CASE: Efficient Curricular Data Pre-training for Building Assistive Psychology Expert Models

TL;DR

This paper introduces CASE-BERT, a pre-trained NLP model that efficiently identifies mental health issues from online forum texts, addressing data scarcity and privacy concerns in mental health diagnostics.

Contribution

The study presents a novel curricular pre-training approach for NLP models using mental health institute texts, improving disorder detection accuracy in online forums.

Findings

CASE-BERT achieves an F1 score of 0.91 for Depression.

CASE-BERT achieves an F1 score of 0.88 for Anxiety.

The approach outperforms existing methods in mental health text analysis.

Abstract

The limited availability of psychologists necessitates efficient identification of individuals requiring urgent mental healthcare. This study explores the use of Natural Language Processing (NLP) pipelines to analyze text data from online mental health forums used for consultations. By analyzing forum posts, these pipelines can flag users who may require immediate professional attention. A crucial challenge in this domain is data privacy and scarcity. To address this, we propose utilizing readily available curricular texts used in institutes specializing in mental health for pre-training the NLP pipelines. This helps us mimic the training process of a psychologist. Our work presents CASE-BERT that flags potential mental health disorders based on forum text. CASE-BERT demonstrates superior performance compared to existing methods, achieving an f1 score of 0.91 for Depression and 0.88 for Anxiety, two of the most commonly reported mental health disorders. Our code and data are publicly available.