摘要
为了提取和分析中国上海的社交网络位置数据,通过使用KDE作为空间分析技术来探讨LBSN数据的应用,分析用户参与的新浪微博签到数据与城市特征之间的关系,更重要的是调查上海密集地区的人口密度,以便于相关部门更好地观察和管理。通过使用新浪微博API收集了中国上海10个不同地区在2016年1月~3月期间的数据,并利用核密度估计对基于位置社交网络数据集的新浪微博用户的签到频率进行分析。研究结果表明,核密度估计方法为利用地理空间数据集进行空间模式建模提供了有益的见解。此外,与研究区域的副城区相比,中心城区的密度更大。由此得出结论:通过使用核密度估计技术,可以评估个体的签到行为以及更广泛的总体人口模式。该研究对城市功能及其环境影响、城市可持续性发展和基于城市人口密度的应急响应等领域都有一定的借鉴意义。
To extract and analyze the check-in patterns of location-based social network data in Shanghai,China,the study explores the applications of LBSN data by using KDE as spatial analysis technique to analyze the association between Sina-Weibo check-in data based on user participation and the city’s characteristics,and more importantly investigate the density of more crowded places in Shanghai for better management and observation for the relevant authorities.In the current study,the data is gathered from Sina-Weibo during January to March 2016 in 10 different districts of Shanghai,China using an API,and Kernel Density Estimation is utilized to analyze the check-in frequency of users from location-based social network dataset acquired from Sina-Weibo.The results of the current study show that the Kernel Density Estimation method provide useful insights for modeling spatial patterns using geo-spatial dataset.Furthermore,the city-center is denser as compared to the sub-urban areas in the study area.Finally,the study can conclude that by using Kernel Density Estimation technique we can examine the check-in behavior for an individual as well as broader patterns in population as a whole.This study can be beneficial for in various fields like urban functionalities and its environmental effects,urban sustainability,development and emergency response based on crowed densities within the city.
出处
《电子测量技术》
2019年第21期32-38,共7页
Electronic Measurement Technology
基金
国家自然科学基金(61711530245)
上海市科委项目(18510760300)资助
