Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy

TL;DR

This paper introduces a deep learning approach to understanding mental health concepts from Cognitive Behavioural Therapy, using a new ontology and annotated corpus, significantly outperforming traditional models in this complex task.

Contribution

It presents a novel mental health ontology, annotated corpus, and deep learning models for understanding CBT-derived concepts in natural language.

Findings

Deep learning models outperform non-deep-learning models

Word and sentence embeddings improve understanding accuracy

The approach is essential for therapy dialogue systems

Abstract

In recent years, we have seen deep learning and distributed representations of words and sentences make impact on a number of natural language processing tasks, such as similarity, entailment and sentiment analysis. Here we introduce a new task: understanding of mental health concepts derived from Cognitive Behavioural Therapy (CBT). We define a mental health ontology based on the CBT principles, annotate a large corpus where this phenomena is exhibited and perform understanding using deep learning and distributed representations. Our results show that the performance of deep learning models combined with word embeddings or sentence embeddings significantly outperform non-deep-learning models in this difficult task. This understanding module will be an essential component of a statistical dialogue system delivering therapy.