Georgia Institute of Technology
Using Natural Language Processing for Understanding and Development of Online Mental Health Platforms
Abstract
dc:description.abstractTherapy is expensive and inaccessible, and in certain countries, there is a negative stigma attached to seeking mental health help. As a result, millions of users look towards online platforms for their mental health needs. Often, these platforms are a mix of "counseling sessions" and "support groups", where a counselor and a support seeker are paired in a private one-to-one fashion but the counselors are non-professionals offering support through shared experiences. Despite having a large prevalence and user base of Online Mental Health Communities, there have been limited systematic studies on the efficacy and development of such platforms. In this work, we use Natural Language Processing tools to explore two research directions for understanding these platforms. First, we leverage a large amount of psychology-based counseling literature on successful therapist skills to model counselors' behavior on online peer-to-peer mental health platforms. Second, we define success outcomes on such platforms and understand how counselor behaviors may be indicative of conversation success. This research hopes to lay the foundation work for the development and increase in efficacy of Online Mental Health Communities for greater support seeker betterment.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Computer Science
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shah, Raj Sanjay
- Advisors dc:contributor.advisor
-
- Yang, Diyi
- Varma, Sashank
- Committee member dc:contributor.committeemember
-
- Kumar, Srijan
Subjects
dc:subject × 3Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/72014