Causal Categorization of Mental Health Posts using Transformers

TL;DR

This paper explores using transformer models with transfer learning to improve causal categorization of mental health posts on social media, emphasizing the importance of cause-and-effect understanding for better classification accuracy.

Contribution

It introduces a transformer-based transfer learning approach for causal categorization in mental health social media posts, addressing data scarcity issues.

Findings

Improved classification accuracy with transformer models

Demonstrated effectiveness of transfer learning on CAMS dataset

Highlighting the importance of cause-effect relationship detection

Abstract

With recent developments in digitization of clinical psychology, NLP research community has revolutionized the field of mental health detection on social media. Existing research in mental health analysis revolves around the cross-sectional studies to classify users' intent on social media. For in-depth analysis, we investigate existing classifiers to solve the problem of causal categorization which suggests the inefficiency of learning based methods due to limited training samples. To handle this challenge, we use transformer models and demonstrate the efficacy of a pre-trained transfer learning on "CAMS" dataset. The experimental result improves the accuracy and depicts the importance of identifying cause-and-effect relationships in the underlying text.