비정형 SNS 데이터를 이용한 사회적 거리두기 정량화 시스템에 관한 연구
A Study on the Quantification System of Social Distance Using Unstructured SNS Data
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 몇 년 동안 SARS, MERS 등의 수많은 호흡기 질환이 세계적으로 유행하였고 현재는 코로나-19의 발생으로 호흡기 바이러스 전염 문제가 심각하다. 이에 따라 각 국가들이 바이러스 전파 방지에 역량을 집중하고 있다. 우리나라도 확진 의심자가 발생하면 대기중인 의료진이 투입되어 실시간으로 검사를 실시하고, 확진자 발생시에는 실시간으로 확진자의 위치와 수를 알려 바이러스를 주변에 전파할 위험을 줄이는 노력을 하고 있다. WHO를 비롯한 보건기구들에 따르면, 호흡기 바이러스 전파를 막는 가장 핵심적이고 기본적인 예방 방법은 사회적 거리두기 준수라고 말한다. 그러나 사회적 거리두기 준수의 기준이 개개인별로 다르고 객관적으로 실천하기 어려워 사회적 거리두기 가이드라인을 따르도록 권고하는 것만으로는 사회적 거리두기의 실천에 한계가 있다. 본 논문에서는 이 문제를 해결하기 위해 SNS상의 GPS 좌표, TAG 데이터, TXT 데이터 등의 대규모 비정형 데이터를 하둡과 스파크 기반의 분산처리 시스템으로 처리해 주 별 평균 이동동선과 방문횟수를 기준으로 개인의 사회적 거리두기 준수 정도를 점수화하여 정량적으로 모니터링 할 수 있는 시스템을 제안한다.
Abstract
In recent years, numerous respiratory diseases such as SARS and MERS have become popular around the world, and now the respiratory virus epidemic is serious due to the outbreak of corona-19. As a result, each country is focusing its capabilities on preventing the spread of viruses. South Korea is also making efforts to reduce the risk of spreading the virus around by sending in medical personnel on standby to conduct real-time tests when suspected cases occur, and by informing the location and number of confirmed cases in real time. According to WHO and other health organizations, the most important and basic prevention method to prevent the spread of respiratory viruses is social distance compliance. However, there is a limit to the practice of social distance keeping, just by recommending people to follow the guidelines for social distance keeping because the criteria for compliance with social distance are different for each individual and difficult to objectively implement. To solve this problem, this paper proposes a system that can be quantitatively monitored by scoring individuals' compliance with social distance based on user movement, number of visits by processing large unstructured data such as GPS coordinates, TAG data, and TXT data on SNS with Hadoop and Spark-based distributed processing systems.
참고문헌 (17)
- P. Phillips, "Managing the health and safety legal and psychological ramifications of covid-19: an australian multidisciplinary perspective", Society Register, 4(3), pp.45~66 (2020)
- J. A. Lewnard, "Scientific and ethical basis for social-distancing interventions against COVID-19", The Lancet. Infectious diseases, 20(6), pp.631~633 (2020)
- "A case of domestic group infection" (2020)[URL]
- S. G. Jeong, "A status and improvement plan on the cell broadcasting service (CBS)", The Korean Institute of Communications and Information Sciences, 37(11), pp.220~221 (2018)
- "Causing fatigue from frequent disaster texts" (2020)[URL]
- J. A. Cha, "A Study on the quantification system of social distance using spatial information", Journal of Knowledge Information Technology and Systems, 15, pp.135~138 (2020)
- L. Liu, "Encyclopedia of database systems" (2009), Springer US
- J. A. Iglesias, "Web news mining in an evolving framework", Information Fusion, 28, pp.90~98 (2016)
- K. Jahanbin, "Using Twitter and web news mining to predict COVID-19outbreak", Asian Pacific Journal of Tropical Medicine, 13(8), pp.378~380 (2020)
- D. Borthakur, "Apache hadoop goes realtime at facebook", Proceedings of the ACM SIGMOD International Conference on Management of Data, 11, pp.1071~1080 (2011)
- K Shvachko, "The hadoop distributed file system", 2010IEEE 26th symposium on mass storage systems and technologies (MSST), IEEE, pp.1~10 (2010)
- 황성태, "A Study on Big Data Platform Architecture-based Conceptual Measurement Model Using Comparative Analysis for Social Commerce", 한국지식정보기술학회 논문지, 15(5), pp.623~630 (2020), 한국지식정보기술학회[DOI]
- D. Borthakur, "The hadoop distributed file system: Architecture and design", Hadoop Project Website, ~ (2007)
- A. O’Driscoll, "‘Big data’, Hadoop and cloud computing in genomics", Journal of biomedical informatics, 46(5), pp.774~781 (2013)
- B. Akil, "On the usability of Hadoop MapReduce, Apache Spark & Apache flink for data science", 2017IEEE International Conference on Big Data (Big Data), IEEE, pp.303~310 (2017)
- C. C. Wai, "Typhoon quantitative rainfall prediction from big Data analytics by using the Apache Hadoop Spark parallel computing framework", Atmosphere, 11(8), pp.870~ (2020)
- P. K. Chahal, "An efficient Hadoop-based brain tumor detection framework using big data analytic", Software : Practice and Experience, 50, pp.1~14 (2020)