The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

An Analysis of Civil Complaints about Traffic Policing Using the LDA Model

토픽모델링을 활용한 교통경찰 민원 분석

  • Lee, Sangyub (Dept. of Police Science, Korea National Police University)
  • Received : 2021.07.12
  • Accepted : 2021.08.10
  • Published : 2021.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study aims to investigate the security demand about the traffic policing by analyzing civil complaints. Latent Dirichlet Allocation(LDA) was applied to extract key topics for 2,062 civil complaints data related to traffic policing from e-People. And additional analysis was made of reports of violations, which accounted for a high proportion. In this process, the consistency and convergence of keywords and representative documents were considered together. As a result of the analysis, complaints related to traffic police could be classified into 41 topics, including traffic safety facilities, passing through intersections(signals), provisional impoundment of vehicle plate, and personal mobility. It is necessary to strengthen crackdowns on violations at intersections and violations of motorcycles and take preemptive measures for the installation and operation of unmanned traffic control equipments, crosswalks, and traffic lights. In addition, it is necessary to publicize the recently amended laws a implemented policies, e-fine, procedure after crackdown.

본 연구는 민원데이터를 분석함으로써 교통경찰에 대한 국민의 치안 수요를 탐색하고자 하였다. 이를 위해 교통경찰 관련 국민신문고 민원데이터 2,062건을 대상으로, 토픽모델링 방법 중 하나인 잠재 디리클레 할당(Latent Dirichlet Allocation)을 통해 주요 토픽을 추출하고 높은 비중을 차지한 위반신고에 대해 추가분석을 시도하였다. 이 과정에서 키워드와 대표문서의 일관성과 합치성을 함께 고려하였다. 분석 결과 교통경찰 관련 민원은 시설개선, 신호에 따른 교차로통행방법, 번호판 영치, 개인형 이동장치 등 41개의 토픽으로 분류할 수 있었다. 교차로내 위반과 이륜자동차의 위반에 대한 단속을 강화하고 무인교통단속장비, 횡단보도, 신호등의 설치 및 운영에 대한 선제적인 조치, 최근 개정된 법령과 시행된 정책, 경찰교통민원 사이트, 단속 사후 절차에 대한 더욱 활발한 홍보가 필요한 것으로 판단된다.

Keywords

References

  1. Baeck B.(2013), "A Study on the Administrative System and Problems 'Voice of Customer'," The Korean Association of Police Science Review, vol. 15, no. 5, pp.115-146.
  2. Baek S.(2019), Exploration on utilization of word embedding for topic modeling in Korean data, Master's Thesis, The Graduate School of Seoul National University.
  3. Blei D. M.(2012), "Probabilistic Topic Models," Communications of the ACM, vol. 55, no. 4, pp.77-84. https://doi.org/10.1145/2133806.2133826
  4. Blei D. M., Ng A. Y. and Jordan M. I.(2003), "Latent dirichlet allocation," The Journal of Machine Learning Research, vol. 3, pp.993-1022.
  5. Choi H.(2016), "Study on Selecting Priority Criteria Utilizing Civil Complaint Data in the Field of Environment and Sanitation," Journal of Environmental Policy and Administration, vol, 24, no. 2, pp.45-57. https://doi.org/10.15301/jepa.2016.24.2.45
  6. Choi S. and Ko E.(2019), "Analysis of from 1960 to 2018 using Metadata with Dynamic Topic Modeling," Korean Journal of Journalism & Communication Studies, vol. 63, no. 4, pp.7-42. https://doi.org/10.20879/kjjcs.2019.63.4.001
  7. Hamzeian D.(2021), Using Machine Learning Algorithms for Finding the Topics of COVID-19 Open Research Dataset Automatically, Master's Thesis, University of Waterloo.
  8. Hong S., Jeong I. and Lee Y.(2019), "A Study on the Automatic Categorization of Security Demand through Text Mining," The Journal of Police Science, vol. 19, no. 2, pp.271-298.
  9. Kang M.(2009), "Traffic Accident analysis and Traffic Police Activity-Centering Gwangju Province Police Agency," Journal of the Korea Contents Association, vol. 9, no. 9, pp.199-209. https://doi.org/10.5392/JKCA.2009.9.9.199
  10. Kil H.(2018), "The Study of Korean Stopwords list for Text mining," URIMALGEUL: The Korean Language and Literature, vol. 78, pp.1-25. https://doi.org/10.18628/urimal.78..201809.1
  11. Kim C., Kang J. and Park J.(2019), "A Study on the opinion spam detection system using natural language processing based on machine Learning," Proceedings of Symposium of the Korean Institute of Communications and Information Sciences, pp.956-957.
  12. Kim J. Y. and Chang J. S.(2018), "Analysing Civil Traffic Complaints using Latent Dirichlet Allocation," Proceedings of the KOR-KST Conference, vol. 79, pp.106-111.
  13. Kim S.(2009), "An Analysis of Policing Needs in Daegu Gyeongbuk Areas," Korean Local Government Review, vol. 11, no. 3, pp.185-203.
  14. Korea Information Society Agency, https://www.data.go.kr/, 2021.06.15.
  15. Korea Legislation Research Institute, https://elaw.klri.re.kr/kor_service/main.do, 2021.07.05.
  16. Lee H., Chang J. and Kim G.(2020), "A Study on the Conflict Structure of the Standing Committee through Topic Analysis of the National Assembly Minutes: Health and Welfare Committee in the First Half of the 20th National Assembly," Korean Party Studies Review, vol. 19, no. 2, pp.131-167. https://doi.org/10.30992/KPSR.2020.06.19.2.131
  17. Lee S. and Kim H.(2009), "Keyword Extraction from News Corpus using Modified TF-IDF," The Journal of Society for e-Business Studies, vol. 14, no. 4, pp.59-73.
  18. Lee Y., Lee Y., Seong J., Stanescu A., Ji S. and Hwang C. S.(2020), "An Analysis of the latest Trends and Topics in Geography Research Using Topic Modeling," Journal of the Korean Geographical Society, vol. 55, no. 6, pp.589-599. https://doi.org/10.22776/KGS.2020.55.6.589
  19. Medical World News, http://medicalworldnews.co.kr/news/view.php?idx=1510929258, 2021.06.21.
  20. Ministry of Government Legislation, https://www.moleg.go.kr/lawinfo/makingInfo.mo?lawSeq=60649&lawCd=0&&lawType=TYPE5&mid=a10104010000, 2021.07.05.
  21. Moneytoday, https://news.mt.co.kr/mtview.php?no=2020091716432163577, 2021.07.02.
  22. Na S., Yang G. and Shin J.(2019), "Classifying Customer's Written Questions by Topics Using Deep Learning(LSTM)," The Transactions of the Korean Institute of Electrical Engineers, vol. 68, no. 11, pp.1411-1416. https://doi.org/10.5370/KIEE.2019.68.11.1411
  23. Oh C., Lee Y. and Ko M.(2016), "Establishment of ITS Policy Issues Investigation Method in the Road Section applied Text mining," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 15, no. 6, pp.10-23. https://doi.org/10.12815/kits.2016.15.6.010
  24. Park H., Kim H. and Hong Y.(2017), "A Topic Modeling Analysis on the Major Social Issues of the Students' Human Rights Ordinance in Korea," Asian Journal of Education, vol. 18, no. 4, pp.683-711. https://doi.org/10.15753/aje.2017.12.18.4.683
  25. Park J. and Lee S.(2020), "Big Data Analysis of Busan Civil Affairs Using the LDA Topic Modeling Technique," Information Policy, vol. 27, no. 2, pp.66-83.
  26. Park S., Lee H., So J. and Yun I.(2021), "Study of Analysis for Autonomous Vehicle Collision Using Text Embedding," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 20, no. 1, pp.160-173. https://doi.org/10.12815/kits.2021.20.1.160
  27. Roder M., Both A. and Hinneburg A.(2015), "Exploring the space of topic coherence measures," In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, pp.399-408.
  28. Shin A.(2019), Keyword and Topic Analysis on Free Semester Policy Using Big Data, Ph.D. Dissertation, The Graduate School of Seoul National University.
  29. Syed S. and Spruit M.(2017), "Full-text or abstract? Examining topic coherence scores using latent dirichlet allocation," In 2017 IEEE International Conference on Data Science and Advanced Analytics(DSAA), pp.165-174.
  30. Woo C. W. and Lee J. Y.(2020), "Investigation of Research Topic and Trends of National ICT Research-Development Using the LDA Model," Journal of the Korea Convergence Society, vol. 11, no. 7, pp.9-18. https://doi.org/10.15207/JKCS.2020.11.7.009
  31. Woo Y. H. and Kim H. H.(2020), "Topic Analysis of the National Petition Site and Prediction of Answerable Petitions Based on Deep Learning," KIPS Transactions on Software and Data Engineering, vol. 9, no. 2, pp.45-52. https://doi.org/10.3745/KTSDE.2020.9.2.45
  32. Yang H., Ahn J. and Lee T.(2021), "A Study of Korean's Experiences of Unfairness Based on Analysis of Text Big Data Posted on the Blue House National Petition," Survey Research, vol. 22, pp.25-59. https://doi.org/10.20997/SR.22.1.2
  33. Yonhap News Agencies, https://news.naver.com/main/read.nhn?mode=LSD&mid=sec&sid1=102&oid=001&aid=0006801892, 2021.07.02.
  34. Yoo S., Kang B., Kim J., Lee G., Lee M. and Koh S.(2020), "The Lowest Price Matching Service Using Cosine Similarity Analysis," Proceedings of the Korean Society of Broadcast Engineers Conference, pp.502-507.
  35. Yu Y. R.(2017), Analysis of media coverage on 2015 revised curriculum policy using Big Data Analysis, Ph.D. Dissertation, The Graduate School of Seoul National University.