Spatio-temporal modeling of city events combining datasets in cyberspace and real space

doi:10.11947/j.AGCS.2019.20180327

Abstract

Abstract: The scale and impacts of city events, including cultural, entertainment and sporting events, reflect the economics and culture of a city to a certain extent.The occurrence of events affects urban city significantly both online in cyberspace and offline in real space. The evolutionary perception, dynamic modeling and spatio-temporal analysis of city events from cyberspace and real space, are of important theoretical research and application value. This article proposes a novel approach of city events spatio-temporal modeling and analysis with trajectories and social media datasets in real space and cyberspace respectively. The approach firstly identifies statistically significant anomalous city regions and traffic flows with trajectories during the events, analyzing spatio-temporal change of events in real space, then analyzes spatio-temporal change during the whole process of city events in cyberspace.Finally, this article presents a modeling approach for characterizing the development and evolution of urban geospatial and behavioral space throughout events, with datasets in cyberspace and real space combined. Taking the Opus Ⅱ Jay World Tour in 2015 as an example, employing taxi GPS trace data and Weibo data in Wuhan, the proposed method realizes the whole process modeling and evolution analysis of urban geospatial and behavioral space before, during and after the event. Then the method is compared with two other approaches that use either real space dataset or cyberspace dataset alone. The experimental results show that the proposed approach measures the impact of an event both in cyberspace and real space with reason, and describes city events effectively.

Key words: city events, spatio-temporal analysis, GPS trajectory, social media data, multiple datasets

CLC Number:

P208

TANG Luliang, DAI Ling, REN Chang, ZHANG Xia. Spatio-temporal modeling of city events combining datasets in cyberspace and real space[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(5): 618-629.

References

[1] GELDERS D, VAN ZUILEN B. City events:short and serial reproduction effects on the city's image?[J]. Corporate Communications:An International Journal, 2013, 18(1):110-118.
[2] LUCARELLI A, BERG P O. City branding:a state-of-the-art review of the research domain[J]. Journal of Place Management and Development, 2011, 4(1):9-27.
[3] 北京演出行业协会. 2017年北京市演出市场统计与分析[EB/OL].[2018-01-09]. http://www.bjycxh.com/news/191.html. Beijing Trade Association for Performances. Beijing performance market statistics and analysis in 2017[EB/OL].[2018-01-09]. http://www.bjycxh.com/news/191.html.
[4] NEILL D B, COOPER G F. A multivariate Bayesian scan statistic for early event detection and characterization[J]. Machine Learning, 2010, 79(3):261-282.
[5] MARGINEANTU D, WONG W K, DASH D. Machine learning algorithms for event detection[J]. Machine Learning, 2010, 79(3):257-259.
[6] 牛爽. 基于浮动车的城市道路交通异常事件检测的研究[D]. 北京:北京交通大学, 2008. NIU Shuang. Research on urban traffic incident detection based on floating car[D]. Beijing:Beijing Jiaotong University, 2008.
[7] ZHENG Yu, ZHANG Huichu, YU Yong. Detecting collective anomalies from multiple spatio-temporal datasets across different domains[C]//Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. Seattle, Washington:ACM, 2015:2.
[8] HONG Liang, ZHENG Yu, YUNG D, et al. Detecting urban black holes based on human mobility data[C]//Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. Seattle, Washington:ACM, 2015:35.
[9] LI Zhongmou, XIONG Hui, LIU Yanchi, et al. Detecting Blackhole and Volcano Patterns in Directed Networks[C]//Proceedings of 2010 IEEE International Conference on Data Mining. Sydney, NSW, Australia:IEEE, 2010:294-303.
[10] LI Zhongmou, XIONG Hui, LIU Yanchi. Mining blackhole and volcano patterns in directed graphs:a general approach[J]. Data Mining and Knowledge Discovery, 2012, 25(3):577-602.
[11] ZHOU Xun, KHEZERLOU A V, LIU A, et al. A traffic flow approach to early detection of gathering events:comprehensive results[C]//Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Burlingame, California:ACM, 2016:4.
[12] PAN Bei, ZHENG Yu, WILKIE D, et al. Crowd sensing of traffic anomalies based on human mobility and social media[C]//Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Orlando, Florida:ACM, 2013:344-353.
[13] GABRIELLI L, RINZIVILLO S, RONZANO F, et al. From tweets to semantic trajectories:mining anomalous urban mobility patterns[M]//NIN J, VILLATORO D. Citizen in Sensor Networks. Cham:Springer, 2014(8313):26-35.
[14] ALDHAHERI A, LEE J. Event detection on large social media using temporal analysis[C]//Proceedings of 2017 IEEE 7th Annual Computing and Communication Workshop and Conference. Las Vegas, NV:IEEE, 2017:1-6.
[15] 徐程浩, 郭斌, 欧阳逸, 等. 基于社交媒体的事件感知与多模态事件脉络生成[J]. 计算机科学, 2017, 44(S1):33-36. XU Chenghao, GUO Bin, OUYANG Yi, et al. Event sensing and multimodal event vein generation leveraging social media[J]. Computer Science, 2017, 44(S1):33-36.
[16] XU Lin, YUE Yang, LI Qingquan. Identifying urban traffic congestion pattern from historical floating car data[J]. Procedia-Social and Behavioral Sciences, 2013(96):2084-2095.
[17] XU Zheng, ZHANG Hui, HU Chuanping, et al. Building knowledge base of urban emergency events based on crowdsourcing of social media[J]. Concurrency and Computation:Practice and Experience, 2016, 28(15):4038-4052.
[18] LEE P, LAKSHMANAN L V S, MILIOS E. CAST:a context-aware story-teller for streaming social content[C]//Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. Shanghai:ACM, 2014:789-798.
[19] 王艳东, 李昊, 王腾, 等. 基于社交媒体的突发事件应急信息挖掘与分析[J]. 武汉大学学报(信息科学版), 2016, 41(3):290-297. WANG Yandong, LI Hao, WANG Teng, et al. The Mining and Analysis of Emergency Information in Sudden Events Based on Social Media[J]. Geomatics and Information Science of Wuhan University, 2016, 41(3):290-297.
[20] NEILL D B. Expectation-based scan statistics for monitoring spatial time series data[J]. International Journal of Forecasting, 2009, 25(3):498-517.
[21] LESKOVEC J, RAJARAMAN A, ULLMAN J D. Mining of massive datasets[M]. Cambridge:Cambridge University Press, 2014:8-9.
[22] KREYSZIG E. Advanced engineering mathematics[M]. 4th ed. New York:Wiley, 1979.
[23] Bethlehem J. Applied survey methods:A statistical perspective[M]. Hoboken, N.J.:Wiley, 2009.
[24] BÖRSCH-SUPAN A, ELSNER D, FAβBENDEI H, et al. How to make internet surveys representative:A case study of a two-step weighting procedure[R]. Mannheim, Germany:Munich Center for the Economics of Aging (MEA) at the Max Planck Institute for Social Law and Social Policy, 2004.
[25] BOONSTRA H J, Statistics Netherlands. A simulation study of repeated weighting estimation[R].[S.l.]:Statistics Netherlands, Research Department, Discussion Papers No.04003, 2004.
[26] BETHLEHEM J. Applied survey methods-a statistical perspective[EB/OL]. http://www.applied-survey-methods.com/weight.html.