# A Text Classification Framework for Simple and Effective Early Depression Detection Over Social Media Streams

arXiv: https://arxiv.org/abs/1905.08772 · HTML: https://mlsanity.com/paper/1905.08772/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2019.

## Built on by (most cited first, 18 of 18)

- [Text2TimeSeries: Enhancing Financial Forecasting through Time Series Prediction Updates with Event-Driven Insights from Large Language Models](https://mlsanity.com/paper/2407.03689/) (2024)
- [Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews](https://mlsanity.com/paper/2307.00920/) (2023)
- [Exploring Social Media for Early Detection of Depression in COVID-19 Patients](https://mlsanity.com/paper/2302.12044/) (2023)
- [Early Detection of Depression and Eating Disorders in Spanish: UNSL at MentalRiskES 2023](https://mlsanity.com/paper/2310.20003/) (2023)
- [We Care: Multimodal Depression Detection and Knowledge Infused Mental Health Therapeutic Response Generation](https://mlsanity.com/paper/2406.10561/) (2024)
- [Strategies to Harness the Transformers' Potential: UNSL at eRisk 2023](https://mlsanity.com/paper/2310.19970/) (2023)
- [Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.01315/) (2025)
- [Quantifying the Suicidal Tendency on Social Media: A Survey](https://mlsanity.com/paper/2110.03663/) (2021)
- [Sentiment Informed Sentence BERT-Ensemble Algorithm for Depression Detection](https://mlsanity.com/paper/2409.13713/) (2024)
- [Mental Disorders on Online Social Media Through the Lens of Language and Behaviour: Analysis and Visualisation](https://mlsanity.com/paper/2202.03291/) (2022)
- [Life is not Always Depressing: Exploring the Happy Moments of People Diagnosed with Depression](https://mlsanity.com/paper/2204.13569/) (2022)
- [A Time-Aware Approach to Early Detection of Anorexia: UNSL at eRisk 2024](https://mlsanity.com/paper/2410.17963/) (2024)
- [Social Behavior and Mental Health: A Snapshot Survey under COVID-19 Pandemic](https://mlsanity.com/paper/2105.08165/) (2021)
- [Hybrid Representation Learning for Cognitive Diagnosis in Late-Life Depression Over 5 Years with Structural MRI](https://mlsanity.com/paper/2212.12810/) (2022)
- [Early Detection of Mental Health Issues Using Social Media Posts](https://mlsanity.com/paper/2503.07653/) (2025)
- [Explainable Depression Detection using Masked Hard Instance Mining](https://mlsanity.com/paper/2505.24609/) (2025)
- [Tackling a Challenging Corpus for Early Detection of Gambling Disorder: UNSL at MentalRiskES 2025](https://mlsanity.com/paper/2511.23325/) (2025)
- [Self-Stigma Is Not a Monolith, but Generic Empathy Is: Persona-Conditioned LLM Support for People Who Use Drugs](https://mlsanity.com/paper/2606.23387/) (2026)

## Abstract (arXiv)

With the rise of the Internet, there is a growing need to build intelligent systems that are capable of efficiently dealing with early risk detection (ERD) problems on social media, such as early depression detection, early rumor detection or identification of sexual predators. These systems, nowadays mostly based on machine learning techniques, must be able to deal with data streams since users provide their data over time. In addition, these systems must be able to decide when the processed data is sufficient to actually classify users. Moreover, since ERD tasks involve risky decisions by which people's lives could be affected, such systems must also be able to justify their decisions. However, most standard and state-of-the-art supervised machine learning models are not well suited to deal with this scenario. This is due to the fact that they either act as black boxes or do not support incremental classification/learning. In this paper we introduce SS3, a novel supervised learning model for text classification that naturally supports these aspects. SS3 was designed to be used as a general framework to deal with ERD problems. We evaluated our model on the CLEF's eRisk2017 pilot task on early depression detection. Most of the 30 contributions submitted to this competition used state-of-the-art methods. Experimental results show that our classifier was able to outperform these models and standard classifiers, despite being less computationally expensive and having the ability to explain its rationale.