Received: November 20, 2025 Accepted: January 3, 2026 Publication Date: March 5, 2026
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.
Accurately assessing the psychological impact of public health events is challenging because social media data contain substantial noise that obscures important temporal patterns and spatial distribution characteristics. To address this issue, this study proposes a social-media-driven spatiotemporal analysis framework that improves data quality, feature extraction, and predictive accuracy. Using user-generated content from the Sina Weibo platform, the method collects epidemic-related posts, including official fact-checking information and user interactions, and performs sentiment classification using a comprehensive emotional vocabulary corpus. To reduce noise and enhance topic extraction, an improved form of complete ensemble empirical mode decomposition with adaptive noise is combined with the curvelet transform, and the refined content is analyzed through latent Dirichlet allocation topic modeling and clustering to extract coherent topic features. Psychological indicators are identified using a hybrid deep learning model that integrates convolutional neural networks with long short-term memory neural networks, enabling simultaneous extraction of spatial features and modeling of temporal sequences. These indicators support a detailed examination of the psychological impact of public health events from both temporal and spatial perspectives, and bivariate spatial autocorrelation analysis is applied to reveal spatial relationships between psychological responses and epidemic-related factors. Experimental results demonstrate that this method effectively identifies regional differences in psychological impact, captures evolving psychological trends across stages of the epidemic, and maintains strong robustness under varying clustering conditions, offering a precise and dynamic solution for analyzing public psychological responses during public health emergencies.
Keywords: social media driven by big data, Public health events, CNN-LSTM, Psychological indicators, Spatio-temporal modeling
[1] R. Mousavi and B. Gu. Resilience messaging: The effect of governors’ social media communications on community compliance during a public health crisis. 2024. DOI: https: //doi.org/10.1287/isre.2021.0599.
[2] S. MuhammedTandS.K.Mathew,(2022) “The disaster of misinformation: a review of research in social media" International journal of data science and analytics 13(4): 271–285. DOI: https: //doi.org/10.1007/s41060-022-00311-6.
[3] N. Salari, H. Zarei, A. Hosseinian-Far, S. Rasoulpoor, S. Shohaimi, and M. Mohammadi, (2025) “The global prevalence of social media addiction among university students: a systematic review and meta-analysis" Journal of Public Health 33(1): 223–236. DOI: https: //doi.org/10.1007/s10389-023-02012-1.
[4] F. Chirico, (2024) “Navigating global challenges in the workplace: Innovative strategies for combating burnout, preventing workplace violence, and enhancing psychosocial well-being" Adv Med Psychol Public Health 1(3): 108–109. DOI: https: //doi.org/10.5281/ZENODO.10897920.
[5] O. Iparraguirre-Villanueva, A. Alvarez-Risco, J. L. Herrera Salazar, S. Beltozar-Clemente, J. Zapata Paulini, J. A. Yáñez, and M. Cabanillas-Carbonell, (2023) “The public health contribution of sentiment analysis of Monkeypox tweets to detect polarities using the CNN-LSTM model" Vaccines 11(2): 312. DOI: https: //doi.org/10.3390/vaccines11020312.
[6] J. H. Joloudari, S. Hussain, M. A. Nematollahi, R. Bagheri, F. Fazl, R. Alizadehsani, R. Lashgari, and A. Talukder, (2023) “BERT-deep CNN: State of the art for sentiment analysis of COVID-19 tweets" Social Net work Analysis and Mining 13(1): 99. DOI: https: //doi.org/10.1007/s13278-023-01102-y.
[7] Z. Zeng, S. Sun, and Q. Li, (2023) “Multimodal negative sentiment recognition of online public opinion on public health emergencies based on graph convolutional networks and ensemble learning" Information Processing &Management60(4): 103378. DOI: https: //doi.org/10.1016/j.ipm.2023.103378.
[8] J. Samuolis, (2024) “Psychological distress and identity distress related to the COVID-19 pandemic among college students" Journal of Adult Development 31(2): 145 155. DOI: https: //doi.org/10.1007/s10804-023-09456-5.
[9] P. Cui, M. Yang, H. Hu, C. Cheng, X. Chen, J. Shi, S. Li, C. Chen, and H. Zhang, (2024) “The impact of caregiver burden on quality of life in family caregivers of patients with advanced cancer: a moderated mediation analysis of the role of psychological distress and family resilience" BMC Public Health 24(1): 817. DOI: https: //doi.org/10.1186/s12889-024-18321-3.
[10] J. An, X. Zhu, Z. Shi, and J. An, (2024) “A serial mediating effect of perceived family support on psychological well-being" BMC Public Health 24(1): 940. DOI: https: //doi.org/10.1186/s12889-024-18476-z.
[11] S. Nagi, S. Kempe, S. Barriault, L. Masri, S. Dyyat, C. Muhl, S. Bennett, and N. Racine, (2025) “Into the wild: a mixed-methods pilot study of the mental health benefits of a nature summer camp for urban children with psychological needs" BMC Public Health 25(1): 1–12. DOI: https: //doi.org/10.1186/s12889-025-21847-9.
[12] J. Chen, Y. Wang, et al., (2021) “Social media use for health purposes: systematic review" Journal of medical Internet research 23(5): e17917. DOI: https: //doi.org/10.2196/17917.
[13] A. Ø.Geirdal, M. Ruffolo, J. Leung, H. Thygesen, D. Price, T. Bonsaksen, and M. Schoultz, (2021) “Mental health, quality of life, wellbeing, loneliness and use of social media in a time of social distancing during the COVID-19outbreak. A cross-country comparative study" Journal of Mental Health 30(2): 148–155. DOI: https: //doi.org/10.1080/09638237.2021.1875413.
[14] M. A. Gisondi, R. Barber, J. S. Faust, A. Raja, M. C. Strehlow, L. M. Westafer, and M. Gottlieb. A deadly infodemic: social media and the power of COVID-19 misinformation. 2022. DOI: https: //doi.org/10.2196/35552.
[15] D. Farsi, (2021) “Social media and health care, part I: literature review of social media use by health care providers" Journal of medical internet research 23(4): e23205. DOI: https: //doi.org/10.2196/23205.
[16] C. Melchior and M. Oliveira, (2024) “A systematic literature review of the motivations to share fake news on social media platforms and how to fight them" New Media &Society 26(2): 1127–1150. DOI: https: //doi.org/10.1177/14614448231174224.
[17] S.-F. Tsao, H. Chen, T. Tisseverasinghe, Y. Yang, L. Li, and Z. A. Butt, (2021) “What social media told us in the time of COVID-19: a scoping review" The Lancet Digital Health 3(3): e175–e194. DOI: https: //doi.org/10.1016/S2589-7500(20)30315-0.
[18] V. Suarez-Lledo and J. Alvarez-Galvez, (2021) “Prevalence of health misinformation on social media: systematic review" Journal of medical Internet research 23(1): e17187. DOI: https: //doi.org/10.2196/17187.
[19] Y. Yan, A. Mahmood, and Q. Z. Sheng. Protecting Location Privacy in the Era of Big Data: A Technical Perspective. CRC Press, 2024. DOI: https: //doi.org/10.1201/9781003546344.
[20] Y. Liu, (2025) “Analyzing Evolution and Key Themes in Food Policy: A Latent Dirichlet Allocation (LDA) Approach" Journal of food safety 45(1): e70009. DOI: https: //doi.org/10.1111/jfs.70009.
[21] T. Park, (2024) “COVID-19 Research Trends in Social Work: LDA Topic Modeling Analysis in South Korea" Journal of Social Service Research 50(4): 609–619. DOI: https: //doi.org/10.1080/01488376.2024.2354528.
[22] M. S. Martín, F.-W. Chen, and P. A. Urbistondo, (2025) “Application of the LDA model to identify topics in telemedicine conversations on the X social network" BMCHealthServicesResearch25(1):1–9. DOI: https: //doi.org/10.1186/s12913-025-12493-3.
[23] X. Chen, M. Zhang, Q. Bu, B. Tan, P. Peng, Y. Zhou, Y. Tang, X. Tian, and D. Deng, (2024) “Exploring hot topics and evolutionary paths in the Diagnosis-Related Groups (DRGs) field: a comparative study using LDA modeling" BMC Health Services Research 24(1): 756. DOI: https: //doi.org/10.1186/s12913-024-11209-3.
[24] Y. Wang and Y. Chen,(2023)“Characterizing discourses about COVID-19 vaccines on Twitter: a topic modeling and sentiment analysis approach" Journal of communication in healthcare 16(1): 103–112. DOI: https: //doi.org/10.1080/17538068.2022.2054196.
[25] S. Sun, T. Zack, C. Y. Williams, M. Sushil, and A. J. Butte, (2024) “Topic modeling on clinical social work notes for exploring social determinants of health factors" JAMIAopen7(1): ooad112. DOI: https: //doi.org/10.1093/jamiaopen/ooad112.
We use cookies on this website to personalize content to improve your user experience and analyze our traffic. By using this site you agree to its use of cookies.
