Publication: Depression Detection Based on Features of Depressive Behaviour Through Social Media Analytic: A Systematic Literature Review
Date
2023
Authors
Mat Ripah N.A.
Abdul Latif A.
Che Cob Z.
Mohd Drus S.
Md Anwar R.
Mohd Radzi H.
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Science and Business Media Deutschland GmbH
Abstract
People are becoming more conscious of the importance of mental health as time goes on. Thus, the detection of mental diseases is becoming a significant concern. Due to the multifaceted nature of each mental problem, many psychiatrists have had difficulty diagnosing mental illness in a patient, making it challenging to provide proper therapy before it is too late. However, because social media has become so ingrained in people's daily lives, it has created an environment where more information about a patient's mental illness is potentially available. This research was carried out as a Systematic Literature Review (SLR), a method of locating, evaluating, and interpreting publicly available materials to answer a set of research questions. The purpose of this study is to answer questions about text-based depression detection based on people who depressive behavior might have shown in their social media postings. The findings reveal that specific aspects of how these people use social media can help diagnose depression early on. This SLR discovered that the chosen social media data is basically the country's leading social site. However, some of the papers indirectly mentioned their challenges during the process. The main challenges highlighted are regarding the ethical issues of the data available. Furthermore, it is also shown that various machine learning algorithms are used, and the most used are Neural Network and Support Vector Machine. Similarly, the most common computing tool used is Phyton. The use of social media, as well as computational tools and machine learning algorithm, contributes to current public health efforts to detect any indicators of depression from sources close to patients. � 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Description
Keywords
Depression detection , Machine learning , Social media , Diseases , Learning algorithms , Learning systems , Patient treatment , Social networking (online) , Support vector machines , Depression detection , Machine learning algorithms , Machine-learning , Mental disease , Mental health , Mental illness , Mental problems , Social media , Social media analytics , Systematic literature review , Diagnosis