정보화정책 (Informatization Policy)

한국지능정보사회진흥원 (National Information Society Agency)
권호 표지
DOI QR코드

DOI QR Code

이상탐지 활용 전자집단민원 추정 방법론에 관한 탐색적 연구: 창원시 시민의 소리 사례를 중심으로

An Exploratory Study of Collective E-Petitions Estimation Methodology Using Anomaly Detection: Focusing on the Voice of Citizens of Changwon City

  • 투고 : 2019.11.19
  • 심사 : 2019.12.16
  • 발행 : 2019.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 전자민원시스템에 집단민원을 제기하는 사례가 늘어나고 있으나 이에 대한 효율적인 관리시스템이 아직 마련되어 있지 않아 행정 업무량 증대와 사회적 갈등 양산 등의 부작용이 우려되고 있다. 이에 본 연구에서는 이상탐지와 코퍼스 언어학 기반의 내용분석을 활용한 전자 집단민원 추정 방법론을 제시하고자 하였다. 이를 위하여 1)집단민원의 개념에 대한 이론적 고찰과 2) 비모수적 비지도 학습에 기반 한 이상탐지를 활용한 전자 집단민원 추정과 3) n-gram 코사인 각도 거리를 활용한 민원의 내용 유사도 분석방법론을 제안하고 4) 창원시 시민의 소리에 대한 사례분석을 통하여 제시한 방법론의 유용성과 정책적 시사점, 향후 과제를 검토하였다.

Recently, there have been increasing cases of collective petitions filed in the electronic petitions system. However, there is no efficient management system, raising concerns on side effects such as increased administrative workload and mass production of social conflicts. Aimed at suggesting a methodology for estimating electronic collective petitions using anomaly detection and corpus linguistics-based content analysis, this study conducted the followings: i) a theoretical review of the concept of collective petitions, ii) estimation of electronic collective petitions using anomaly detection based on nonparametric unsupervised learning, iii) a content similarity analysis on petitions using n-gram cosine angle distance, and iv) a case study on the Voice of Citizens of Changwon City, through which the utility of the proposed methodology, policy implications and future tasks were reviewed.

키워드

참고문헌

  1. ACRC(2013). A Study on Reasonable Management of Public Sector Chromic Petitions by Reviewing Overseas Cases. Anti-Corrpuration & Civil Rights Commission.
  2. ACRC(2019a). [Two years of government launch](3) National participation and communication policy culture settled in.... Reinforcing the resolution of national discomfort based on "Civil Petitions Big Data", Anti-Corrpuration & Civil Rights Commission(May 23, 2019. released).
  3. ACRC(2019b). Sinmungo Petition Data: Q1 2019. Anti-Corrpuration & Civil Rights Commission.
  4. ACT No. 15617(2018). Act on the Prevention of Corrution and the Establishment and Management of the Anti-Corruption and Civil Rights Commission.
  5. ACT No. 14839(2017). Civil Petitions Treatment Act.
  6. Aggarwal, C. C. (2013). "Proximity-Based Outlier Detection, Outlier Analysis." in Outlier Analysis, 101-133, Berlin, Heidelberg: Springer.
  7. Daegu(2015). A Study on the Development Direction of Big Data and Cloud-based Civil Service: Focusing on Civil Service Proposal Integrated Management System. Daegu Metropolitan City.
  8. EGOV24(2008). E-Petitions G4C Introduction, Ministry of the Interior and Safety.
  9. EGOV24(2019). E-Petition Service Status. Ministry of the Interior and Safety.
  10. Eun, J. (2006). "The Roh Administration's Strategies of Government Innovation: Continuity and Discontinuity." Korean Journal of Public Administration, 44(3), 207-247.
  11. Guzman, R. (2018). "Sampling: Markov Chains.", https://relguzman.blogspot.com/2018/04/sampling-markov-chains.html. (Retrieved on November 1, 2019).
  12. Hawkins, D. (1980). Identification of Outliers, Chapman and Hall.
  13. Jeong, H., Hatori, T. & Kobayashi, K. (2007). Discourse Analysis of Public Debates: a Corpus-Based Approach. Proceedings of the IEEE Systems, Man, and Cybernetics Conference, Montreal, Canada, 7-10 October: 1782-1793.
  14. Jeong, H. (2008). A Study on Public Deliberation in Provision of Social Overhead Capital, Kyoto University(in Japanese).
  15. Jeong, H., Kobayashi, K., Hatori, K. & Shiramatsu, S. (2010). "Facet Decomposition and Discourse Analysis of Public Debate." Journal of Japan Society of Civil Engineers, Ser. F(Construction and Management), 66(1): 45-56(in Japanese).
  16. Jeong, H, Lee, T. & Hong, S. (2017). "A Copus Analysis of Electronic Petitions For Improving the Responsiveness of Public Services: Forcusing on Busan Petiton." The Korean Journal of Local Government Studies, 21(1), 423-436. https://doi.org/10.20484/klog.21.1.17
  17. Jeong, H., Shiramatsu, S., Kobayashi, K. & Hatori, T. (2008). "Discourse Analysis of Public Debates Using Corpus Inguistic Methodologies." Journal of Computers, 3(8): 58-68
  18. Jung, H. (2006). "A Study on Efficient Solution for Collective Petitions- Centering on Chungcheongnam-do Province." The Korea Local Administration Review, 20(4), 83-108.
  19. KCC(1985). Petitoins Management Guidelines, The Korea Coal Corporation(1992 revised).
  20. Kim, K. & Son, Y. (2018). "Change Acceptable In-Depth Searching in LOD Cloud for Efficient Knowledge Expansion." The Journal of Intelligence and Information Systems, 24(2), 171-193. https://doi.org/10.13088/JIIS.2018.24.2.171
  21. Lee, T., Hong, S. & Jeong, H. (2017). "A Time Series Analysis on the Daily Media Corpus of Public Project in Local Government: Focusing on the Gijang Seawater Desalination Plant Project", The Korean Journal of Local Government Studies, 20(4), 1-23. https://doi.org/10.20484/klog.20.4.1
  22. Majumder, G., Pakray, P., Gelbukh, A. & Pinto, D. (2016). "Semantic Textual Similarity Methods, Tools, and Applications: A Survey." Research Advances and Applications of Evolutionary Computation, 20(4), 647-665.
  23. Min, H., Park, J., Lee, D. & Kim, I. (2014). "Outlier Detection Method for Mobile Banking with User Input Pattern and E-finance Transaction Pattern." Journal of Internet Computing and Services(JICS), 15(1), 157-170. https://doi.org/10.7472/jksii.2014.15.1.157
  24. Modi, K. & Oza, B. (2016). "Outlier Analysis Approaches in Data Mining." IJIRT, 3(7), 6-12.
  25. Oh, M., Park, A., Kim, Y. & Jin, J. (2018). A Study on anomaly detection based on Machine Learning. Sejong: Korea Institute for Health and Social Affairs.
  26. Oh, S. (1984). "A Study on Civil Petition Administration." Korean Journal of Public Administration, 22(1), 1001-1023.
  27. PSIIF(2005), Citizen Participatory Petition System Improvement Manual, Petitions System Improvement and Innovation Forum supported by The Korea Institute of Public Administration.
  28. Rahman,M.S, & Brishty, F. P. (2018). "Anomaly detection of river data for disaster prevention." The International Journal of Engineering and Science(IJES), 7(9.I), 59-68.
  29. Richardson, C. (2009). Virus detection with machine learning. University of Bristol.
  30. Scikit-learn(2019). Novelty and Outlier Detection (2019-07-07 accessed).
  31. Tukey, J.W. (1977). Exploratory data analysis, Addison-Wesley.
  32. Watson, M. R., Shirazi, N., Marnerides, A. K., Mauthe, A. & Hutchison, D. (2016). "Malware Detection in Cloud Computing Infrastructures." IEEE Transactions on Dependable and Secure Computing, 13(2), 192-205. https://doi.org/10.1109/TDSC.2015.2457918
  33. WCPP(2019). How to submit a petition, Western cape provincial parliament.
  34. Wilcox, R. R. (1996). Statistics for the social sciences. Academic Press.
  35. Yahalom, S. (2008). "URI Anomaly Detection Using Similarity Metrics." Master's Thesis, School of Computer Science, Tel-Aviv University.
  36. Yeon, J., Shim, J. & Lee, S. (2013). "Outlier Detection Techniques for Biased Opinion Discovery." The Journal of Society for e-Business Studies, 18(4), 315-326. https://doi.org/10.7838/jsebs.2013.18.4.315
  37. Yi, S., Rhew, S. & Lee, K. (2009). "A Study on the Construction of the System Integration Management System for Civil Affairs." Journal of the Korea Society of Computer and Information, 14(8), 107-109.
  38. Yoon, Y. (1997). Information Society and Teledemocracy: Issues and Prospects. in Lee, H. & Choi, J. (ed.) Utopia of communication? : Informatization and Korean Life, 23-40. Kyunggi: Nanam Publishing.