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

## TL;DR

This paper introduces SS3, a new supervised learning framework for early depression detection on social media streams that is efficient, supports incremental learning, and provides explanations for its decisions.

## Contribution

The paper presents SS3, a novel, explainable, and computationally efficient supervised learning model specifically designed for early risk detection tasks on social media.

## Key findings

- SS3 outperformed state-of-the-art models in early depression detection.
- SS3 is less computationally expensive than existing methods.
- SS3 provides explanations for its classification decisions.

## Abstract

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.