뉴스 기사 텍스트 마이닝과 네트워크 분석을 통한 폭염의 사회·경제적 영향 유형 도출: 2012~2016년 사례
Text Mining and Network Analysis of News Articles for Deriving Socio-Economic Damage Types of Heat Wave Events in Korea: 2012~2016 Cases
0
조회
0
다운로드
8
인용
0
참고문헌
키워드
초록
In order to effectively prepare for damage caused by weather events, it is important to proactively identify the possible impacts of weather phenomena on the domestic society and economy. Text mining and Network analysis are used in this paper to build a database of damage types and levels caused by heat wave. We collect news articles about heat wave from the SBS news website and determine the primary and secondary effects of that through network analysis. In addition to that, based on the frequency with which each impact keyword is mentioned, we estimate how much influence each factor has. As a result, the types of impacts caused by heat wave are efficiently derived. Among these types of impacts, we find that people in South Korea are mainly interested in algae and heat-related illness. Since this technique of analysis can be applied not only to news articles but also to social media contents, such as Twitter and Facebook, it is expected to be used as a useful tool for building weather impact databases.
Abstract
In order to effectively prepare for damage caused by weather events, it is important to proactively identify the possible impacts of weather phenomena on the domestic society and economy. Text mining and Network analysis are used in this paper to build a database of damage types and levels caused by heat wave. We collect news articles about heat wave from the SBS news website and determine the primary and secondary effects of that through network analysis. In addition to that, based on the frequency with which each impact keyword is mentioned, we estimate how much influence each factor has. As a result, the types of impacts caused by heat wave are efficiently derived. Among these types of impacts, we find that people in South Korea are mainly interested in algae and heat-related illness. Since this technique of analysis can be applied not only to news articles but also to social media contents, such as Twitter and Facebook, it is expected to be used as a useful tool for building weather impact databases.
참고문헌 (21)
- Bastian, M., "Gephi:An open source software for exploring and manipulating networks", Proc., In Third international AAAI conference on weblogs and social media, San Jose, California, the Association for the Advancement of Artificial Intelligence, pp.2~ (2009)
- Blondel, V. D., "Fast unfolding of communities in large networks", J. Stat. Mech.-Theory E, 10, pp.10008~ (2008)
- An analysis of the multiple impacts and policy networks of an extreme flood event in a metropolitan area, "Chae, Y.", KEI, 162~, pp.KEI 2016-14 (2016)
- Big data analysis of disaster caused by climate change, "GTC", Green Technology Center, 129~ (2015)
- Gupta, V., "A survey of text mining techniques and applications", J. Emerging Technologies in Web Intelligence, 1, pp.60~76 (2009)
- Hagberg, A. A., "Exploring network structure, dynamics, and function using NetworkX", Proc. The 7th Python in Science Conference (SciPy2008), pp.11~15 (2008)
- Jacomy, M., "ForceAtlas2, a continuous graph layout algorithm for handy network visualization designed for the Gephi software", PLoS ONE, 9, pp.e98679~ (2014)[DOI]
- 김도우, "우리나라 폭염 인명피해 발생특징", 대기, 24(2), pp.225~234 (2014), 한국기상학회
- Annual Report on the Notified Patients with Heat-related illness in Korea, "KCDC", Korea Centers for Disease Control and Prevention, 51~ (2016)
- Statistical Yearbook of Natural Disaster 2015, "MPSS", Ministry of Public Safety and Security, 184~ (2016)
- Mittermayer, M. -A., "Forecasting Intraday Stock Price Trends with Text Mining Techniques", Proc.The 37th Hawaii International Conference on Social Systems, pp.10~ (2004), IEEE
- Nassirtoussi, A. K., "Text mining for market prediction : a systematic review", Expert Syst. Appl, 41, pp.7653~7670 (2014)[DOI]
- Newman, M. E. J., "Modularity and community structure in networks", Proc. The National Academy of Sciences, 103, pp.8577~8582 (2006)[DOI]
- Report on climate change scenario 2011, "NIMS", National Institute of Meteorological Sciences, 117~ (2011)
- Announcement of government-wide heat wave measures 2017, "MOIS", Ministry of the Interior and Safety, 15~ (2017)
- Park, E. L., "KoNLPy: Korean natural language processing in Python", Proc. The 26th Annual Conference on Human & Cognitive Language Technology, SIGHCLT, pp.133~136 (2014)
- Park, S. B., "Algal blooms hit South Korean rivers", Nature (2012)[DOI]
- Rickman, T. A., "The changing digital dynamics of multichannel marketing : The feasibility of the weblog : text mining approach for fast fashion trending", J. Fashion Marketing and Management, 11, pp.604~621 (2007)[DOI]
- 선현석, "텍스트 마이닝 알고리즘을 이용한 기상청 기상연감 자료 분석", 응용통계연구, 30(4), pp.603~613 (2017), 한국통계학회
- 원진영, "텍스트마이닝을 활용한 사회위험 이슈 도출", Crisisonomy, 10(7), pp.33~52 (2014), (사)위기관리이론과실천
- WMO Guidelines on Multi-Hazard Impactbased Forecast and Warning Services, "WMO", World Meteorological Organization, 23~ (2015)