A Hierarchical Attention Network-Based Approach for Depression Detection from Transcribed Clinical Interviews

Abstract

The high prevalence of depression in society has given rise to a need for new digital tools that can aid its early detection. Among other effects, depression impacts the use of language. Seeking to exploit this, this work focuses on the detection of depressed and non-depressed individuals through the analysis of linguistic information extracted from transcripts of clinical interviews with a virtual agent. Specifically, we investigated the advantages of employing hierarchical attention-based networks for this task. Using Global Vectors (GloVe) pretrained word embedding models to extract low-level representations of the words, we compared hierarchical local-global attention networks and hierarchical contextual attention networks. We performed our experiments on the Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WoZ) dataset, which contains audio, visual, and linguistic information acquired from participants during a clinical session. Our results using the DAIC-WoZ test set indicate that hierarchical contextual attention networks are the most suitable configuration to detect depression from transcripts. The configuration achieves an Unweighted Average Recall (UAR) of .66 using the test set, surpassing our baseline, a Recurrent Neural Network that does not use attention.

Adventitious Respiratory Classification Using Attentive Residual Neural Networks

“…Similarly, the attention mechanism leads CNN models to focus on the most relevant areas of an image-by this increasing their understanding-which usually optimises CNN performance [23]. Several attention-based modules have been proposed, showing that this mechanism can optimise the abilities of neural networks on feature recognition [24,25,26,27].…”

Predicting Depression in Screening Interviews from Latent Categorization of Interview Prompts

“…More recent approaches are based on deep learning. Yang et al (2017) propose a CNNbased model leveraging jointly trained paragraph vectorizations, Al Hanai et al (2018) propose an LSTM-based model fusing audio features with Doc2Vec representations of response text, Makiuchi et al (2019) combine LSTM andCNN components, andMallol-Ragolta et al (2019) propose a model that uses a hierarchical attention mechanism. However, these approaches are more opaque and difficult to interpret.…”

“…To capitalize on this source of information, recent work has proposed deep learning models that leverage linguistic features to identify depressed individuals (Mallol-Ragolta et al, 2019). Such deep learning models achieve high performance by uncovering complex, unobservable patterns in data at the cost of transparency.…”

Cough-Based COVID-19 Detection with Contextual Attention Convolutional Neural Networks and Gender Information

“…AI-based systems have been successfully employed to detect coughs or sneezes [1], or to analyse breath signals [2], among others. Furthermore, AI has also been used in the field of mental health, providing solutions to recognise mental illnesses, such as depression [3,4,5] or Post-Traumatic Stress Disorder (PTSD) [6]. The current context of the pandemic challenges researchers to focus on the development of automatic COVID-19 detection tools.…”