Deep Learning-Based Frameworks for Automated Identifying Depression Through Social Media

Abstract

The data generated by users on Twitter is precious for healthcare technology as it can reveal important patterns that can greatly benefit the field in multiple ways. Notably, most of the recent depression detection models are limited to detecting a large number of posts. The objective of this study is to integrate user posts and behavior to create a broad spectrum of behavioral, and semantic representations of users. This will enable the automatic selection of the most significant user-generated information and the development of an explainable deep-learning architecture to identify depression. Furthermore, this study aims to create new tasks that model user narratives in social media.