Combined GIS Based Spatial-Temporal Analysis Using Social Media Data of Wuhan, China

Abstract

The development and growth of Internet technology with geo-location has promoted the development of China's Volunteered Geographical Information (VGI) Services. Twitter-like Sina Weibo has gathered a large number of user check-in data, which contains the geolocation features with temporal information. Weibo data has become a major source of geographic location information, helping to access human to service facilities, social events, disaster activities, and real-estate business. This study selects Wuhan (capital of Hubei province) as the study area and combines the collected micro-blog data (2012-2017), POI data (Hubei Surveying and Mapping Bureau) and OSM road network dataset with remote sensing image data. Through spatial inclusion statistical analysis and Change Detection techniques, time and space of Weibo visit frequency and its influence in major universities and commercial pedestrian streets in Wuhan were carried out. This paper will use the clustering algorithm (K-Means), query analysis technique and density analysis method to generate a time-space density cloud of microblog data for institutes and pedestrian streets to find the socio-economical sites within streets and universities, which is beneficial for realestate business. Both spatial and statistical analysis indicates that the Wuhan University is the university with the highest number of user’s favorite, commentary and content published. All these trend analyses verified through K-mean clustering and change detection techniques to find changes in human mobility patterns of crowds in Wuhan's well-known streets and universities using Google Earth's high-resolution optical



Author Information
Uqba Ramzan, Wuhan University, China
Fan Hong, Wuhan University, China

Paper Information
Conference: ECE2022
Stream: Assessment Theories & Methodologies

This paper is part of the ECE2022 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window


Comments & Feedback

Place a comment using your LinkedIn profile

Comments

Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by amp21