DOI QR코드

DOI QR Code

텍스트마이닝을 활용한 도로분야 ITS 정책이슈 탐색기법 정립

Establishment of ITS Policy Issues Investigation Method in the Road Section applied Textmining

  • 투고 : 2016.09.20
  • 심사 : 2016.11.09
  • 발행 : 2016.12.31

초록

본 연구는 빅데이터를 활용하여 감사 시 유의해서 살펴보아야 할 ITS 관련 정책이슈 탐색방법 개발 및 적용을 목적으로 한다. 이를 위해 본 연구에서는 William Dunn이 제안한 경계분석을 이론적 토대로 하여, 여기에 감사원 감사실무 프로세스를 접목한 감사이슈 분석 틀을 제안했다. 그리고 이 분석 틀을 전산으로 구현하기 위해 메타문제를 추정하는 개념이 경계분석과 유사한 텍스트마이닝 기법을 응용했다. 텍스트마이닝의 구체적 모형은 David Blei가 제안한 Latent Dirichlet Allocation(LDA) 모형을 기반으로 하는 비대칭-대칭 혼합 어휘소 기반 LDA를 응용했다. 사례분석 결과, 경찰청에서 운영하는 도시교통정보시스템의 교통정보 수집률 저조와 국토교통부의 첨단교통관리시스템과의 중복 문제, 디지털 운행기록계의 주행거리 조작 등이 주요 이슈로 도출됐다.

With requiring circumspections using big data, this study attempts to develop and apply the search method for audit issues relating to the ITS policy or program. For the foregoing, the auditing process of the board of audit and inspection was converged with the theoretical frame of boundary analysis proposed by William Dunn as an analysis tool for audit issues. Moreover, we apply the text mining technique in order to computerize the analysis tool, which is similar to the boundary analysis in the concept of approaching meta-problems. For the text mining analysis, specific model we applied the antisymmetry-symmetry compound lexeme-based LDA model based on the Latent Dirichlet Allocation(LDA) methodologies proposed by David Blei. The several prime issues were founded through a case analysis as follows: lack of collection of traffic information by the urban traffic information system, which is operated by the National Police Agency, the overlapping problems between the Ministry of Land, Infrastructure and Transport and the Advanced Traffic Management System and fabrication of the mileage on digital tachograph.

키워드

참고문헌

  1. Oh C. S. (2016), A Study on the Audit Issues Investigation Method Applied Bigdata and Textmining-Focusing on the Project to Construct Transportation Information in the Road sector, Audit and Inspection Research Institute.
  2. OECD (2015), Government at a Glance 2015, Organization Economic Cooperative Development Publishing, p.146.
  3. GAO (2015), Open Data for Government Accountability, Efficiency, and Effectiveness, GAO-15-240CG, Government Executive Media Group of the United States Government Accountability Office.
  4. ECOPA (2014), Risk-Based Audits: Principles and Implementation, Optimal Audit Case Selection, White Paper, The European Consensus Platform.
  5. Dunn W. (2008), Public Policy Analysis, 4th edition, Pearson, p.97.
  6. Dunn W. (2012), Public Policy Analysis, 5th edition, Pearson, p.90.
  7. Hearst M. (1999), Untangling Text Data Mining, Retrieved March 20, 2007, from School of Information, University of California, Berkeley.
  8. Hearst M. (2003), What is Text Mining?, Retrieved March 20, 2007, from School of Information, University of California, Berkeley.
  9. Grabowski M. and Lula P. (2011), "Automatic Identification of Time and Subject Related Patterns in Large Collection of Scientific Publications," Management Information Systems, vol. 6, no. 3, p.1.
  10. Jung D. M. (2015), Study of Topic Classification and Keywords for Online Fiction Search, A Master's Thesis of Seoul National University, p.22.
  11. Kim D. G. and Weon J. (2013), Development of Foresight Method for Future Disaster Through the Analysis of Complex Foresight Methodology, National Disaster Management, pp.59-79.
  12. OwlNest and Audit and Inspection Research Institute (2015), Audit Topic Model for Transportation Information System using Textmining, p.42.
  13. Jung D. M., Kim J. S., Kim K. N., Heo J. W., Ohn B. W. and Kang M. J. (2013), "A Proposal of a Keyword Extraction System for Detecting Social Issues," J. Intell. Inform. Syst., vol. 19, no. 3, pp.1-23. https://doi.org/10.13088/jiis.2013.19.3.001
  14. Blei D. M., Ng A. Y. and Jordan M. I. (2003), "Latent Dirichlet Allocation," Journal of Machine Learning Research 3.
  15. Steyvers M. and Griffiths T. (2007), Probabilistic Topic Models, In Landauer, T., McNamara, D. S., Dennis, S. and Kintsch, W. (Eds.), Handbook of Latent Semantic Analysis, Hillsdale.
  16. Wallach H., Mimno D. and McCallum A. (2009), Rethinking LDA: Why Priors matter, NIPS.

피인용 문헌

  1. 텍스트 마이닝 기법을 활용한 자율주행자동차 인식분석연구 vol.16, pp.6, 2017, https://doi.org/10.12815/kits.2017.16.6.231
  2. 텍스트 임베딩을 이용한 자율주행자동차 교통사고 분석에 관한 연구 vol.20, pp.1, 2021, https://doi.org/10.12815/kits.2021.20.1.160
  3. 토픽모델링을 활용한 교통경찰 민원 분석 vol.20, pp.4, 2016, https://doi.org/10.12815/kits.2021.20.4.57