Using Natural Language Processing for Understanding and Development of Online Mental Health Platforms
Author(s)
Shah, Raj Sanjay
Advisor(s)
Varma, Sashank
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Therapy 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.
Sponsor
Date
2023-05-02
Extent
Resource Type
Text
Resource Subtype
Thesis