A Review on Machine Learning and Deep Learning Models for Identifying Potential Depression on Social Media Text Datasets

Depression is a global mental health crisis, affecting over 300 million people worldwide, according to the World Health Organization (WHO). Despite its prevalence, depression often goes undiagnosed or is misdiagnosed due to social stigma, limited access to healthcare, and the subjective nature of traditional diagnostic methods. This highlights the urgent need for innovative and objective tools to identify depression early and accurately. Machine learning (ML), with its ability to process and analyze vast amounts of data, offers a promising solution to bridge this gap and transform depression detection methods. Since the data sets are often extremely large and complex, hence off late, opinion mining and sentiment analysis is executed based on artificial intelligence and machine learning models, rather than statistical rule based systems. This paper presents a systematic review of the existing methods for depression detection along with their salient contribution.