All Issue

2023 Vol.41, Issue 1 Preview Page

Article

Estimation of Leisure Behavior Using Unstructured Data: Focusing on Seoul City Wall

비정형 데이터를 이용한 여가통행 행태 추정: 서울시 한양도성을 중심으로

Joonsik JO1
,
Juhyeon KWAK2
,
Donggyun KU3
,
Yeontaek YOO1
,
Seungjae LEE4*
조 준식1
,
곽 주현2
,
구 동균3
,
유 연택1
,
이 승재4*
1Master Course, Department of Transportation Engineering/Department of Smart Cities, University of Seoul, Seoul 02504, Korea
2PhD Course, Department of Transportation Engineering/Department of Smart Cities, University of Seoul, Seoul 02504, Korea
3Research Professor, Department of Transportation Engineering, University of Seoul, Seoul 02504, Korea
4Professor, Department of Transportation Engineering, University of Seoul, Seoul 02504, Korea
1서울시립대학교 교통공학과/스마트시티학과 석사과정
2서울시립대학교 교통공학과/스마트시티학과 석박사통합과정
3서울시립대학교 교통공학과 연구교수
4서울시립대학교 교통공학과 교수
*Corresponding Author
28 February 2023. pp. 135-147
PDF XML Citation
Abstract

Recently, as the types of leisure activities have diversified and the leisure traffic has increased, individual travel patterns have become more complex. It is impossible to precisely track non-daily travel with the existing survey method. Therefore, this study attempted to estimate leisure travel behavior by collecting social media platform information that is easy to grasp leisure activities and using text mining techniques. First, Instagram posts were collected for Hanyang City Wall in Seoul. The collected text data was extracted into a total of four leisure types: social, exercise, tourism, and rest by applying the Latent Dirichlet Allocation (LDA). After that, hot spot analysis using Kernel Density Estimation (KDE) was conducted to understand how each leisure activity is spatially distributed in Hanyang City Wall. Social-type activities occurred relatively much in the eastern region, exercise-type activities in the northwest, tourism-type activities in the central region, and rest-type activities in the southern region. In addition, a Geographically Weighted Regression (GWR) was conducted to find out how the characteristics of leisure activities by region affect the mode choice behavior. The more social/tourism-type activities were observed, the more traffic increased, and the more exercise/rest-type activities were observed, the more traffic decreased. By region, social/tourism-type activities greatly increase the use of transportation in the northern region, and exercise/rest-type activities greatly reduce the use of each means in the central region.

Keywords
GWR
KDE
LDA
leisure travel
social media data

여가활동의 종류가 다양해지고 여가 통행의 수가 증가하면서, 개개인의 통행 패턴은 더욱 복잡해졌다. 이에 따라 기존의 설문조사 방식으로는 비일상 통행 데이터를 정확하게 구축하는 것이 불가능해졌다. 따라서 본 연구에서는 여가활동 파악이 용이한 소셜 미디어 플랫폼 정보를 수집하고, 텍스트마이닝 기법을 활용함으로써 여가통행 행태를 추정하고자 하였다. 먼저, 서울시 한양도성을 대상으로 인스타그램의 게시물을 수집하였다. 수집된 텍스트 데이터는 Latent Dirichlet Allocation(LDA) 모델을 적용함으로써, 사교, 운동, 관광, 휴양의 총 4개의 여가 유형으로 추출되었다. 이후 각각의 여가활동들이 한양도성 내에서 공간적으로 어떻게 분포하고 있는지 파악하기 위해, Kernel Density Estimation(KDE)를 활용한 핫스팟 분석을 시행하였다. 시행 결과, 상대적으로 사교형 활동은 동부지역, 운동형 활동은 서북부지역, 관광형 활동은 중부지역, 휴양형 활동은 남부지역에서 많이 발생한 것으로 확인되었다. 또한, 지역별 여가활동 특성들이 통행수단 선택행위에 어떠한 영향을 미치는지 알아보기 위해 Geographically Weighted Regression(GWR) 분석을 실시하였다. 분석 결과, 사교형 및 관광형 활동이 많이 관측될수록 교통량이 증가하였고, 운동형 및 휴양형 활동은 많이 관측될수록 교통량이 감소하였다. 지역별로는 북부지역의 경우 사교형 및 관광형 여가활동이 교통수단 이용량을 크게 증가시키며, 중부지역에서는 운동형 및 휴양형 여가활동이 각 수단별 이용량을 크게 감소시키는 것으로 분석되었다.

키워드
GWR
KDE
LDA
여가통행
소셜 미디어 데이터
References
1
Bin M.Y., Lee W.D., Moon J.B., Joh C.H. (2013), Integrated Equity Analysis Based on Travel Behavior and Transportation Infrastructure: In Gyeonggi-Do Case, J. Korean Soc. Transp., 31(4), Korean Society of Transportation, 47-57. 10.7470/jkst.2013.31.4.047
2
Blei D.M., Ng A.Y., Jordan M.I. (2003), Latent Dirichlet Allocation, Journal of Machine Learning Research, 3(Jan), 993-1022.
3
Chen Z., Zhang Y., Wu C., Ran B. (2019), Understanding Individualization Driving States Via Latent Dirichlet Allocation Model, IEEE Intelligent Transportation Systems Magazine, 11(2), 41-53. 10.1109/MITS.2019.2903525
4
Cho S.J., Lee K.I., Yoon S.H., Moon S.G., Kim H.Y. (2019), Modifiable Areal Unit Problem in Transit Accessibility Analysis, J. Korean Soc. Transp., 37(6), Korean Society of Transportation, 499-513. 10.7470/jkst.2019.37.6.499
5
Chun H.J., Kim S.A., Yang G.P. (2021), The Effect of Residential Environment on Housing Price Using GWR Model, Korea Association of Real Estate Law, 25(1), 135-151. 10.32989/rel.2021.25.1.135
6
Cliff A. D., Ord J. K. (1981), Spatial processes: models & applications, Taylor & Francis.
7
Go W.Y., Hong J.G. (2022), Framework for Key Performance Index of Use Cases in Smart Transportation Using Text Mining: Focusing on Daegu Metropolitan City, J. Korean Soc. Transp., 40(4), Korean Society of Transportation, 449-461. 10.7470/jkst.2022.40.4.449
8
Im K. H. (2017), SNS Bigdata Analysis Technology Trend and Development Direction, Review of Korea Contents Association, 15(1), 38-43.
9
Injadat M., Salo F., Nassif A.B. (2016), Data Mining Techniques in Social Media: A Survey, Neurocomputing, 214, 654-670. 10.1016/j.neucom.2016.06.045
10
Jang Y.J. (2014), Research Trends and Issues Relating to Leisure and Tourist Trips, International Journal of Tourism and Hospitality Research, 29(3), 139-149.
11
Jang Y.J. (2015), A Methodological Study for Collection of Leisure Travel Data: Focused on ICT Technologies, International Journal of Tourism and Hospitality Research, 28(9), 65-84.
12
Jang Y.J., Ku D.G., Lee S.J. (2021), Pedestrian Mode Identification, Classification and Characterization by Tracking Mobile Data, Transportmetrica A: Transport science, 1-29. 10.1080/23249935.2021.2008044
13
Jang Y.J., Lee C.H. (2016), A Study of Behavioural Characteristics of 20-30’s Single Households on DestinationChoices and Preferences for Leisure Travel, Seoul Urban Research, 17(2), 77-96.
14
Jelodar H., Wang Y., Yuan C., Feng X., Jiang X., Li Y., Zhao L. (2019), Latent Dirichlet Allocation (LDA) and Topic Modeling: Models, Applications, A Survey, Multimedia Tools and Applications, 78(11), 15169-15211. 10.1007/s11042-018-6894-4
15
Kim J.H., Park I.S., Jeong J.H. (2011), Trip Generation Model Based on Geographically Weighted Regression, J. Korean Soc. Transp., 29(2), Korean Society of Transportation, 101-109.
16
Kim S.J., Choo S.H., Kim Y.J., Han Y.J. (2018), Analyzing Factors to Affect Trip Mode Chaining Behavior Using Travel Diary Survey Data in Seoul, The Journal of The Korea Institute of Intelligent Transport Systems, 17(1), 55-70. 10.12815/kits.2018.17.1.55
17
Kim Y.H. (2022), Soical Network Service(SNS) Usage Behavior by Generation, ICT KISDI STAT Report, 22(11), 1-6.
18
Koo J.H., Choo S.H. (2021), Analysis of Factors Affecting Travel Time Considering Travel Purpose, J. Korean Soc. Transp., 39(5), Korean Society of Transportation, 697-709. 10.7470/jkst.2021.39.5.697
19
Kwak J.H., Jo J.S., Ku D.G., Lee S.J. (2022a), The Relationship between Green Transportation and Leisure Travel Based on Social Media Data Chemical Engineering Transactions, 97, 115-120.
20
Kwak J.H., Ku D.G., Oh H.R., Jeong I.H., Shin S.H., Lee S.J. (2022b), Impact Analysis in Spatial Use Changes by COVID: Focusing on Shared Bicycles, J. Korean Soc. Transp., 40(2), Korean Society of Transportation, 178-189. 10.7470/jkst.2022.40.2.178
21
Kwon D.Y., Suh T.J., Kim S.Y., Kim H.S. (2014), Effects of Urban Environments on Pedestrian Behaviors: a Case of the Seoul Central Area, J. Korean Soc. Transp., 32(6), Korean Society of Transportation, 638-650. 10.7470/jkst.2014.32.6.638
22
Lee B.K., Moon, Y.S., Yun T.W., Lee J.K., Jeong J.N., Noh H.H., Rim H.B. (2020a), An Exploratory Study on Instagram Usage Behavior: Based on Structural Relationships between User Motivation and Big 5 Personality Traits, Journal of the HCI Society of Korea, 15(3), 13-22. 10.17210/jhsk.2020.09.15.3.13
23
Lee H.J., 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. 10.21189/JKUGS.23.1.8
24
Lee J.S., Son W.j., Lee H.T., Cho I.S. (2020b), A Study on the Factors Affecting Optimal Site of Offshore Wind Farm from the Perspective of Maritime Traffic using Spatial Analysis, Journal of Coastal Disaster Prevention, 7(2), 85-96. 10.20481/kscdp.2020.7.2.85
25
Magdolen M., von Behren S., Chlond B., Vortisch P. (2022), Long-distance Travel in Tension with Everyday Mobility of Urbanites: A Classification of Leisure Travellers, Travel Behaviour and Society, 26, 290-300. 10.1016/j.tbs.2021.10.010
26
Mahdi A., Hamadneh J., Esztergár-Kiss D. (2022), Modeling of Travel Behavior in Budapest: Leisure Travelers, Transportation Research Procedia, 62, 310-317. 10.1016/j.trpro.2022.02.039
27
Park J.H., Ku, D.G., Jeong I.H., Lee S.J. (2022), A Study of Walking Activity Time Characteristics Based on the Time Use Survey, Journal of the Korea Institute of Intelligent Transportation Systems, 21(3), 53-61. 10.12815/kits.2022.21.3.53
28
Paulsen D. J., Robinson M. B. (2004), Spatial Aspects of Crime: Theory and Practice, Allyn & Bacon.
29
Sa H.J., Lee W.S., Lee B.G. (2021), Corona Blue and Leisure Activities: Focusing on Korean Case, Journal of Internet Computing and Services, 22(2), 109-121.
30
Shafabakhsh G.A., Famili A., Bahadori M.S. (2017), GIS-based Spatial Analysis of Urban Traffic Accidents: Case Study in Mashhad, Iran, Journal of Traffic and Transportation Engineering (English edition), 4(3), 290-299. 10.1016/j.jtte.2017.05.005
31
Shin S.G., Lee C.H., Cheon S.H. (2019), Analyzing Changes in Revenue of Subway Organizations according to Bus Fare Increase in Seoul Metropolitan Area, J. Korean Soc. Transp., 37(6), Korean Society of Transportation, 486-498. 10.7470/jkst.2019.37.6.486
32
Sievert C., Shirley K. (2014), LDAvis: A Method for Visualizing and Interpreting Topics, In Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces, 63-70. 10.3115/v1/W14-311024684756
33
Son S.O., Park J.Y. (2022), Identifying Micro-Level Hotspots of Urban Network Infrastructures Using GIS Data, J. Korean Soc. Transp., 40(4), Korean Society of Transportation, 585-598. 10.7470/jkst.2022.40.4.585
34
Tobler W.R. (1970), A Computer Movie Simulating Urban Growth in the Detroit Region, Economic Geography, 46(sup1), 234-240. 10.2307/143141
35
Toivonen T., Heikinheimo V., Fink C., Hausmann A., Hiippala T., Järv O., et al. (2019), Social Media Data for Conservation Science: A Methodological Overview, Biological Conservation, 233, 298-315. 10.1016/j.biocon.2019.01.023
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 41
  • No :1
  • Pages :135-147
  • Received Date : 2022-11-28
  • Revised Date : 2022-12-05
  • Accepted Date : 2023-01-03
  • DOI :https://doi.org/10.7470/jkst.2023.41.1.135
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • scopus
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close