屈树学;董琪;秦嘉徽;刘雨思;张晶;
QU Shu-xue;DONG Qi;QIN Jia-hui;LIU Yu-si;ZHANG Jing;College of Geospatial Information Science and Technology/3D Information Collection and Application Key Lab of Ministry of Education,State Key Laboratory Incubation Base of Urban Environmental Processes and Digital Simulation/Beijing Laboratory of Water Resources Security,Capital Normal University;

• 1:首都师范大学地球空间信息科学与技术国际化示范学院首都师范大学三维信息获取与应用教育部重点实验室/城市环境过程与数字模拟国家重点实验室培育基地/水资源安全北京实验室

摘要(Abstract)：

城市空间分异研究对城市规划、旅游地资源配置、公共交通优化等具有重要意义。该文基于2016年北京市核心六区微博签到数据,根据游客和当地居民签到行为差异,依据时间特征、空间特征和签到比率特征,通过机器学习方法对游客与当地居民进行分类,利用局部莫兰指数和基于签到POI类型的层次聚类法实现细粒度的签到聚集区类型识别,并探究两类人群签到聚集区空间分布与签到类型的差异。结果表明:该文分类模型各项评价指标均在0.9以上,较前人分类结果有较大提升;基于该分类模型所得游客和居民社交媒体签到特征差异显著,游客签到主要集中在故宫周边,以风景名胜、体育休闲和餐饮服务类型为主,居民签到较分散且科教文化服务、商务住宅类型突出,同时发现"菖蒲河公园"等居民签到多而游客签到少的显著差异地区。利用社交媒体数据进行人群异质性角度下的空间分异研究,有助于准确捕捉不同人群在城市中的活动类型、特征并探究城市内部活动规律。
The study of urban spatial differentiation is of great significance to urban planning, resource allocation of tourist destination and optimization of public transportation.In recent years, with the wide application of big data, social media data with geographic tags provide new directions and threads for urban research.Based on the microblogging check-in data of the six core districts of Beijing in 2016,this paper classifies tourists and local residents according to the time characteristics, location characteristics and check-in frequency characteristics through machine learning method.Next, Anselin Local Moran′s I and hierarchical clustering based on check-in POI types are used to identify the check-in area types in fine-grained check-in clusters and explore the differences between the spatial distribution and check-in types of the two groups.The results showed that the eigenvalues of all the evaluation indexes of the classification model adopted in this paper are above 0.9,which is greatly improved compared with previous classification results.The social media check-in characteristics of tourists and residents based on this model are significantly different.Tourists′ check-in mainly focuses on scenic spots, sports leisure and catering services around the Forbidden City, while residents′ check-in is scattered and scientific, educational and cultural services and commercial housing are prominent check-in areas.It also found that "Changpu River Park" and other significant difference areas with more residents′ check-in and fewer tourists′ check-in.The use of social media data in group classification can accurately capture the activity types, characteristics and contrasts of different groups, which provides reference and help for revealing the urban spatial differentiation, exploring the activity differences within the city, and promoting urban development.

关键词(KeyWords)： 社交媒体数据;空间分异;机器学习;游客;居民
social media data;spatial differentiation;machine learning;tourists;residents

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金面上项目“基于事件语义增强的地理信息服务群推荐”(41771477)

作者(Authors): 屈树学;董琪;秦嘉徽;刘雨思;张晶;
QU Shu-xue;DONG Qi;QIN Jia-hui;LIU Yu-si;ZHANG Jing;College of Geospatial Information Science and Technology/3D Information Collection and Application Key Lab of Ministry of Education,State Key Laboratory Incubation Base of Urban Environmental Processes and Digital Simulation/Beijing Laboratory of Water Resources Security,Capital Normal University;

参考文献(References)：

• [1] 北京市发展和改革委员会.北京市国民经济和社会发展第十四个五年规划和二〇三五年远景目标纲要[EB/OL].http://fgw.beijing.gov.cn/fzggzl/2021bjlh/zwssw/202102/P0202103
• 09585602206062.pdf,2021-04-01.
• [2] RICHTER L K,SMITH V L.Hosts and Guests:The Anthropology of Tourism[M].University of Pennsylvania Press,2012.
• [3] LIU Y,LIU X,GAO S,et al.Social sensing:A new approach to understanding our socioeconomic environments[J].Annals of the Association of American Geographers,2015,105(3):512-530.
• [4] 梁雨廷，胡云锋.基于POI数据的“美丽浙江”建设评估[J].地理与地理信息科学，2021,37(5):55-63.
• [5] 张俊涛，武芳，张浩.利用出租车轨迹数据挖掘城市居民出行特征[J].地理与地理信息科学，2015,31(6):104-108.
• [6] 刘瑜，詹朝晖，朱递，等.集成多源地理大数据感知城市空间分异格局[J].武汉大学学报(信息科学版),2018,43(3):327-335.
• [7] CAO W P,DONG L,WU L,et al.Quantifying urban areas with multi-source data based on percolation theory[J].Remote Sensing of Environment,2020,241:111730.
• [8] 贺泽亚，吴必虎，刘瑜.基于社交网络签到数据的城市空间相互作用和节点吸引力研究[J].北京大学学报(自然科学版),2017,53(5):862-872.
• [9] GIRARDIN F,DAL FIORE F,BLAT J,et al.Understanding of tourist dynamics from explicitly disclosed location information[A].Symposium on LBS and Telecartography[C].2007.58.
• [10] CHUA A,SERVILLO L,MARCHEGGIANI E,et al.Mapping Cilento:Using geotagged social media data to characterize tourist flows in southern Italy[J].Tourism Management,2016,57:295-310.
• [11] ANDRIENKO G,ANDRIENKO N,BOSCH H,et al.Thematic patterns in georeferenced tweets through space-time visual analytics[J].Computing in Science & Engineering,2013,15(3):72-82.
• [12] HASNAT M M,HASAN S.Identifying tourists and analyzing spatial patterns of their destinations from location-based social media data[J].Transportation Research Part C:Emerging Technologies,2018,96:38-54.
• [13] YANG L Y,DURARTE C M.Identifying tourist-functional relations of urban places through Foursquare from Barcelona[J].GeoJournal,2021(86):1-18.
• [14] MANNIK L,MCGARRY K.Practicing Ethnography:A Student Guide to Method and Methodology[M].Toronto:University of Toronto Press,2017.
• [15] SUN Y,FAN H C,HELBICH M,et al.Analyzing human activities through volunteered geographic information:Using Flickr to analyze spatial and temporal pattern of tourist accommodation[A].Progress in Location-Based Services[C].Springer,Berlin,Heidelberg,2013.57-69.
• [16] 陈子豪，张毅，刘瑜，等.基于社交媒体感知城市旅游活动类型——以苏州市为例[J].地理与地理信息科学，2020,36(2):54-61.
• [17] SHAO H,ZHANG Y,LI W W.Extraction and analysis of city′s tourism districts based on social media data[J].Computers,Environment and Urban Systems,2017,65:66-78.
• [18] GU Z H,ZHANG Y,CHEN Y,et al.Analysis of attraction features of tourism destinations in a mega-city based on check-in data mining—A case study of ShenZhen,China[J].ISPRS International Journal of Geo-Information,2016,5(11):210.
• [19] PENG X,BAO Y,HUANG Z.Perceiving Beijing′s "city image" across different groups based on geotagged social media data[J].IEEE Access,2020,8:93868-93881.
• [20] 新浪微博数据中心.2016微博用户发展报告[EB/OL].https://data.weibo.com/report/file/view?download_name=3b895b5c-6010-f5fb-8001-a1e9d14d7bc4&file-type=.pdf,2016-12-31.
• [21] 北京市人民政府.北京市国民经济和社会发展第十三个五年规划纲要[EB/OL].http://www.beijing.gov.cn/gongkai/guihua/wngh/qtgh/201907/t20190701_99981.html,2016-12-31.
• [22] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
• [23] MOHRI M,ROSTAMIZADEH A,TALWALKAR A.Foundations of Machine Learning[M].MIT press,2018.
• [24] GAURAHA N.Stability feature selection using cluster representative lasso[A].International Conference on Pattern Recognition Applications and Methods[C].2016,2:381-386.
• [25] ANSELIN L.Local indicators of spatial association-LISA[J].Geographical Analysis,1995,27(2):93-115.
• [26] TOBLER W R.A computer movie simulating urban growth in the Detroit region[J].Economic Geography,1970,46(sup1):234-240.
• [27] SALTON G,MCGILL M J.Introduction to Modern Information Retrieval[M].Mcgraw-hill,1983.
• [28] JAIN A K,MURTY M N,FLYNN P J.Data clustering:A review[J].ACM Computing Surveys (CSUR),1999,31(3):264-323.
• [29] TAN P N,STEINBACH M,KUMAR V.Introduction to Data Mining[M].Pearson Education India,2016.
• [30] ROUSSEEUW P J.Silhouettes:A graphical aid to the interpretation and validation of cluster analysis[J].Journal of Computational and Applied Mathematics,1987,20:53-65.
• [31] DAVIES D L,BOULDIN D W.A cluster separation measure[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1979(2):224-227.
• [32] CALIN′ SKI T,HARABASZ J.A dendrite method for cluster analysis[J].Communications in Statistics-Theory and Methods,1974,3(1):1-27.
• [33] WANG Y D,GU Y Y,DOU M X,et al.Using spatial semantics and interactions to identify urban functional regions[J].ISPRS International Journal of Geo-Information,2018,7(4):130.