Related Experiment Video
Updated: Jun 11, 2025

Measuring Neural and Behavioral Activity During Ongoing Computerized Social Interactions: An Examination of Event-Related Brain Potentials
Published on: November 15, 2014
Exploring Trade-Offs for Online Mental Health Matching: Agent-Based Modeling Study.
Yuhan Liu1, Anna Fang2, Glen Moriarty3
1Department of Computer Science, Princeton University, Princeton, NJ, United States.
Agent-based modeling optimizes online mental health community (OMHC) matching algorithms. Topic-based matching improves support seeker-counselor interactions, especially for marginalized groups, balancing satisfaction and success rates.
Area of Science:
- Computational Social Science
- Human-Computer Interaction
- Health Informatics
Background:
- Online mental health communities (OMHCs) offer accessible support but struggle with effective user matching.
- Current matching mechanisms in OMHCs are often naive, hindering optimal user interactions.
Purpose of the Study:
- To apply agent-based modeling (ABM) for designing and evaluating online community matching algorithms.
- To uncover trade-offs between different matching algorithms for support seekers and volunteer counselors in OMHCs.
Main Methods:
- Developed an agent-based simulation framework using comprehensive OMHC data (Jan 2020-Apr 2022).
- Validated the simulation against existing matching mechanisms.
- Utilized the validated simulation as a sandbox to test various matching algorithms, including deferred acceptance, first-come-first-served, and topic-based matching.
Main Results:
- Algorithmic choices create trade-offs; intelligent matching can increase waiting times for support seekers.
- Topic-based matching significantly improved chat ratings and reduced blocking incidents for all user groups, particularly benefiting underaged and gender minority populations.
- Filter-based matching for specific demographics improved outcomes for those groups but decreased overall user satisfaction.
Conclusions:
- Agent-based modeling is a valuable tool for understanding design considerations and trade-offs in OMHCs.
- Algorithmic matching, particularly topic-based approaches, shows potential for improving support quality and equity for marginalized users in online mental health settings.
More Related Videos
08:53Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
Published on: May 31, 2019
06:18The Collective Trust Game: An Online Group Adaptation of the Trust Game Based on the HoneyComb Paradigm
Published on: October 20, 2022
Related Concept Videos
Modeling in Therapy
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
Relationship Formation
Self-Presentation: Self-Monitoring and Self-Handicapping
Stereotype Content Model
Self-Discrepancy Theory
Self-Help Support Groups
Accessibility and Cost-Effectiveness
One of the primary strengths of self-help...