A Melancholy Spotting with Interdisciplinary AI using Multimode Framework

Abstract

Depression is a serious global health concern that, it may result in a loss of interest in everyday pursuits and suicidal thoughts. As a result, the necessity for a motorized system that assist in identifying melancholy in individuals across a range of age groups is becoming apparent. Experimenter have been searching as methods to accurately identify depression in order to detect it. Numerous investigations have been suggested in this context. In this work, we review a number of prior investigations that used AI and ML to identify misery. In addition, many methods for determining a person's mood and emotions are described. This study examines how emotions may be accurately detected and then depression can be indicated through facial expressions, photos, emotional chatbots, messages on social media sites and responses to the questions. This review article lists many machine learning techniques for identifying and diagnosing depression. The three classes of ML-based depression detection methods include classifications, deep learning, and ensemble. We outline an all-encompassing paradigm for diagnosing depression that comprises pre-processing, data extraction, ML classifier training, detection classification, and performance evaluation. Additionally, it provides a summary of the goals and restrictions of the various research papers that have been presented in the field of depression detection. Additionally, it covered potential directions for future research in the realm of diagnosing depression.