Evaluation of ChatGPT for NLP-based Mental Health Applications

TL;DR

This study evaluates ChatGPT's effectiveness in classifying social media posts for mental health indicators, demonstrating promising results especially in stress and depression detection, highlighting its potential for NLP-based mental health applications.

Contribution

The paper assesses ChatGPT's zero-shot classification performance on mental health tasks, providing insights into its capabilities and limitations compared to baseline models.

Findings

ChatGPT achieved F1 scores of 0.73 for stress detection, 0.86 for depression, and 0.37 for suicidality.

Baseline model's F1 scores were 0.35, 0.60, and 0.19 respectively.

Results suggest potential for LLMs in mental health classification with room for improvement.

Abstract

Large language models (LLM) have been successful in several natural language understanding tasks and could be relevant for natural language processing (NLP)-based mental health application research. In this work, we report the performance of LLM-based ChatGPT (with gpt-3.5-turbo backend) in three text-based mental health classification tasks: stress detection (2-class classification), depression detection (2-class classification), and suicidality detection (5-class classification). We obtained annotated social media posts for the three classification tasks from public datasets. Then ChatGPT API classified the social media posts with an input prompt for classification. We obtained F1 scores of 0.73, 0.86, and 0.37 for stress detection, depression detection, and suicidality detection, respectively. A baseline model that always predicted the dominant class resulted in F1 scores of 0.35, 0.60, and 0.19. The zero-shot classification accuracy obtained with ChatGPT indicates a potential use of language models for mental health classification tasks.