Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Suggestion of Urban Regeneration Type Recommendation System Based on Local Characteristics Using Text Mining

텍스트 마이닝을 활용한 지역 특성 기반 도시재생 유형 추천 시스템 제안

  • Kim, Ikjun (Department of e-business, Ajou University) ;
  • Lee, Junho (Department of e-business, Ajou University) ;
  • Kim, Hyomin (Department of e-business, Ajou University) ;
  • Kang, Juyoung (Department of e-business, Ajou University)
  • 김익준 (아주대학교 e-비즈니스학과) ;
  • 이준호 (아주대학교 e-비즈니스학과) ;
  • 김효민 (아주대학교 e-비즈니스학과) ;
  • 강주영 (아주대학교 e-비즈니스학과)
  • Received : 2020.04.10
  • Accepted : 2020.09.14
  • Published : 2020.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

"The Urban Renewal New Deal project", one of the government's major national projects, is about developing underdeveloped areas by investing 50 trillion won in 100 locations on the first year and 500 over the next four years. This project is drawing keen attention from the media and local governments. However, the project model which fails to reflect the original characteristics of the area as it divides project area into five categories: "Our Neighborhood Restoration, Housing Maintenance Support Type, General Neighborhood Type, Central Urban Type, and Economic Base Type," According to keywords for successful urban regeneration in Korea, "resident participation," "regional specialization," "ministerial cooperation" and "public-private cooperation", when local governments propose urban regeneration projects to the government, they can see that it is most important to accurately understand the characteristics of the city and push ahead with the projects in a way that suits the characteristics of the city with the help of local residents and private companies. In addition, considering the gentrification problem, which is one of the side effects of urban regeneration projects, it is important to select and implement urban regeneration types suitable for the characteristics of the area. In order to supplement the limitations of the 'Urban Regeneration New Deal Project' methodology, this study aims to propose a system that recommends urban regeneration types suitable for urban regeneration sites by utilizing various machine learning algorithms, referring to the urban regeneration types of the '2025 Seoul Metropolitan Government Urban Regeneration Strategy Plan' promoted based on regional characteristics. There are four types of urban regeneration in Seoul: "Low-use Low-Level Development, Abandonment, Deteriorated Housing, and Specialization of Historical and Cultural Resources" (Shon and Park, 2017). In order to identify regional characteristics, approximately 100,000 text data were collected for 22 regions where the project was carried out for a total of four types of urban regeneration. Using the collected data, we drew key keywords for each region according to the type of urban regeneration and conducted topic modeling to explore whether there were differences between types. As a result, it was confirmed that a number of topics related to real estate and economy appeared in old residential areas, and in the case of declining and underdeveloped areas, topics reflecting the characteristics of areas where industrial activities were active in the past appeared. In the case of the historical and cultural resource area, since it is an area that contains traces of the past, many keywords related to the government appeared. Therefore, it was possible to confirm political topics and cultural topics resulting from various events. Finally, in the case of low-use and under-developed areas, many topics on real estate and accessibility are emerging, so accessibility is good. It mainly had the characteristics of a region where development is planned or is likely to be developed. Furthermore, a model was implemented that proposes urban regeneration types tailored to regional characteristics for regions other than Seoul. Machine learning technology was used to implement the model, and training data and test data were randomly extracted at an 8:2 ratio and used. In order to compare the performance between various models, the input variables are set in two ways: Count Vector and TF-IDF Vector, and as Classifier, there are 5 types of SVM (Support Vector Machine), Decision Tree, Random Forest, Logistic Regression, and Gradient Boosting. By applying it, performance comparison for a total of 10 models was conducted. The model with the highest performance was the Gradient Boosting method using TF-IDF Vector input data, and the accuracy was 97%. Therefore, the recommendation system proposed in this study is expected to recommend urban regeneration types based on the regional characteristics of new business sites in the process of carrying out urban regeneration projects."

현 정부의 주요 국책사업 중 하나인 도시재생 뉴딜사업은 매년 100 곳씩, 5년간 500곳을대상으로 50조를 투자하여 낙후된 지역을 개발하는 것으로 언론과 지자체의 높은 이목이 집중되고 있다. 그러나, 현재 이 사업모델은 면적 규모에 따라 "우리동네 살리기, 주거정비지원형, 일반근린형, 중심시가지형, 경제기반형" 등 다섯 가지로 나뉘어 추진되어 그 지역 본래의 특성을 반영하지 못하고 있다. 국내 도시재생 성공 키워드는 "주민 참여", "지역특화" "부처협업", "민관협력"이다. 성공 키워드에 따르면 지자체에서 정부에게 도시재생 사업을 제안할 때 지역주민, 민간기업의 도움과 함께 도시의 특성을 정확히 이해하고 도시의 특성에 어울리는 방향으로 사업을 추진하는 것이 가장 중요하다는 것을 알 수 있다. 또한 도시재생 사업 후 발생하는 부작용 중 하나인 젠트리피케이션 문제를 고려하면 그 지역 특성에 맞는 도시재생 유형을 선정하여 추진하는 것이 중요하다. 이에 본 연구는 '도시재생 뉴딜 사업' 방법론의 한계점을 보완하기 위해, 기존 서울시가 지역 특성에 기반하여 추진하고 있는 "2025 서울시 도시재생 전략계획"의 도시재생 유형을 참고하여 도시재생 사업지에 맞는 도시재생 유형을 추천하는 시스템을 머신러닝 알고리즘을 활용하여 제안하고자 한다. 서울시 도시재생 유형은 "저이용저개발, 쇠퇴낙후, 노후주거, 역사문화자원 특화" 네 가지로 분류된다 (Shon and Park, 2017). 지역 특성을 파악하기 위해 총 4가지 도시재생 유형에 대해 사업이 진행된 22개의 지역에 대한 뉴스 미디어 10만여건의 텍스트 데이터를 수집하였다. 수집된 텍스트를 이용하여 도시재생 유형에 따른 지역별 주요 키워드를 도출하고 토픽모델링을 수행하여 유형별 차이가 있는 지 탐색해 보았다. 다음 단계로 주어진 텍스트를 기반으로 도시재생 유형을 추천하는 추천시스템 구축을 위해 텍스트 데이터를 벡터로 변환하여 머신러닝 분류모델을 개발하였고, 이를 검증한 결과 97% 정확도를 보였다. 따라서 본 연구에서 제안하는 추천 시스템은 도시재생 사업을 진행하는 과정에서 신규 사업지의 지역 특성에 기반한 도시재생 유형을 추천할 수 있을 것으로 기대된다.

Keywords

References

  1. Aizawa, A., "An Information-Theoretic Perspective of Tf-Idf Measures", Information Processing & Management, Vol. 39, No. 1, 2003, 45-65. https://doi.org/10.1016/S0306-4573(02)00021-3
  2. Bae, M.-K. and Park, S.-H., "Classification and Analysis of the Project Contents and Expected Effects of Urban Regeneration Pilot Projects", JOURNAL OF THE KOREA CONTENTS ASSOCIATION, Vol. 18, No. 10, 2018, 527-544. https://doi.org/10.5392/JKCA.2018.18.10.527
  3. Blei, D. M., Ng, A. Y. and Jordan, M. I., "Latent Dirichlet Allocation", Journal of machine Learning research, Vol. 3, No. Jan, 2003, 993-1022.
  4. Caruana, R. and Niculescu-Mizil, A., "An Empirical Comparison of Supervised Learning Algorithms", Proceedings of Proceedings of the 23rd international conference on Machine learning, 2006.
  5. Choi, J.-W. and Lee, J.-H., "An Impact Analysis of Idle Space Regeneration Types on Regional Revitalization", Journal of the Korea Academia-Industrial cooperation Society, Vol. 17, No. 5, 2016, 478-489. https://doi.org/10.5762/KAIS.2016.17.5.478
  6. Ikonomakis, M., Kotsiantis, S. and Tampakas, V., "Text Classification Using Machine Learning Techniques", WSEAS transactions on computers, Vol. 4, No. 8, 2005, 966-974.
  7. Jeon, K. S., "Urban Regeneration and Sustainable Growth Strategies in Gwangju Metropolitan City", Journal of the Korean Urban Geographical Society, Vol. 14, No. 3, 2011, 1-17. https://doi.org/10.23841/egsk.2011.14.1.1
  8. Jin, E.-A. and Lee, W.-J., "Criticality Analysis of Performance Indicators by Urban Regeneration Project Type - with a Focus on Central City Type, General Neighborhood Type, Urban Residential District Regeneration and Town Regeneration Projects", KIEAE Journal, Vol. 18, No. 6, 2018, 29-41. https://doi.org/10.12813/kieae.2018.18.6.029
  9. Jung, K., Lee, J. and Lee, S., "An Empirical Study on Project Type and Funds Supply Characteristics of Urban Regeneration Priority Regions", Journal of The Korean Regional Development Association, Vol. 28, No. 2, 2016, 19-37. https://doi.org/10.22885/KRDA.2016.28.2.19
  10. Khan, A., Baharudin, B., Lee, L. H. and Khan, K., "A Review of Machine Learning Algorithms for Text-Documents Classification", Journal of advances in information technology, Vol. 1, No. 1, 2010, 4-20.
  11. Kim, D., Kang, J. and Lim, J. I., "Comparative Analysis of Job Satisfaction Factors, Using Lda Topic Modeling by Industries : The Case Study of Job Planet Reviews", Journal of Korea Socierty of IT Services, Vol. 15, No., 2016a.
  12. Kim, T., Choi, H. and Lee, H., "A Study on the Research Trends in Fintech Using Topic Modeling", Journal of the Korea Academia-Industrial Cooperation Society, Vol. 17, No. 11, 2016b, 670-681. https://doi.org/10.5762/KAIS.2016.17.11.670
  13. Lee, J.-H., Seo, E.-K. and Lim, J.-H., "Analyses on Type and Characteristics of Urban Regeneration for Establishment of Urban Identity", KIEAE Journal, Vol. 9, No. 5, 2009, 85-96.
  14. Lee, S.-H., Oh, D.-S. and Kim, J.-K., "Types and Characteristics of Ecological Urban Regeneration - Focused on Urban Regeneration Cases in Germany", KIEAE Journal, Vol. 17, No. 6, 2017, 213-220. https://doi.org/10.12813/kieae.2017.17.6.213
  15. Molit. (2017) "Special Act on Activation and Support of Urban Regeneration".
  16. Park, S., Han, E.-J., Lee, J. and Kim, D.-G., "A Recommendation System for Assisting Devices in Long-Term Care Insurance", The Korean Journal of Applied Statistics, Vol. 31, No. 6, 2018, 693-706. https://doi.org/10.5351/KJAS.2018.31.6.693
  17. Patra, A. and Singh, D., "A Survey Report on Text Classification with Different Term Weighing Methods and Comparison between Classification Algorithms", International Journal of Computer Applications, Vol. 75, No. 7, 2013.
  18. Ryu, T.-C. and Kim, W.-H., "A Study on the Method to Activate of Urban Regeneration in Business Districts in Old Towns through Ipa Analysis - Focusing on Andong-Si Food Street", RESIDENTIAL ENVIRONMENT : JOURNAL OF THE RESIDENTIAL ENVIRONMENT INSTITUTE OF KOREA, Vol. 16, No. 2, 2018, 159-169.
  19. Sang, N. (2010) Toward a Collaborative Implementation Model for Urban Regeneration in Seoul : With Special Reference to Se-Woon District. Seoul City University.
  20. Seo, I., "An Emperical Analysis on the Type of Cultural Urban Regeneration : Focused on the Case of Masan Old Downtown in Changwon City", RESIDENTIAL ENVIRONMENT : JOURNAL OF THE RESIDENTIAL ENVIRONMENT INSTITUTE OF KOREA, Vol. 14, No. 4, 2016, 363-382. https://doi.org/10.22313/reik.2016.14.4.363
  21. Seoul, C. O. (2015) "2025 Seoul Urban Regeneration Stratigies".
  22. Shin, W.-H. and Shin, W.-J., "A Study on the Priority among Achievement Indexes Depending on the Types of Urban Regeneration Projects: Focused on the Cases in Daegu", Journal of The Korean Regional Development Association, Vol. 29, No. 5, 2017, 39-52. https://doi.org/10.22885/KRDA.2017.29.5.39
  23. Shon, Y.-M. and Park, T.-W., "Priority Comparative Analysis for Urban Revitalization Factor of Decline Commercial Area - Focused on Shinchon in Seoul", Journal of the Korean Urban Management Association, Vol. 30, No. 4, 2017, 1-18. https://doi.org/10.36700/KRUMA.2017.12.30.4.1
  24. Williams, N., Zander, S. and Armitage, G., "A Preliminary Performance Comparison of Five Machine Learning Algorithms for Practical Ip Traffic Flow Classification", ACM SIGCOMM Computer Communication Review, Vol. 36, No. 5, 2006, 5-16. https://doi.org/10.1145/1163593.1163596
  25. Yang, N. Y., Kim, S. G. and Kang, J. Y., "Researcher and Research Area Recommendation System for Promoting Convergence Research Using Text Mining and Messenger Ui", The Journal of Information Systems, Vol. 27, No. 4, 2018, 71-96. https://doi.org/10.5859/KAIS.2018.27.4.71
  26. Yoon, S., Shin, M. and J, K., "A Study on City Brand Evaluation Method Using Text Mining : Focused on News Media", Journal of Korea IT Service, Vol. 18, No. 1, 2019, 153-171.
  27. You, E.-S., Choi, G.-H. and Kim, S.-H., "Study on Extraction of Keywords Using Tf-Idf and Text Structure of Novels", Journal of the Korea Society of Computer and Information, Vol. 20, No. 2, 2015, 121-129. https://doi.org/10.9708/jksci.2015.20.2.121
  28. Zhang, Y., Jin, R. and Zhou, Z.-H., "Understanding Bag-of-Words Model: A Statistical Framework", International Journal of Machine Learning and Cybernetics, Vol. 1, No. 1-4, 2010, 43-52. https://doi.org/10.1007/s13042-010-0001-0