtual social contexts relevant to social anxiety.
- Findings support the development of just-in-time adaptive interventions for social anxiety.
- Future research should consider personalization and optimal sensing strategies for context detection.
More Related Videos
Related Concept Videos
01:28Social Anxiety Disorder
33
Social anxiety disorder, also known as social phobia, is characterized by an intense fear of social situations where one might face humiliation, rejection, embarrassment, or negative evaluation. This disorder leads individuals to avoid activities like casual conversations, public speaking, or seemingly simple tasks such as eating, signing documents, or swimming, in public settings. Its impact extends beyond discomfort, often significantly interfering with daily functioning and quality of life.
33
01:19Autism Spectrum Disorder
83
Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by persistent deficits in social communication and interaction alongside restrictive and repetitive behaviors or interests. ASD is sometimes accompanied by intellectual impairment.
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.
83