Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Influenza prediction models by using meteorological and social media informations

기상 및 소셜미디어 정보를 활용한 인플루엔자 예측모형

  • Hwang, Eun-Ji (Korea Health Industry Policy Development Institute) ;
  • Na, Jong-Hwa (Department of Information and Statistics/Business Data Convergence, Chungbuk National University)
  • 황은지 (한국보건산업진흥원) ;
  • 나종화 (충북대학교 정보통계학과/비즈니스데이터융합학과)
  • Received : 2015.07.25
  • Accepted : 2015.09.24
  • Published : 2015.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Influenza, commonly known as "the flu", is an infectious disease caused by the influenza virus. We consider, in this paper, regression models as a prediction model of influenza disease. While most of previous researches use mainly the meteorological variables as a predictive variables, we consider social media information in the models. As a result, we found that the contributions of two-type of informations are comparable. We used the medical treatment data of influenza provided by Natioal Health Insurance Survice (NHIS) and the meteorological data provided by Korea Meteorological Administration (KMA). We collect social media information (twitter buzz amount) from Twitter. Time series model is also considered for comparison.

인플루엔자는 흔히 독감으로 불리는 질병으로 인플루엔자 바이러스가 호흡기 (코, 인후, 기관지, 폐 등)에 감염되어 생기는 병이다. 감기와는 달리 심한 증상을 나타내거나 생명이 위험한 합병증 (폐렴 등)을 유발할 수도 있다. 본 연구에서는 인플루엔자에 대한 예측모형을 다루었으며, 주로 회귀적인 모형을 고려하였다. 기존의 연구들이 주로 기상요인을 예측변수로 사용한 반면, 본 연구에서는 소셜요인의 효과를 살펴보았으며 그 결과 기상요인과 대등한 설명력을 가짐을 확인하였다. 반응변수로는 국민건강보험공단에서 제공하는 인플루엔자 진료건수가 사용되었고, 설명변수에는 기상청에서 제공하는 기상정보와 트위터에서의 인플루엔자 연관키워드 빈도가 사용되었다. 모형의 비교를 위해 시계열 모형도 함께 제시되었다.

Keywords

References

  1. Askitas, N. and Zimmermann, K. F. (2009). Google econometrics and unemployment forecasting, IZA Discussion Paper, 4201.
  2. Box, G. E. P. and Jenkins, G. M. (1976). Time series analysis : Forecasting and control, Holden Day, San Francisco.
  3. Cho, S. A. (2012). nvestigation of association between influenza occurrence and climate factors using time series analysis, Master's Thesis, Korea University, Seoul.
  4. Cho, S., Sohn, C. H., Jo, M. W., Shin, S. Y., Lee, J. H., Ryoo, S. M., Kim, W. Y. and Seo, D. W. (2013). Correlation between national influenza surweillance data and google trends in South Korea, PLos ONE, 8, doi:10.1371/journal.pone.0081422.
  5. Choi, H. (2010). Predicting initial claims for unemployment benefits, Google Technical Report.
  6. Choi, H. and Varian, H. (2012). Predicting the present with google trends, The Econometric Record, 88, 2-9. https://doi.org/10.1111/j.1475-4932.2012.00809.x
  7. D'Amuri, F. (2009). Predicting unemployment in short samples with internet job search query data, MPRA paper, 18403.
  8. D'Amuri, F. and Marcucci, J. (2009). Google it! forecasting the US unemployment rate with a google job search index, Bank of Italy.
  9. Ginsberg, J., Mohebbi, M. H., Patel, R. S., Brammer, L., Smolinski, M. S. and Brilliant, L. (2009). Detecting influenza epidemics using search engine query data, Nature, 457, 1012-1014. https://doi.org/10.1038/nature07634
  10. Haines and Patz (2004). Health Effects of Climate Change, The Journal of the American Medical Association, 291, 99-103. https://doi.org/10.1001/jama.291.1.99
  11. Jang, M. (2011). A study on the prediction of regional influenza patients by using meteorological factors, Proceedings of the Autumn Meeting of KMS, 292-293.
  12. Lee, H. J. (2014). Analysis of statistical models on temperature at the seosan city in Korea, Journal of the Korean Data & Information Science Society, 25, 1293-1300. https://doi.org/10.7465/jkdi.2014.25.6.1293
  13. Manangan, A. P. (2006). Influenza prevalence in the US associated with climate factors, analyzed at multiple spatial and temporal scales, Master Thesis, Georgia State University.
  14. Na, J. H. and Kim, E. S. (2013). Forecasting unemployment rate using social media information, Journal of the Korea Industrial Information Systems Research, 18, 95-101. https://doi.org/10.9723/jksiis.2013.18.6.095
  15. Pablo, F. (2004). Climate, weather and flu diagnoses incidence in the region of Santander (Northern Sapain) during the 1999-2000 epidemic diffusion period, Kluwer Academic Publishers, 20, 223-228.
  16. SAS and UN Global Pulse. (2011). Using social media and online conversations to add depth to unemployment statistics, White Paper, 1-21.
  17. Son, K. T. and Kim, D. H. (2015). Development of statictical forecast model for $PM_{10}$ concentration over Seoul, Journal of the Korean Data & Information Science Society, 26, 289-299. https://doi.org/10.7465/jkdi.2015.26.2.289
  18. Xiao, H., Tian, H., Lin, X., Gao, L., Dai, X., Zhang, X., Chen, B., Zhao, Z. and Xu, J. (2013). Influence of extreme weather and meteorological anomalies on outbreaks of influenza (H1N1), Prevention Medicine & Hygienics, 58, 741-749.
  19. Xu, W., Li, Z. and Chen, Q. (2012). Forecasting the unemployment rate by neural networks using search engine query data, 2012 45th Hawaii International Conference on System Sciences, 3591-3599.

Cited by

  1. R의 Shiny를 이용한 시각화 분석 활용 사례 vol.28, pp.6, 2015, https://doi.org/10.7465/jkdi.2017.28.6.1279
  2. 고차원 자료에서 영향점의 영향을 평가하기 위한 그래픽 방법 vol.28, pp.6, 2015, https://doi.org/10.7465/jkdi.2017.28.6.1291