Estimating Individuals’ Suffering Levels Induced by Disasters via Social Media: A Case Study of the 2023 Beijing–Tianjin–Hebei Extreme Rainfall

Abstract

Extreme hazard events can severely threaten the well-being of society. To understand their impacts on the well-being of people, social scientists have proposed various indicators related to individuals’ suffering, and analyzed them mainly via post-disaster surveys. Social media has shown its value in capturing people’s perceptions of disasters, but few scholars have investigated individuals’ suffering levels based on social media data. Accordingly, this study used social media data and developed a hybrid model that combines machine learning classifiers and lexicon-based approaches to estimate the well-being impacts of disasters, which are measured by individuals’ physical, emotional, and social suffering levels. Six machine learning models were trained to categorize the suffering as reflected by disaster-related posts on Weibo. Convolutional neural networks (CNN) were found to be the most accurate model, and was selected to classify all posts into four groups (no suffering, physical suffering, emotional suffering, and social suffering). In each classified group of posts, word co-occurrence analysis was then applied to construct suffering lexicons. By combining the classification results from CNN and suffering lexicons, this study proposed optimization-based algorithms to estimate suffering levels for posts across space and time. The proposed model was applied to the 2023 Beijing-Tianjin-Hebei extreme rainfall event. The temporal analysis revealed that individuals’ physical suffering levels declined more rapidly than mental and social suffering levels. Spatial analysis revealed that individuals’ suffering presented high spatial heterogeneity, and that the hazard-affected regions experienced significantly greater levels of suffering. This hybrid model provides an analytical tool for timely and human-centered disaster emergency management.

Keywords

Beijing–Tianjin–Hebei extreme rainfall / Disasters / Social media / Suffering level / Well-being impact

References

[1] Anderson RE. Human suffering and quality of life: Conceptualizing stories and statistics, 2013, Dordrecht. Springer

[2] Anguita, D., L. Ghelardoni, A. Ghio, L. Oneto, and S. Ridella. 2012. The “K” in K-fold cross validation. In Proceedings of European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 25–27 Bruges, Belgium, 441–446.

[3] Bazarova NN, Choi YH. Self-disclosure in social media: Extending the functional approach to disclosure motivations and characteristics on social network sites. Journal of Communication, 2014, 64(4): 635-657.

[4] Beigi G, Hu X, Maciejewski R, Liu HKacprzyk J. An overview of sentiment analysis in social media and its applications in disaster relief. Studies in computational intelligence, 2016, Berlin. Springer313-340

[5] Birjali, M., M. Kasri, and A. Beni-Hssane. 2021. A comprehensive survey on sentiment analysis: Approaches, challenges and trends. Knowledge-Based Systems 226: Article 107134.

[6] Brady WJ, Wills JA, Jost JT, Tucker JA, Van Bavel JJ. Emotion shapes the diffusion of moralized content in social networks. Proceedings of the National Academy of Sciences, 2017, 114(28): 7313-7318.

[7] Brynielsson J, Granåsen M, Lindquist S, Narganes Quijano M, Nilsson S, Trnka J. Informing crisis alerts using social media: Best practices and proof of concept. Journal of Contingencies and Crisis Management, 2018, 26(1): 28-40.

[8] Chandra, R., and A. Krishna. 2021. COVID-19 sentiment analysis via deep learning during the rise of novel cases. PLOS ONE 16(8): Article e0255615.

[9] Dai, J., Y. Zhao, and Z. Li. 2024. Sentiment-topic dynamic collaborative analysis-based public opinion mapping in aviation disaster management: A case study of the MU5735 air crash. International Journal of Disaster Risk Reduction 102: Article 104268.

[10] Dalian University of Technology. Chinese stopwords list [EB/OL], 2024, Dalian, China. Dalian University of Technology

[11] Demirci, G.M., S.R. Keskin, and G. Dogan. 2019. Sentiment analysis in Turkish with deep learning. In Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), 9–12 December 2019, Los Angeles, CA, USA, 2215–2221.

[12] Gardoni P, Murphy C. Gauging the societal impacts of natural disasters using a capability approach. Disasters, 2010, 34(3): 619-636.

[13] Han H, Zhang J, Yang J, Shen Y, Zhang Y. Generate domain-specific sentiment lexicon for review sentiment analysis. Multimedia Tools and Applications, 2018, 77(16): 21265-21280.

[14] Jamil, M.L., S. Pais, and J. Cordeiro. 2022. Detection of dangerous events on social media: A critical review. Social Network Analysis and Mining 12(1): Article 154.

[15] Karami A, Shah V, Vaezi R, Bansal A. Twitter speaks: A case of national disaster situational awareness. Journal of Information Science, 2020, 46(3): 313-324.

[16] Kim, Y., J. Huang, and S. Emery. 2016. Garbage in, garbage out: Data collection, quality assessment and reporting standards for social media data use in health research, infodemiology and digital disease detection. Journal of Medical Internet Research 18(2): Article e41.

[17] Luo T, Li R, Sun Z, Tao F, Kumar M, Li CSun X, Zhang X, Xia Z, Bertino E. Let the big data speak: Collaborative model of topic extract and sentiment analysis COVID-19 based on Weibo data. Artificial intelligence and security, 2022, Cham. Springer264-275.

[18] Mahajani, S.J., S. Srivastava, and A.F. Smeaton. 2023. A comparison of lexicon-based and ML-based sentiment analysis: Are there outlier words? In Proceedings of the 2023 31st Irish Conference on Artificial Intelligence and Cognitive Science (AICS), 7–8 December 2023, Letterkenny, Ireland, 1–4.

[19] Murphy C, Gardoni P. The role of society in engineering risk analysis: A capabilities-based approach. Risk Analysis, 2006, 26(4): 1073-1083.

[20] Neppalli VK, Caragea C, Squicciarini A, Tapia A, Stehle S. Sentiment analysis during Hurricane Sandy in emergency response. International Journal of Disaster Risk Reduction, 2017, 21: 213-222.

[21] Norris, F.H., M.J. Friedman, P.J. Watson, C.M. Byrne, E. Diaz, and K. Kaniasty. 2002. 60,000 disaster victims speak: Part I. An empirical review of the empirical literature, 1981–2001. Psychiatry: Interpersonal and Biological Processes 65(3): 207–239.

[22] Podesta, C., N. Coleman, A. Esmalian, F. Yuan, and A. Mostafavi. 2021. Quantifying community resilience based on fluctuations in visits to points-of-interest derived from digital trace data. Journal of the Royal Society Interface 18(177): Article 20210158.

[23] Robeyns I. The capability approach: A theoretical survey. Journal of Human Development, 2005, 6(1): 93-117.

[24] Turney, P.D. 2001. Thumbs up or thumbs down? In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics – ACL ’02, 7–12 July 2002, Philadelphia, PA, USA.

[25] Valinejad J, Guo Z, Cho JH, Chen IR. Social media-based social-psychological community resilience analysis of five countries on COVID-19. Journal of Computational Social Science, 2023, 6(2): 1001-1032.

[26] Wang, W., J.W. van De Lindt, N. Rosenheim, H. Cutler, B. Hartman, J. Sung Lee, and D. Calderon. 2021. Effect of residential building wind retrofits on social and economic community-level resilience metrics. Journal of Infrastructure Systems 27(4): Article 04021034.

[27] Wang, C., X. Zhang, and J. Wu. 2024. Disaster information mining from a social perception perspective: A case study of 2023 extreme rainfall in the Beijing-Tianjin-Hebei Region. International Journal of Disaster Risk Reduction 115: Article 105056.

[28] Wiseman J, Brasher K. Community wellbeing in an unwell world: Trends, challenges, and possibilities. Journal of Public Health Policy, 2008, 29(3): 353-366.

[29] Yang, Y., H. Liu, A. Mostafavi, and H. Tatano. 2025. Review on modeling the societal impact of infrastructure disruptions due to disasters. Reliability Engineering & System Safety 257: Article 110879.

[30] Yang, Y., H. Liu, S. Zhong, K. Liu, M. Wang, and Q. Huang. 2023. Agent-based societal impact modeling for infrastructure disruption and countermeasures analyses. Sustainable Cities and Society 97: Article 104737.

[31] Yang, Y., H. Tatano, Q. Huang, H. Liu, G. Yoshizawa, and K. Wang. 2021. Evaluating the societal impact of disaster-driven infrastructure disruptions: A water analysis perspective. International Journal of Disaster Risk Reduction 52: Article 101988.

[32] Zhang, L., S. Wang, and B. Liu. 2018. Deep learning for sentiment analysis: A survey. WIREs Data Mining and Knowledge Discovery 8(4): Article e1253.

[33] Zhang C, Yao W, Yang Y, Huang R, Mostafavi A. Semiautomated social media analytics for sensing societal impacts due to community disruptions during disasters. Computer-Aided Civil and Infrastructure Engineering, 2020, 35(12): 1331-1348.

[34] Zhao, D., H. Xu, Y. Li, Y. Yu, Y. Duan, X. Xu, and L. Chen. 2024. Locally opposite responses of the 2023 Beijing–Tianjin–Hebei extreme rainfall event to global anthropogenic warming. Npj Climate and Atmospheric Science 7(1): Article 38.

RIGHTS & PERMISSIONS

The Author(s)