Authors - U Ananthanagu, Pooja Agarwal Abstract - In recent couple of years, social media platform has attained a tremendous growth in sharing information and become an integral part of everyday life. Such real time information portrays one’s daily activities by exposing their private space, behaviour aspects and emotions. With the wide range of availability of personal information on social media, it plays a prominent role on the process of individual’s mental illness detection. Although, in the last few decades mental illness rates create more attention and also many cases are not recognized as now. Indications related to the mental illness are visible on web forums, Facebook and Twitter henceforth computerized techniques are in demand in earlier detection of mental illnesses and depression. In this case, automated analysis of mental illness detection on social media may provide early accurate detection process. Studies have so far explored how the use of social networking sites is linked to mental illness in users or attempts to diagnose mental illness by analysing user-generated content. The review focuses on the confines of machine learning and deep learning techniques on the diagnosis of mental illness of the publications regulated from 2017 to 2021. Amidst current depression detection algorithm, we spotlight various transfer learning categories and scrutinize the issues. Finally, the presented work providing the research guidelines to the upcoming research works for the detection of mental illness based on transfer learning deep learning. The main motive of the manuscript focuses on future prospects of transfer leering based mental illness detection on digital media stream.
Open Zoom