All Issue

2026 Vol.22, Issue 1 Preview Page

Original Article

31 March 2026. pp. 223-237
Abstract
Purpose: This study aims to systematically classify social risks associated with cold waves using news big data and to analyze how media coverage of cold wave risks has changed over time. Method: A four-stage refinement process was designed using the BERT based model and a Large Language Model (GPT-4o-mini) on approximately 100 million Naver news articles collected from 2010 to 2025. After removing simple weather forecasts and figurative expressions, 1,973 news articles specifically related to cold waves were finalized. From these, 2,829 risk-related sentences were extracted and analyzed according to a classification system of five major and twenty-four subcategories established based on WHO standards. Result: The classification of cold wave risk factors revealed that the number of new articles related to vulnerable groups (42.0%) and vulnerable facilities (33.2%) accounted for the highest proportions, indicating that news media perceives cold waves as disasters with a disproportionately large impact on the socially disadvantaged. While reports in the 2010s focused on physical damage such as infrastructure failure, the 2020s saw a shift toward highlighting complex disasters associated with COVID-19 and issues regarding the protection of vulnerable populations. Conclusion: The study confirms that cold waves are recognized as complex risks where damage is concentrated on vulnerable groups and facilities, especially under special circumstances like pandemic-driven complex disasters. Considering that cold wave damage is concentrated on specific classes, it is necessary to establish “user-centered” policies that reflect the needs and situations of vulnerable groups, alongside a cold wave response system from a complex disaster perspective.
연구목적: 본 연구는 뉴스 빅데이터를 활용해 한파로 인한 사회적 피해와 위험요소를 체계적으로 분류하는 것을 목표로 한다. 또한 한파 위험이 시대별로 어떻게 보도되는지 분석하고자 한다. 연구방법: 2010년부터 2025년까지 수집된 약 1억 건의 네이버 뉴스를 대상으로 BERT 기반 모델과 거대언어모델(GPT-4o-mini)을 활용한 4단계 정제 프로세스를 설계하였다. 단순 날씨 예보와 비유적 표현을 제거하여 최종 1,973건의 한파 관련 뉴스를 확정하고, 최종 선별된 뉴스에서 2,829개의 위험 문장을 추출하여 WHO 기준을 바탕으로 구축한 5개 대분류와 24개 세분류 체계에 따라 위험요소를 분류·분석하였다. 연구결과: 한파 위험요소 분류 결과 취약계층(42.0%), 취약시설(33.2%) 관련 보도가 가장 높은 비중을 차지하여, 뉴스에서는 한파가 사회적 약자에게 상대적으로 큰 영향을 미치는 재난으로 다루어지고 있다. 시대별로는 2010년대에 인프라 손상 등 물리적 피해에 집중되었으나, 2020년대에는 코로나19와 결합된 복합재난 및 취약계층 보호 이슈가 부각되었다. 결론: 한파는 단순한 기상 현상을 넘어 취약계층과 취약시설에 피해가 집중되는 복합적 위험으로 인식되고 있으며, 감염병 등 복합재난 상황에서의 특수성 또한 부각되고 있는 것으로 확인되었다. 이에 한파 피해가 특정 계층에 집중되는 특성을 고려하여, 취약계층의 수요와 상황을 반영한 ‘수요자 중심’의 정책과 복합재난 관점에서의 한파 대응 체계 마련이 필요하다.
References
  1. Bae, J.Y., Yoo, J.h., Yun, G.J. (2024). Policy Directions and Initiatives for Person and Consumer Centered Healthcare. Korea Institute for Health and Social Affairs, Sejong, Korea.
  2. Busby, J.W., Baker, K., Bazilian, M.D., Gilbert, A.Q., Grubert, E., Rai, V., Rhodes, J.D., Shidore, S., Smith, C.A., Webber, M.E. (2021). “Cascading risks: Understanding the 2021 winter blackout in Texas.” Energy Research & Social Science, Vol.77, No.102106, pp.1-15. 10.1016/j.erss.2021.102106
  3. Chae, Y.R., Lee, S.J., Jeon, H.C., Seo, S.B., Park, J.C., Choi, Y.W., Kim, D.S., Choi, S.H., Ko, M.S., Lee, J.Y., Lim, S.H., Kim, Y.W. (2019). Construction and Evaluation of Climate Change Adaptation Capacity for National Risk Management: Data-based Analysis of Direct and Indirect Effects of Heatwaves and Cold Waves. Korea Environment Institute, RE2019-14, Sejong, Korea.
  4. Cheung, H.N., Zhou, W., Mok, H.Y., Wu, M.C. (2012). “Relationship between Ural-Siberian blocking and the East Asian winter monsoon in relation to the Arctic Oscillation and the El Nino-Southern Oscillation.” Journal of Climate, Vol. 25, No. 12, pp. 4242-4257. 10.1175/JCLI-D-11-00225.1
  5. Cohen, J., Jones, J., Furtado, J.C., Tziperman, E. (2013). “Warm arctic, cold continents: A common pattern related to Arctic sea ice melt, snow advance, and extreme winter weather.” Oceanography, Vol. 26, No. 4, pp. 150-160. 10.5670/oceanog.2013.70
  6. Devlin, J., Chang, M.-W., Lee, K., Toutanova, K. (2019). “BERT: Pre-training of deep bidirectional transformers for language understanding.” Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), Minneapolis, US, pp. 4171-4186. 10.18653/v1/N19-1423
  7. Hankook Ilbo (2025). 76% of Elderly and Disabled Unable to Use Energy Vouchers: Barriers Still High. (Accessed Aug. 18, 2025).
  8. Heo, Y., Lee, J., Kim, J., Park, K. (2021). “KoELECTRA: Pre-training a large-scale Korean language representation generator with replaced token detection.” arXiv preprint, arXiv:2104.06940.
  9. Korea Press Foundation (2014). 2014 Media Audience in Korea. Seoul, Korea.
  10. Lee, H.J., Byun, Y.K., Jang, S.J., Choi, S.J., Oh, S.H., Lee, Y.T. (2019). “A big data analysis of the news trends on wireless emergency alert Service.” Journal of Broadcast Engineering, Vol. 24, No. 5, pp. 726-734. 10.5909/JBE.2019.24.5.726
  11. Ministry of the Interior and Safety (2018). Partial Amendment of the Framework Act on the Management of Disasters and Safety (Act No. 15764). Seoul, Korea.
  12. Ministry of the Interior and Safety (2025). 2025-2026 Winter Season Comprehensive Countermeasures for Heavy Snow and Cold Waves, Sejong, Korea.
  13. National Disaster and Safety Research Institute (2025). Development of Disaster Safety Management Knowledge Base and Utilizing Manuals. National Disaster and Safety Research Institute, Ulsan, Korea.
  14. News1 (2020). Last Winter Was the Warmest Since 1973 Observations Began: Least Amount of Snow. (Accessed Mar. 4, 2020).
  15. OpenAI (2024). GPT-4o mini: Advancing cost-efficient intelligence. (Accessed July 18, 2024).
  16. Overland, J.E., Dethloff, K., Francis, J.A., Hall, R.J., Hanna, E., Kim, S.J., Screen, J.A., Shepherd, T.G., Vihma, T. (2016). “Nonlinear response of mid-latitude weather to the changing Arctic.” Nature Climate Change, Vol. 6, No. 11, pp. 992-999. 10.1038/nclimate3121
  17. Park, J.C., Han, K.J., Chae, Y.R. (2019). “Correlation Analysis between Livestock Mortality Caused by Heat Wave and News Big Data.” Journal of the Association of Korean Geographers, Vol. 8, No. 3, pp. 529-543. 10.25202/JAKG.8.3.13
  18. Park, T.W., Ho, C.H., Yang, S. (2011). “Relationship between the Arctic Oscillation and cold surges over East Asia.” Journal of Climate, Vol. 24, No. 1, pp. 68-83. 10.1175/2010JCLI3529.1
  19. Shin, E.H., Kim, D.W., Chung, J.H., Chang, S.R. (2023). “Development of a method for measuring social interest index on disaster using news data.” Journal of the Korean Society of Safety, Vol. 38, No. 5, pp. 27-35. 10.14346/JKOSOS.2023.38.5.27
  20. Son, J.Y., Lee, J.T., Anderson, G.B., Bell, M.L. (2011). “Vulnerability to temperature-related mortality in Seoul, Korea.” Environmental Research Letters, Vol. 6, No. 3, 034027. 10.1088/1748-9326/6/3/034027 23335945 PMC3546816
  21. Sunako, S., Yamaguchi, S., Nakamura, K., Sato, K., Motoyoshi, H. (2025). “Impacts of the December 2022 Heavy Snowfall on Tree Fall and Power Outages in Sado City, Japan.” Journal of Disaster Research, Vol. 20, No. 6, pp. 1103-1110. 10.20965/jdr.2025.p1103
  22. Sung, J.H., Jeong, H.K., Lee, H.J. (2019). The Effects of Extreme Events on Korean Agricultural Sector. Korea Rural Economic Institute, R881, Naju, Korea.
  23. The Economist (2023). Expensive Energy May Have Killed More Europeans than Covid-19 Last Winter. The Economist (Graphic detail), London, UK.
  24. World Health Organization (2021). “Annex 7. Cold wave checklists.” In Checklists to Assess Vulnerabilities in Health Care Facilities in the Context of Climate Change, Geneva, Switzerland, pp. 51-64.
Information
  • Publisher :The Korean Society of Disaster Information
  • Publisher(Ko) :한국재난정보학회
  • Journal Title :Journal of the Society of Disaster Information
  • Journal Title(Ko) :한국재난정보학회논문집
  • Volume : 22
  • No :1
  • Pages :223-237