Accepted for/Published in: JMIR Mental Health
Date Submitted: Jan 18, 2021
Date Accepted: Dec 16, 2021
Detecting and Measuring Depression on Social Media by Machine Learning Approach: A Systematic Review
ABSTRACT
Background:
Detection of depression gained prominence soon after this troublesome disease emerged as a serious public health concern worldwide.
Objective:
The aim of this review intends to summarize methods to measure depressive symptoms on social media by machine learning approaches.
Methods:
A bibliographic retrieval was conducted from January 1990 until December 2020 in Google Scholar, PubMed, Medline, ERIC, PsycINFO, and BioMed. Seventeen studies met the inclusion criteria.
Results:
Of the fifteen studies, ten defined depression based on self-reported mental status, five defined based on self-declared mental status, and the last two were based on community membership. Besides, among the fifteen studies, thirteen conducted depression detection with Supervised Learning (SL) approaches, three used Unsupervised Learning (UL) approaches to detect depression, while the remaining one did not report the ML approach. Challenges such as sample scale, optimizing of predicting approaches and features, generalizability, issues about privacy, and ethic are still open to research.
Conclusions:
ML approaches might work effectively for depression detection using text data from users on social media and it could serve as a complementary tool in practice about public psychological health.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.