首页 | 本学科首页   官方微博 | 高级检索  
     

基于社交媒体数据的北京市游客与居民签到差异研究
引用本文:屈树学,董琪,秦嘉徽,刘雨思,张晶. 基于社交媒体数据的北京市游客与居民签到差异研究[J]. 地理与地理信息科学, 2022, 38(1): 37-44. DOI: 10.3969/j.issn.1672-0504.2022.01.006
作者姓名:屈树学  董琪  秦嘉徽  刘雨思  张晶
作者单位: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,北京 100048
基金项目: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)。
摘    要: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。

关 键 词:社交媒体数据  空间分异  机器学习  游客  居民

Study on the Check-in Difference between Touristsand Residentsin Beijing Based on Social Media Data
QU Shu-xue,DONG Qi,QIN Jia-hui,LIU Yu-si,ZHANG Jing. Study on the Check-in Difference between Touristsand Residentsin Beijing Based on Social Media Data[J]. Geography and Geo-Information Science, 2022, 38(1): 37-44. DOI: 10.3969/j.issn.1672-0504.2022.01.006
Authors:QU Shu-xue  DONG Qi  QIN Jia-hui  LIU Yu-si  ZHANG Jing
Affiliation:(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,Beijing 100048,China)
Abstract: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.
Keywords:social media data  spatial differentiation  machine learning  tourists  residents
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号