mlsanityData to 7 Oct 2026

DEPTWEET: A Typology for Social Media Texts to Detect Depression Severities

arXiv 2210.05372 ↗First posted 10 Oct 2022cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

Mental health research through data-driven methods has been hindered by a lack of standard typology and scarcity of adequate data. In this study, we leverage the clinical articulation of depression to build a typology for social media texts for detecting the severity of depression. It emulates the standard clinical assessment procedure Diagnostic and Statistical Manual of Mental Disorders (DSM-5) and Patient Health Questionnaire (PHQ-9) to encompass subtle indications of depressive disorders from tweets. Along with the typology, we present a new dataset of 40191 tweets labeled by expert annotators. Each tweet is labeled as 'non-depressed' or 'depressed'. Moreover, three severity levels are considered for 'depressed' tweets: (1) mild, (2) moderate, and (3) severe. An associated confidence score is provided with each label to validate the quality of annotation. We examine the quality of the dataset via representing summary statistics while setting strong baseline results using attention-based models like BERT and DistilBERT. Finally, we extensively address the limitations of the study to provide directions for further research.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 26 of its 88 references that are in the map. First posted on arXiv 10 Oct 2022.

Builds on

26 of 88 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  8. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
  9. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  10. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  11. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  12. 2020A Primer in BERTology: What we know about how BERT workscited by 807
14 more
  1. 2019Text Summarization with Pretrained Encoderscited by 553
  2. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
  3. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 149
  4. 2019Scalable Zero-shot Entity Linking with Dense Entity Retrievalcited by 85
  5. 2019TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selectioncited by 74
  6. 2020Comparing BERT against traditional machine learning text classificationcited by 45
  7. 2020BEEP! Korean Corpus of Online News Comments for Toxic Speech Detectioncited by 39
  8. 2020Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Frameworkcited by 25
  9. 2017Semi-Supervised Approach to Monitoring Clinical Depressive Symptoms in Social Mediacited by 24
  10. 2020WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarizationcited by 23
  11. 2021Domain Adaptation with Pre-trained Transformers for Query Focused Abstractive Text Summarizationcited by 21
  12. 2020Six Attributes of Unhealthy Conversationcited by 19
  13. 2017Quantifying Mental Health from Social Media with Neural User Embeddingscited by 13
  14. 2021DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learningcited by 12

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 5.

12 papers.

  1. 2023Transformers in Healthcare: A Surveycited by 17
  2. 2024DepressionEmo: A novel dataset for multilabel classification of depression emotionscited by 10
  3. 2024A Comprehensive Evaluation of Large Language Models on Mental Illnessescited by 7
  4. 2025Datasets for Depression Modeling in Social Media: An Overviewcited by 5
  5. 2023Harnessing the Power of Hugging Face Transformers for Predicting Mental Health Disorders in Social Networkscited by 3
  6. 2025A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Contextcited by 3
  7. 2025A Survey on Multilingual Mental Disorders Detection from Social Media Datacited by 3
  8. 2024Depression detection in social media posts using transformer-based models and auxiliary featurescited by 2
  9. 2024The First Multilingual Model For The Detection of Suicide Textscited by 2
  10. 2025Semantic Label Drift in Cross-Cultural Translationcited by 2
  11. 20243M-Health: Multimodal Multi-Teacher Knowledge Distillation for Mental Health Detectioncited by 1
  12. 2025An Integrated Approach to AI-Generated Content in e-healthcited by 0