A Systematic Review on Application of Machine Learning Techniques for Depression Detection

Abstract

Depression is one of the leading causes of suicide worldwide and a complex clinical entity. Unfortunately, a huge percentage of depression patients goes undiagnosed and, therefore remains untreated. Therefore, it poses challenges for clinicians regarding both accurate diagnosis and effective timely treatment. Moreover, social networks have been developed as a great point for its users to communicate with their interested friends and share their opinions, photos, and videos reflecting their moods, feelings and sentiments. This creates an opportunity to analyze social network data for user’s feelings and sentiments to investigate their moods and attitudes when they are communicating via these online tools. Thus, depression analysis of a person can be done using the textual data collected from an online public source. Messages and posts posted by individuals with major depressive disorder on social media platforms can be analyzed to predict if they are suffering, or likely to suffer, from depression.  In this context, machine learning can turn out to be an efficient and scalable method to help improve the management of this disease. Thus, several text preprocessing and textual-based featuring methods along with machine learning classifiers can be used to propose a generalized approach for depression detection using social media texts. This article is a review paper that presents the state-of-the-art of machine learning techniques in the detection of depression.