Deep Temporal Modelling of Clinical Depression through Social Media Text

TL;DR

This paper presents a temporal social media-based model for detecting clinical depression, utilizing clinician-annotated tweets and extracting features like depression scores and activity patterns to improve detection accuracy.

Contribution

It introduces a novel DSD classifier trained on clinician-annotated tweets and evaluates its effectiveness with multiple datasets and feature ablation tests.

Findings

Semantic models perform well in depression detection.

Clinical features improve performance with similar training and testing distributions.

Depression score predictions become more accurate with more user data.

Abstract

We describe the development of a model to detect user-level clinical depression based on a user's temporal social media posts. Our model uses a Depression Symptoms Detection (DSD) classifier, which is trained on the largest existing samples of clinician annotated tweets for clinical depression symptoms. We subsequently use our DSD model to extract clinically relevant features, e.g., depression scores and their consequent temporal patterns, as well as user posting activity patterns, e.g., quantifying their ``no activity'' or ``silence.'' Furthermore, to evaluate the efficacy of these extracted features, we create three kinds of datasets including a test dataset, from two existing well-known benchmark datasets for user-level depression detection. We then provide accuracy measures based on single features, baseline features and feature ablation tests, at several different levels of temporal granularity. The relevant data distributions and clinical depression detection related settings can be exploited to draw a complete picture of the impact of different features across our created datasets. Finally, we show that, in general, only semantic oriented representation models perform well. However, clinical features may enhance overall performance provided that the training and testing distribution is similar, and there is more data in a user's timeline. The consequence is that the predictive capability of depression scores increase significantly while used in a more sensitive clinical depression detection settings.