Societal Transformation: AI and Big Data Journal

Social Media Data for Mental Health Screening: Perspectives on Age Bias

Research Article 10
- Volume 3, Issue 2 2025
By Hamdah Hamid
DOI:10.20547/aibd.253202
Keywords: Age Bias; Mental health; Social Media; Data Bias; Demographic Analysis

Abstract: During the past few years, there have been a surge in the use of social media. Various social media platforms have emerged such as Twitter, WhatsApp, Facebook and LinkedIn. The existing studies reveal that there has been a relation between social media usage and mental health. The objective of this study is to explore age biasness related to mental health data on social media platforms. Some studies have already been done on analysis of the effect of social media platforms on mental health. However, it has been observed that there is an issue of lack of inclusiveness towards the usage of social media platforms by older people. In other words, people of all age groups have not been using social media platforms. Hence, it is very hard to devise any conclusive statements based on these studies. This research is aimed towards the study of the lack of inclusiveness and biasedness prevalent on usage of existing social media platforms by diverse people. The paper highlights that the existing studies that have been done on the impact of social media usage on mental health has inherent biasedness issues. To perform the study, the paper employed an online dataset (Zeybus 2024). By means of interactive data visualizations, correlation analysis and discussions, the hypothesis has been substantiated. It was therefore observed that an inherent biasedness exists in social media data usage. This is due to an imbalance in the participation of people of different sects, races, genders and age groups. The paper has been structured as follows. First, the analysis has been done based on demographics. Using various questions, we determine what are the usage patterns of social media by these prospective users. In the end, the indicators of mental health of respondents were analyzed. A data pipeline was used, comprising preprocessing, descriptive analysis and exploratory data analysis (EDA). The paper concludes by showing that social media–based mental health data is heavily skewed toward younger users and certain demographic groups, limiting its reliability for broader population-level mental health assessments.

Submission Date: 4 Jul, 2025 Reviews Completed: 23 Oct, 2025
Acceptance Date: 10 Dec, 2025 Publication Date: 31 Jan, 2026

Share this paper


Want to publish in ?
Send us your paper for review
Curl Error: Peer reports incompatible or unsupported protocol version.
0
Authors
25
Research Papers
0
Citations