Improving Depression Level Estimation by Concurrently Learning Emotion Intensity

Depression is considered a serious medical condition and a large number of people around the world are suffering from it. Within this context, a lot of studies have been proposed to estimate the degree of depression based on different features and modalities, specific to depression. Supported by medical studies that show how depression is a disorder of impaired emotion regulation, we propose a different approach, which relies on the rationale that the estimation of depression level can benefit from the concurrent learning of emotion intensity. To test this hypothesis, we design different attention-based multi-task architectures that concurrently regress/classify both depression level and emotion intensity using text data. Experiments based on two benchmark datasets, namely, the Distress Analysis Interview Corpus - a Wizard of Oz (DAIC-WOZ), and the CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) show that substantial performance improvements can be achieved when compared to emotion-unaware single-task and multitask approaches.

[1]  Fabio Crestani,et al.  A Test Collection for Research on Depression and Language Use , 2016, CLEF.

[2]  Karin Ackermann,et al.  The Nature Of Emotion Fundamental Questions , 2016 .

[3]  Amit P. Sheth,et al.  Multi-Task Learning Framework for Mining Crowd Intelligence towards Clinical Treatment , 2018, NAACL.

[4]  I. Gotlib,et al.  Emotional variability and clarity in depression and social anxiety , 2017, Cognition & emotion.

[5]  T. Strine,et al.  The PHQ-8 as a measure of current depression in the general population. , 2009, Journal of affective disorders.

[6]  Joachim Bingel,et al.  Identifying beneficial task relations for multi-task learning in deep neural networks , 2017, EACL.

[7]  G. Freedman,et al.  Burden of Depressive Disorders by Country, Sex, Age, and Year: Findings from the Global Burden of Disease Study 2010 , 2013, PLoS medicine.

[8]  Nan Hua,et al.  Universal Sentence Encoder , 2018, ArXiv.

[9]  Fabien Ringeval,et al.  AVEC 2017: Real-life Depression, and Affect Recognition Workshop and Challenge , 2017, AVEC@ACM Multimedia.

[10]  Hamdi Dibeklioglu,et al.  Multimodal Detection of Depression in Clinical Interviews , 2015, ICMI.

[11]  Nancy M. Lorenzi,et al.  Mental Health Practice in a Digital World , 2015 .

[12]  Erik Cambria,et al.  Multi-level Multiple Attentions for Contextual Multimodal Sentiment Analysis , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[13]  Louis-Philippe Morency,et al.  Context-based signal descriptors of heart-rate variability for anxiety assessment , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Dongliang Li,et al.  A Random Forest Regression Method With Selected-Text Feature For Depression Assessment , 2017, AVEC@ACM Multimedia.

[15]  Erik Cambria,et al.  Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph , 2018, ACL.

[16]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[17]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[18]  Erik Cambria,et al.  Recent Trends in Deep Learning Based Natural Language Processing , 2017, IEEE Comput. Intell. Mag..

[19]  Ian H. Gotlib,et al.  Emotion regulation in depression: Relation to cognitive inhibition , 2010, Cognition & emotion.

[20]  Sriparna Saha,et al.  The Verbal and Non Verbal Signals of Depression - Combining Acoustics, Text and Visuals for Estimating Depression Level , 2019, ArXiv.

[21]  Rivka Levitan,et al.  Speech vs. text: A comparative analysis of features for depression detection systems , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[22]  Peter Robinson,et al.  OpenFace: An open source facial behavior analysis toolkit , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[23]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[24]  Erik Cambria,et al.  Multitask Representation Learning for Multimodal Estimation of Depression Level , 2019, IEEE Intelligent Systems.

[25]  David DeVault,et al.  The Distress Analysis Interview Corpus of human and computer interviews , 2014, LREC.

[26]  Dirk Hovy,et al.  Multitask Learning for Mental Health Conditions with Limited Social Media Data , 2017, EACL.

[27]  M. Millard,et al.  Detecting Linguistic Traces of Depression in Topic-Restricted Text: Attending to Self-Stigmatized Depression with NLP , 2018 .

[28]  Michelle Renee Morales,et al.  Multimodal Depression Detection: An Investigation of Features and Fusion Techniques for Automated Systems , 2018 .

[29]  Xuanjing Huang,et al.  Adversarial Multi-task Learning for Text Classification , 2017, ACL.

[30]  Thomas F. Quatieri,et al.  A review of depression and suicide risk assessment using speech analysis , 2015, Speech Commun..

[31]  Timothy F Chen,et al.  The psychometric properties of depression screening tools in primary healthcare settings: A systematic review. , 2018, Journal of affective disorders.

[32]  Kyu-Man Han,et al.  Comparison of the Usefulness of the PHQ-8 and PHQ-9 for Screening for Major Depressive Disorder: Analysis of Psychiatric Outpatient Data , 2019, Psychiatry investigation.

[33]  A. Beck,et al.  Depression: Causes and Treatment , 1967 .

[34]  Global, regional, and national incidence, prevalence, and years lived with disability for 301 acute and chronic diseases and injuries in 188 countries, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2015, The Lancet.

[35]  R. Spitzer,et al.  The PHQ-9: validity of a brief depression severity measure. , 2001, Journal of general internal medicine.

[36]  John Kane,et al.  COVAREP — A collaborative voice analysis repository for speech technologies , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[37]  Louis-Philippe Morency,et al.  MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos , 2016, ArXiv.

[38]  P. Renshaw,et al.  The diagnosis of depression: current and emerging methods. , 2013, Comprehensive psychiatry.

[39]  Gwen Littlewort,et al.  The computer expression recognition toolbox (CERT) , 2011, Face and Gesture 2011.

[40]  Stefan Scherer,et al.  A Linguistically-Informed Fusion Approach for Multimodal Depression Detection , 2018, CLPsych@NAACL-HTL.