Tamil Elakya, T (2024) A Comprehensive Review on Artificial Intelligence based Depression Detection through Social Media Data Analysis. A Comprehensive Review on Artificial Intelligence based Depression Detection through Social Media Data Analysis, 15 (84). pp. 1-9. ISSN 0976 – 0997

[thumbnail of Survey Article - Published Copy_Elakya.pdf] Text
Survey Article - Published Copy_Elakya.pdf - Published Version
Download (446kB)

Abstract

Depression is a range of psychological conditions that affect attitude, feelings, and overall well-being,
and is influenced by various factors. Common symptoms include negative emotions, loss of interest, and
persistent sadness. Maintaining a high quality of life is important for managing mental health issues.
Social media plays a significant role in allowing individuals to express their emotions and share life
events. As mental health challenges continue to increase, there is growing interest in using social network
data for early detection of depression. Recent years have seen progress in using Artificial Intelligence (AI)
to identify depression on online platforms. This manuscript surveys AI frameworks, such as Machine
Learning (ML) and Deep Learning (DL) algorithms, utilized in studies of depression detection from 2020
to 2023. The paper not only presents advancements but also examines the limitations and challenges of
these algorithms, such as data heterogeneity, noise, and the subjective nature of mental health
expressions online. It aims to identify research gaps and suggest future directions for improving
methodologies on online platforms. This exploration contributes to the ongoing discussion about mental
health and AI, with implications for researchers, practitioners, and policymakers.

Item Type: Article
Uncontrolled Keywords: : Depression detection, Social media, AI, Machine learning, Deep learning
Divisions: PSG College of Arts and Science > Department of Computer Science
Depositing User: Mr Team Mosys
Date Deposited: 05 Oct 2024 06:27
Last Modified: 05 Oct 2024 06:27
URI: https://ir.psgcas.ac.in/id/eprint/2311

Actions (login required)

View Item
View Item