한국산업정보학회논문지 (Journal of Korea Society of Industrial Information Systems)

한국산업정보학회 (Korea Society of Industrial Information Systems)
권호 표지
DOI QR코드

DOI QR Code

패싯 기반 민원 다차원 분석을 위한 자동 분류 모델

A Study on an Automatic Classification Model for Facet-Based Multidimensional Analysis of Civil Complaints

  • 김나랑 (동아대학교 경영정보학과)
  • 투고 : 2024.02.01
  • 심사 : 2024.02.21
  • 발행 : 2024.02.29
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

시민의 의견인 민원은 다양한 사람들이 여러 주제에 대하여 반복·지속적으로 실시간 쏟아내기 때문에 담당자가 이를 읽고 분석하는데 한계가 있다. 이에 본 연구에서는 빅데이터 분석을 통해 주요 현안에 대한 여론 및 요구 사항을 파악하기 위하여 정성적인 분석에 패싯을 기반으로 한 정량적인 다차원 분석을 위한 자동 분류 모델을 제안하였다. 구체적으로 첫째, 패싯 이론과 정치분석모형을 기반으로 민원 특성을 분석하고 이를 정책 단계에 활용할 수 있는 새로운 분류 프레임워크를 제시하였다. 둘째, 민원 분석 및 처리에 따른 행정 업무를 감소시키고, 시민들의 정책참여를 용이하게 하기 위해 딥러닝을 활용하여 패싯 분석 프레임에 의해 자동으로 속성을 추출하고 분류 하였다. 본 연구결과는 학문적으로 민원 빅데이터의 특성을 이해하고 분석하는데 중요한 단초를 제공하여 향후 많은 후속 연구를 창출할 수 있을 것으로 기대되며, 공공분야를 넘어 교육, 산업, 의료 등 다른 분야에서의 비정형 데이터의 계량화를 위한 가이드 라인과 다차원 분석의 활용에 대한 이론적 근거를 제시할 수 있다. 실무적으로 대용량 전자 민원에 대한 처리체계 개선 및 딥러닝을 통한 자동화로 민원처리 업무의 효율성과 신속성을 높일 수 있으며, 다른 분야의 텍스트 데이터의 처리에 활용될 수 있을 것이다.

In this study, we propose an automatic classification model for quantitative multidimensional analysis based on facet theory to understand public opinions and demands on major issues through big data analysis. Civil complaints, as a form of public feedback, are generated by various individuals on multiple topics repeatedly and continuously in real-time, which can be challenging for officials to read and analyze efficiently. Specifically, our research introduces a new classification framework that utilizes facet theory and political analysis models to analyze the characteristics of citizen complaints and apply them to the policy-making process. Furthermore, to reduce administrative tasks related to complaint analysis and processing and to facilitate citizen policy participation, we employ deep learning to automatically extract and classify attributes based on the facet analysis framework. The results of this study are expected to provide important insights into understanding and analyzing the characteristics of big data related to citizen complaints, which can pave the way for future research in various fields beyond the public sector, such as education, industry, and healthcare, for quantifying unstructured data and utilizing multidimensional analysis. In practical terms, improving the processing system for large-scale electronic complaints and automation through deep learning can enhance the efficiency and responsiveness of complaint handling, and this approach can also be applied to text data processing in other fields.

키워드

과제정보

이 논문은 2020년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임 (NRF-2020S1A5A8042164)

참고문헌

  1. Banerjee, I., Ling, Y., Chen, M. C., Hasan, S. A., Langlotz, C. P., and Moradzadeh. (2018). Comparative Effectiveness of Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) Architectures for Radiology Text Report Classification. Artificial intelligence in medicine. 
  2. Ban, S. J. (2016). Politics of Universities Reorganization Evaluation Policy. The Politics of Education, 23(1), 59-89. 
  3. Cai, J., Li, J., Li, W., and Wang, J. (2018). Deep Learning Model Used in Text Classification. In 2018 15th International Computer Conference on Wavelet Active Media Technology and Information P rocessing (ICCWAMTIP ), 123-126). 
  4. Cho, Y. (2021). Awareness and resolution of touristification in Korea using social media big data analytics. Global Business & Finance Review (GBFR), 26(1), 68-78.  https://doi.org/10.17549/gbfr.2021.26.1.68
  5. Choi, H. O. (2016). Study on Selecting Priority Criteria Utilizing Civil Complaint Data in the Field of Environment and Sanitation. Environmental policy, 24(2), 45-57.  https://doi.org/10.15301/jepa.2016.24.2.45
  6. Choi, S. J., Shin, G. Y., and Oh, Y. H. (2023). Analyzing data-related policy programs in Korea using text mining and network cluster analysis. Journal of Korea Society of Industrial Information Systems, 28(6), 63-81. 
  7. Han, J. H., and An, K. S. (2022). Comparison of Perceptions of Wellness Tourism in Korea Before and After COVID-19: Results of Social Big Data Analysis. Global Business & Finance Review, 27(2), 1-13. 
  8. Jeong, H., Hatori, T., and Kobayashi, K. (2010). A Protocol Analysis of Public Debate using Facet Theory. In Geographical Marginality as a Global Issue, 77. 
  9. Jin, D. Y., Kang, S. W., Han, K. J., Kim, J. H., Kim, D. Y., and Kang, S. A. (2019). A Study on Improving Reflection of Demands for Settling Environmental Issues in Daily Lives: Focusing on the Analysis of Civil Complaint Big Data. KEI Research Report, 2019(9), 1-100. 
  10. Joo, Y. J. (2023). A Study on the Visualization of Geospatial Big Data using Sentiment Analysis of Collective Civil Complaints. Journal of the KAGIS, 26(1), 11-20. 
  11. Karim, F., Majumdar, S., Darabi, H., and Chen, S. (2018). LSTM Fully Convolutional Networks for Time Series Classification. IEEE Access, 6, 1662-1669.  https://doi.org/10.1109/ACCESS.2017.2779939
  12. Kim, H. J., Lee, T. H., Yu, .S E., and Kim, N. N. (2018). A Study on Text Mining Methods to Analyze Civil Complaints - Structured Association Analysis. Journal of Korea Society of Industrial Information Systems, 23(3), 15-30. 
  13. Kim, I., and Kim, S. (2022). Automatic Classification of Academic Articles Using BERT Model Based on Deep Learning. Journal of the Korean Society for Information Management, 39, 293-310. 
  14. Kim, J. S. (2023). A Study on Fine-Tuning and Transfer Learning to Construct Binary Sentiment Classification Model in Korean Text. Journal of Korea Society of Industrial Information Systems, 28(5), 15-30.  https://doi.org/10.11627/jksie.2023.46.4.015
  15. Kim, M. S., Yang, H. J., Tien Wing An, J., Joo, J. M., and Chae, H. J. (2018). Sentiment Analysis of News Articles on Agricultural Products Using Convolutional Neural Network. KIISE Transactions on Computing Practices, 24(11), 623-627.  https://doi.org/10.5626/KTCP.2018.24.11.623
  16. Kim, N., Nam, H., and Park, Y. (2023). Proposals for Improving Endangered Species Protection Policies through Analysis of Citizen Complaint Data. Proceedings of the Korean Society of Environmental Ecology, 2023(2), 87-88. 
  17. Kim, S. (2008). Meltsner's political analysis model as a case study method for problem structuring: Focused on the conflict case of Mountain Cheonseong Tunnel. The Korean Journal of Local Government Studies, 11(4), 151-170. 
  18. Kim, T. S. (2005). Understanding Classification. Bibliographic Information Processing Society. 
  19. Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1746-1751. 
  20. Kwon, K. S., Choi, Y. S., and Hwang, E. Y. (2006). A study on Interface Evaluation of On-line Commercial Database of Legal Information. Proceedings of the Korean Society for Information Management Conference, 49-56. 
  21. Lee, E., Gu, Y., and Kim, S. (2021). Analysis on the Inquiries of Open Secondary School for Its Operational Improvement. Research Institute of Education Korea University, 34(4), 75-106.  https://doi.org/10.24299/kier.2021.344.75
  22. Lee, H. J., and Kang, Y. O. (2020). Understanding Tourist's Region of Attraction and Image of City through Social Network Data Analysis. Journal of the Korean Urban Geographical Society, 23(1), 101-114.  https://doi.org/10.21189/JKUGS.23.1.8
  23. Lee, I., and Woo, J. (2019). Movie attendance and sales forecast model through big data analysis. The Korea Journal of BigData, 4(2), 185-194.  https://doi.org/10.36498/KBIGDT.2019.4.2.185
  24. Lee, K. H. (2020). A Study on the Analysis of Civil Complaints in Maritime Police. Korean Association of Maritime Police Science, 10(4), 1-18.  https://doi.org/10.30887/jkmps.2020.10.4.001
  25. Lee, S., Jung, C., and Kim, J. (2016). Sentiment analysis on movie reviews through building a modified sentiment dictionary by movie genre. Journal of Intelligence and Information Systems, 22(2), 97-113.  https://doi.org/10.13088/jiis.2016.22.2.097
  26. Lee, T., Hong, S., and Jeong, H. (2020). An Automatic Analysis of Public Debate of Local Assembly by Utilizing a Facet Analysis. The Korea Association for Policy Studies, 29(1), 47-69.  https://doi.org/10.52372/kjps29103
  27. Meltsner, A. J. (1972). Political feasibility and policy analysis. Public administration review, 859-867. 
  28. Newspim.com. (2020). [2020 National Assembly Audit] National Human Rights Commission of Korea Sees a Sharp Increase in Complaints of 'Negligent Handling'... More Than Doubled in Two Years. https://www.newspim.com/news/view/20201015000111 (Accessed on November. 12th, 2023) 
  29. Park, H. J., Choi, B. G., Na, Y. W., and Kim, S. P. (2015). Pattern Analysis of Environmental Complaints Using Spatial Big Data In Incheon. Ksce 2015 Convention 2015 Civil Expo & Conference, 35-36. 
  30. Park, J., and Kim, S. (2011). A Study on Psychological Factors in Establishing Living Space Based on Facet Theory, Proceedings of the Korean Institute of Architects Conference, 31(1), 17-18. 
  31. Park, J., Choi, J., and Kim, S. (2010). A Study on Psychological Behavior at Earthquake Evacuation using the Facet Theory - Focusing on the MDS Analysis Technique. Journal of the Architectural Institute of Korea, 26(8), 71-78. 
  32. Park, T. Y., Kim, S. J., and Oh, H. J. (2019). Empirical Verification of the Disaster Safety Information Facet Classification Scheme. Journal of the Korean Society for Hazard Mitigation, 19(3), 85-95.  https://doi.org/10.9798/KOSHAM.2019.19.3.85
  33. Pitsilis, G. K., Ramampiaro, H., and Langseth, H. (2018). Applied Effective Hate-speech Detection in Twitter Data using Recurrent Neural Networks. Intelligence, 4730-4742. 
  34. Ranganathan, S. R. (1967). Prolegomena to library classification. Asia Publishing House (New York). 
  35. Rosati, L., Lai, M. E., and Gnoli, C. (2004). Faceted classification for public administration. In Semantic Web Applications and Perspectives (SWAP)-1st Italian Semantic Web Workshop. 
  36. Son, N. R., and Kim, S. Y. (2017). Complaints Statistics and Department of Automated Classifications System through Public Complaints Big Data Analysis. Journal of Korean Institute of Next Generation Computing, 13(1), 22-35. 
  37. Yu, S. E., Hong, S. G., Lee, T. H., and Kim, N. R. (2018). A Pattern Analysis of Bus Civil Complaint in Busan City Using the Text Network Analysis. Korean Computers and Accounting Review, 16(2), 19-43  https://doi.org/10.32956/kaoca.2018.16.2.19
  38. Zhang, X., Zhao, J., and LeCun, Y. (2015). Character-level convolutional networks for text classification. Advances in neural information processing systems, 28.