Predicting public mental health needs in a crisis using social media indicators: a Singapore big data study

Predicting public mental health needs in a crisis using social media indicators: a Singapore big data study

Scientific Reports

10.1038/s41598-024-73978-5

https://doi.org/10.1038/s41598-024-73978-5

Nur Atiqah Othman, Chitra Panchapakesan, Siyuan Brandon Loh, Mila Zhang, Raj Kumar Gupta, Wijaya Martanto, Ye Sheng Phang, Robert J. T. Morris, Wai Chiong Loke, Kelvin Bryan Tan, Mythily Subramaniam, Yinping Yang

Psychiatry and Mental health, • Computing methodologies → Machine learning, Public Health, health policy, health information systems

05 October 2024

Othman, N. A., Panchapakesan, C., Loh, S. B., Zhang, M., Gupta, R. K., Martanto, W., Phang, Y. S., Morris, R. J. T., Loke, W. C., Tan, K. B., Subramaniam, M., & Yang, Y. (2024). Predicting public mental health needs in a crisis using social media indicators: a Singapore big data study. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-73978-5

Mental health issues have increased substantially since the onset of the COVID-19 pandemic. However, health policymakers do not have adequate data and tools to predict mental health demand, especially amid a crisis. Using time-series data collected in Singapore, this study examines if and how algorithmically measured emotion indicators from Twitter posts can help forecast emergency mental health needs. We measured the mental health needs during 549 days from 1 July 2020 to 31 December 2021 using the public’s daily visits to the emergency room of the country’s largest psychiatric hospital and the number of users with “crisis” state assessed through a government-initiated online mental health self-help portal. Pairwise Granger-causality tests covering lag length from 1 day to 5 days indicated that forecast models using Twitter joy, anger and sadness emotions as predictors perform significantly better than baseline models using past mental health needs data alone (e.g., Joy Intensity on IMH Visits, χ2 = 14·9, P < ·001***; Sadness Count on Mindline Crisis, χ2 = 4·6, P = ·031*, with a one-day lag length). The findings highlight the potential of new early indicators for tracking emerging public mental health needs.

Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

This research is supported by core funding from: The A*STAR co-authors are supported by A*STAR IHPC Core Funding, under their contributions to the A*CRUSE taskforce's COVID-19 social media analytics project.
Grant Reference no. :

Rights and permissions Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

https://oar.a-star.edu.sg/communities-collections/articles/22094

2045-2322

Institute of High Performance Computing