Affective Conditioning on Hierarchical Networks applied to Depression Detection from Transcribed Clinical Interviews

TL;DR

This paper introduces a hierarchical neural network model with affective feature conditioning for depression detection from transcribed clinical interviews, achieving state-of-the-art results by leveraging affective language cues.

Contribution

It presents a novel hierarchical attention model augmented with affective lexical features for improved depression classification from speech transcripts.

Findings

Affective language is more prevalent in depressed individuals.

External affective features enhance model performance.

Achieved state-of-the-art F1 scores of 71.6 and 68.6 on two datasets.

Abstract

In this work we propose a machine learning model for depression detection from transcribed clinical interviews. Depression is a mental disorder that impacts not only the subject's mood but also the use of language. To this end we use a Hierarchical Attention Network to classify interviews of depressed subjects. We augment the attention layer of our model with a conditioning mechanism on linguistic features, extracted from affective lexica. Our analysis shows that individuals diagnosed with depression use affective language to a greater extent than not-depressed. Our experiments show that external affective information improves the performance of the proposed architecture in the General Psychotherapy Corpus and the DAIC-WoZ 2017 depression datasets, achieving state-of-the-art 71.6 and 68.6 F1 scores respectively.