# Multi-Task Learning for Mental Health using Social Media Text

arXiv: https://arxiv.org/abs/1712.03538 · HTML: https://mlsanity.com/paper/1712.03538/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2017.

## Built on by (most cited first, 25 of 25)

- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [Reducing Privacy Risks in Online Self-Disclosures with Language Models](https://mlsanity.com/paper/2311.09538/) (2023)
- [Disembodied Machine Learning: On the Illusion of Objectivity in NLP](https://mlsanity.com/paper/2101.11974/) (2021)
- [Identifying Moments of Change from Longitudinal User Text](https://mlsanity.com/paper/2205.05593/) (2022)
- [Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health](https://mlsanity.com/paper/2109.13770/) (2021)
- [Diverse Perspectives, Divergent Models: Cross-Cultural Evaluation of Depression Detection on Twitter](https://mlsanity.com/paper/2406.15362/) (2024)
- [Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues](https://mlsanity.com/paper/2401.02746/) (2024)
- [Language Modelling as a Multi-Task Problem](https://mlsanity.com/paper/2101.11287/) (2021)
- [Combining Hierachical VAEs with LLMs for clinically meaningful timeline summarisation in social media](https://mlsanity.com/paper/2401.16240/) (2024)
- [SocioProbe: What, When, and Where Language Models Learn about Sociodemographics](https://mlsanity.com/paper/2211.04281/) (2022)
- [On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook](https://mlsanity.com/paper/2410.08793/) (2024)
- [Datasets for Depression Modeling in Social Media: An Overview](https://mlsanity.com/paper/2503.21513/) (2025)
- [Learning More for Free - A Multi Task Learning Approach for Improved Pathology Classification in Capsule Endoscopy](https://mlsanity.com/paper/2106.16162/) (2021)
- [Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses](https://mlsanity.com/paper/2206.11155/) (2022)
- [The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic](https://mlsanity.com/paper/2206.11160/) (2022)
- [Leveraging LLMs for Translating and Classifying Mental Health Data](https://mlsanity.com/paper/2410.12985/) (2024)
- [Speech as a Multimodal Digital Phenotype for Multi-Task LLM-based Mental Health Prediction](https://mlsanity.com/paper/2505.23822/) (2025)
- [User Factor Adaptation for User Embedding via Multitask Learning](https://mlsanity.com/paper/2102.11103/) (2021)
- [Multi-Task Learning for Depression Detection in Dialogs](https://mlsanity.com/paper/2208.10250/) (2022)
- [Improving Text-based Early Prediction by Distillation from Privileged Time-Series Text](https://mlsanity.com/paper/2301.10887/) (2023)
- [MAMA-Memeia! Multi-Aspect Multi-Agent Collaboration for Depressive Symptoms Identification in Memes](https://mlsanity.com/paper/2512.25015/) (2025)
- [We Are in This Together: Quantifying Community Subjective Wellbeing and Resilience](https://mlsanity.com/paper/2208.10766/) (2022)
- [Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction](https://mlsanity.com/paper/2509.12227/) (2025)
- [A Review: PTSD in Pre-Existing Medical Condition on Social Media](https://mlsanity.com/paper/2601.08836/) (2025)
- [FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data](https://mlsanity.com/paper/2605.18936/) (2026)

## Abstract (arXiv)

We introduce initial groundwork for estimating suicide risk and mental health in a deep learning framework. By modeling multiple conditions, the system learns to make predictions about suicide risk and mental health at a low false positive rate. Conditions are modeled as tasks in a multi-task learning (MTL) framework, with gender prediction as an additional auxiliary task. We demonstrate the effectiveness of multi-task learning by comparison to a well-tuned single-task baseline with the same number of parameters. Our best MTL model predicts potential suicide attempt, as well as the presence of atypical mental health, with AUC > 0.8. We also find additional large improvements using multi-task learning on mental health tasks with limited training data.