CoChat

Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text

Open access
Kirinde Gamaarachchige, Prasadith, Inkpen, Diana · 2019 · Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)

The DOI matches its Crossref record; 35 of the 36 references it cites were found in a registry or an index.

Abstract

We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and posttraumatic stress disorder) model built using a deep neural network architecture.Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection.We illustrate the effectiveness of using multitask learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability.Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90.In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/d19-6208

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Multi-task, multi-channel, multi-input model for mental illness detection
Figure 1 Multi-task, multi-channel, multi-input model for mental illness detectionCC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

  • Adam: A Method for Stochastic Optimization

    Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×

    “The Adam optimizer (Kingma and Ba, 2014) was used when training both the models with the default learning rate of 0.001.”
    MethodInfluential
  • Untitled work

    (2014) · Cited by 33,419

  • Enriching Word Vectors with Subword Information

    Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 1×

    “We decided to use fastText because given the unstructured nature of the twitter messages we could obtain a more meaningful representation by expressing a word as a vector constructed out of the sum of several vectors for different parts of the word (Bojanowski et al., 2017).”
    Method
  • Multitask Learning

    Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · cited 1×

    “Learning a shared representation so that individual tasks can benefit from one another (Caruana, 1997) can be considered as one of the most appropriate architectures when trying to detect multiple mental illnesses.”
    Background
  • Bag of Tricks for Efficient Text Classification

    Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2068 · Cited by 4,545

  • Bag of Tricks for Efficient Text Classification

    Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016) · arXiv · doi:10.48550/arxiv.1607.01759 · Cited by 4,542 · cited 2×

    “Even though our best results were obtained by instantiating the embedding layer weights with random numbers (refer Table 4), we conducted several preliminary experiments using word embeddings trained on the fastText (Joulin et al., 2017)”
    Method
  • Quantifying Mental Health Signals in Twitter

    Coppersmith, G., Dredze, M., & Harman, C. (2014) · Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w14-3207 · Cited by 722 · cited 2×

    “Social media text was used to classify users with insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmi…”
    Background
  • Predicting postpartum changes in emotion and behavior via social media

    De Choudhury, M., Counts, S., & Horvitz, E. (2013) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/2470654.2466447 · Cited by 462 · cited 1×

    “…media text was used to classify users with insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress…”
    Method
  • Characterizing and predicting postpartum depression from shared facebook data

    De Choudhury, M., Counts, S., Horvitz, E. J., & Hoff, A. (2014) · Proceedings of the 17th ACM conference on Computer supported cooperative work & social computing · doi:10.1145/2531602.2531675 · Cited by 379

  • Recognizing Depression from Twitter Activity

    Tsugawa, S., Kikuchi, Y., Kishino, F., Nakajima, K., Itoh, Y., & Ohsaki, H. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702280 · Cited by 334 · cited 1×

    “…et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmith et al., 2014a,b), schizophrenia (Loveys et al., 2017) and many other mental…”
    Background
  • Revisiting Small Batch Training for Deep Neural Networks

    Masters, D. A., & Luschi, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.07612 · Cited by 333 · cited 1×

    “In many cases, the optimal results were obtained by using batch sizes smaller or equal to 32 (Masters and Luschi, 2018).”
  • Deep Learning for Depression Detection of Twitter Users

    Husseini Orabi, A., Buddhitha, P., Husseini Orabi, M., & Inkpen, D. (2018) · Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic · doi:10.18653/v1/w18-0609 · Cited by 333 · cited 3×

    “Even though our experiments are to categorize users into three classes (i.e., control, depression, PTSD), the proposed multi-channel architecture have produced comparable results to the ones presented by Husseini Orabi et al. (2018) using binary classifi-cation to distinguish users susceptible to depression.”
    BackgroundResultInfluentialSelf-citation
  • From ADHD to SAD: Analyzing the Language of Mental Health on Twitter through Self-Reported Diagnoses

    Coppersmith, G., Dredze, M., Harman, C., & Hollingshead, K. (2015) · Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w15-1201 · Cited by 332 · cited 4×

    “Social media text was used to classify users with insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmi…”
    BackgroundMethodInfluential
  • CLPsych 2015 Shared Task: Depression and PTSD on Twitter

    Coppersmith, G., Dredze, M., Harman, C., Hollingshead, K., & Mitchell, M. (2015) · Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w15-1204 · Cited by 327 · cited 4×

    “Social media text was used to classify users with insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmi…”
    BackgroundMethodInfluential
  • Measuring post traumatic stress disorder in Twitter

    Coppersmith, G., Harman, C., & Dredze, M. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14574 · Cited by 316 · cited 2×

    “Social media text was used to classify users with insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmi…”
    Background
  • WASSA-2017 Shared Task on Emotion Intensity

    Mohammad, S., & Bravo-Marquez, F. (2017) · Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis · doi:10.18653/v1/w17-5205 · Cited by 270

  • Towards Assessing Changes in Degree of Depression through Facebook

    Schwartz, H. A., Eichstaedt, J., Kern, M. L., Park, G., Sap, M., Stillwell, D., Kosinski, M., & Ungar, L. (2014) · Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w14-3214 · Cited by 256 · cited 1×

    “…et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmith et al., 2014a,b), schizophrenia (Loveys et al., 2017) and…”
    Background
  • Beyond LDA: Exploring Supervised Topic Modeling for Depression-Related Language in Twitter

    Resnik, P., Armstrong, W., Claudino, L., Nguyen, T., Nguyen, V.-A., & Boyd-Graber, J. (2015) · Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w15-1212 · Cited by 235 · cited 2×

    “In the CLPSych 2015 shared task (Coppersmith et al., 2015b), Resnik et al. (2015a) have reported AUC scores of 0.86 (depression vs. control), 0.84 (depression vs. PTSD) and 0.89 (PTSD vs. control) and similarly Preotiuc-Pietro et al. (2015) have re-ported an average AUC score around 0.86 in…”
    BackgroundMethodInfluential
  • Ethical research protocols for social media health research

    Benton, A., Coppersmith, G., & Dredze, M. (2017) · Proceedings of the First ACL Workshop on Ethics in Natural Language Processing · doi:10.18653/v1/w17-1612 · Cited by 219 · cited 4×

    “Our best model has scored an AUC score > 0.90 in identifying all three individual classes (con-trol, depression, PTSD) in comparison to an AUC score < 0.80 for detecting PTSD and depression and an AUC score > 0.90 for detecting the neu-rotypical users (Benton et al., 2017b).”
    BackgroundMethodResultInfluential
  • SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions

    Cohan, A., Desmet, B., Yates, A., Soldaini, L., MacAvaney, S., & Goharian, N. (2018) · Ghent University Academic Bibliography (Ghent University) · doi:10.48550/arxiv.1806.05258 · Cited by 210 · cited 1×

    “In comparison, the proposed approach can be tested with adequate adjustments to detect multiple mental disorders such as depression, anxiety, PTSD, and six others using the dataset introduced by Cohan et al. (2018).”
    Method
  • The role of personality, age, and gender in tweeting about mental illness

    Preoţiuc-Pietro, D., Eichstaedt, J., Park, G., Sap, M., Smith, L., Tobolsky, V., Schwartz, H. A., & Ungar, L. (2015) · Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w15-1203 · Cited by 161 · cited 2×

    “it was identified that personality traits and metafeatures such as age and gender could have a positive impact on the model performances when detecting users susceptible to PTSD and depression (Preot et al., 2015).”
    BackgroundMethodInfluential
  • Detecting and Characterizing Mental Health Related Self-Disclosure in Social Media

    Balani, S., & De Choudhury, M. (2015) · Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/2702613.2732733 · Cited by 157 · cited 1×

    “The same level of self-disclosure can be identified in the Red-dit forums (Balani and De Choudhury, 2015) and specifically by users with anonymous accounts (Pavalanathan and De Choudhury, 2015).”
    Background
  • Perception Differences between the Depressed and Non-Depressed Users in Twitter

    Park, M., McDonald, D., & Cha, M. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v7i1.14425 · Cited by 135 · cited 2×

    “they reveal detailed information about their treatment history (Park et al., 2013).”
    Background
  • Major life changes and behavioral markers in social media: case of childbirth

    De Choudhury, M., Counts, S., & Horvitz, E. (2013) · Proceedings of the 2013 conference on Computer supported cooperative work · doi:10.1145/2441776.2441937 · Cited by 107 · cited 1×

    “…media text was used to classify users with insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress…”
    Method
  • Using Topic Modeling to Improve Prediction of Neuroticism and Depression in College Students

    Resnik, P., Garron, A., & Resnik, R. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1133 · Cited by 88 · cited 1×

    “…insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmith et al., 2014a,b),…”
    Background
  • Role of social media in tackling challenges in mental health

    De Choudhury, M. (2013) · Proceedings of the 2nd international workshop on Socially-aware multimedia · doi:10.1145/2509916.2509921 · Cited by 80 · cited 2×

    “…(Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmith et al., 2014a,b), schizophrenia (Loveys et…”
    Background
  • "I can't get no sleep": discussing #insomnia on twitter

    Jamison-Powell, S., Linehan, C., Daley, L., Garbett, A., & Lawson, S. (2012) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/2207676.2208612 · Cited by 77 · cited 2×

    “Social media text was used to classify users with insomnia and distress (Jamison-Powell et al., 2012; Lehrman et al., 2012), postpartum depression (De Choudhury et al., 2013a,b, 2014), depression (Resnik et al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress…”
    Method
  • Multi-Task Learning for Mental Health using Social Media Text

    Benton, A., Mitchell, M., & Hovy, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.03538 · Cited by 57 · cited 6×

    “Our best model has scored an AUC score > 0.90 in identifying all three individual classes (con-trol, depression, PTSD) in comparison to an AUC score < 0.80 for detecting PTSD and depression and an AUC score > 0.90 for detecting the neu-rotypical users (Benton et al., 2017b).”
    BackgroundMethodResultInfluential
  • The University of Maryland CLPsych 2015 Shared Task System

    Resnik, P., Armstrong, W., Claudino, L., & Nguyen, T. (2015) · Workshop on Computational Linguistics and Clinical Psychology (CLPsych) · doi:10.3115/v1/w15-1207 · Cited by 55 · cited 2×

    “In the CLPSych 2015 shared task (Coppersmith et al., 2015b), Resnik et al. (2015a) have reported AUC scores of 0.86 (depression vs. control), 0.84 (depression vs. PTSD) and 0.89 (PTSD vs. control) and similarly Preotiuc-Pietro et al. (2015) have re-ported an average AUC score around 0.86 in…”
    BackgroundMethodInfluential
  • Mental Illness Detection at the World Well-Being Project for the CLPsych 2015 Shared Task

    Preoţiuc-Pietro, D., Sap, M., Schwartz, H. A., & Ungar, L. (2015) · Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w15-1205 · Cited by 54 · cited 2×

    “and similarly Preotiuc-Pietro et al. (2015) have reported an average AUC score around 0.”
    BackgroundMethodInfluential
  • Small but Mighty: Affective Micropatterns for Quantifying Mental Health from Social Media Language

    Loveys, K., Crutchley, P., Wyatt, E., & Coppersmith, G. (2017) · Proceedings of the Fourth Workshop on Computational Linguistics and Clinical Psychology –- From Linguistic Signal to Clinical Reality · doi:10.18653/v1/w17-3110 · Cited by 49 · cited 1×

    “…al., 2015a, 2013, 2015b; Schwartz et al., 2014; Tsugawa et al., 2015), Post-Traumatic Stress Disorder (Coppersmith et al., 2014a,b), schizophrenia (Loveys et al., 2017) and many other mental illnesses such as Attention Deficit Hyperactivity Disorder (ADHD), Generalized Anxiety Disorder, Bipolar…”
    Background
  • Detecting and Explaining Crisis

    Kshirsagar, R., Morris, R., & Bowman, S. (2017) · Proceedings of the Fourth Workshop on Computational Linguistics and Clinical Psychology –- From Linguistic Signal to Clinical Reality · doi:10.18653/v1/w17-3108 · Cited by 34 · cited 1×

    “Kshirsagar et al. (2017) have used recurrent neural networks with attention to detect social media posts resembling crisis.”
    Background
  • The Role of Personality, Age and Gender in Tweeting about Mental Illnesses

    Preoțiuc-Pietro, D., Eichstaedt, J. C., Park, G., Sap, M., Smith, L., Tobolsky, V. A., Schwartz, H. A., & Ungar, L. (2015) · Cited by 31

  • Detecting Distressed and Non-distressed Affect States in Short Forum Texts

    Lehrman, M. T., Alm, C. O., & Proaño, R. A. (2012) · Cited by 22

  • Can social media help us reason about mental health?

    Choudhury, M. D. (2014) · International World Wide Web Conference (WWW) · doi:10.1145/2567948.2580064 · Cited by 22 · cited 2×

    “Due to the constraints as mentioned above and social media becoming an integral part of everyday life for many individuals, researchers have identified the importance of using social media data as a source for ascertaining individuals susceptible of mental disorders (De Choudhury, 2013, 2014).”
    Background

Research works printed but not linked: 1

  1. [28]28. Umashanthi Pavalanathan and Munmun De Choud- hury. 2015. Identity Management and Mental Health Discourse in Social Media Identity in Online Communities. In WWW'15 Companion: 24th Inter- national World Wide Web Conference, pages 18-22.

Cited by

See all 28

Metadata

Authors
Kirinde Gamaarachchige, P., & Inkpen, D.
Affiliations
University of Ottawa (CA)
Corresponding author
Inkpen, Diana
Venue
Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)
Published
2019
Pages
54-64
OpenAlex
W2983910710
Cited by
28
References
36
Citations by year
2026: 2 · 2025: 2 · 2024: 8 · 2023: 5 · 2022: 5 · 2021: 4 · 2020: 2
FWCI
4.55
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
International Workshop on Health Text Mining and Information Analysis (LOUHI) (publishedVersion, cc-by)
Topics
  • Social Sciences › Psychology › Social Psychology › Mental Health via Writing
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
  • Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
Keywords
mental disorder detection, depression detection, post-traumatic stress disorder, social media text, multi-task learning, multi-channel convolutional neural network, emotional patterns, suicidal ideation, shared representations

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.