Can We Assess Mental Health through Social Media and Smart Devices? Addressing Bias in Methodology and Evaluation

TL;DR

This paper critically evaluates current methods for assessing mental health via social media and smart devices, revealing that they underperform in real-world settings and highlighting the need for more robust evaluation frameworks.

Contribution

It provides a comprehensive analysis of state-of-the-art approaches, exposing their limitations in real-world generalization and proposing more pragmatic evaluation strategies.

Findings

Current methods barely outperform naive baselines in real-world scenarios.

Most approaches do not meet reported performance levels under pragmatic evaluation.

Feature contributions to mental health prediction are questionable in real-world settings.

Abstract

Predicting mental health from smartphone and social media data on a longitudinal basis has recently attracted great interest, with very promising results being reported across many studies. Such approaches have the potential to revolutionise mental health assessment, if their development and evaluation follows a real world deployment setting. In this work we take a closer look at state-of-the-art approaches, using different mental health datasets and indicators, different feature sources and multiple simulations, in order to assess their ability to generalise. We demonstrate that under a pragmatic evaluation framework, none of the approaches deliver or even approach the reported performances. In fact, we show that current state-of-the-art approaches can barely outperform the most na\"ive baselines in the real-world setting, posing serious questions not only about their deployment ability, but also about the contribution of the derived features for the mental health assessment task and how to make better use of such data in the future.