Bridging the Gap: A Case Study of Integrating Social Media Big Data with Geography

Integrating social media data with geography can offer great potential for understanding the urban dynamics in real-time. However, traditional GIS systems are limited in processing large-scale datasets. The objective of this work is to develop methods to effectively merge these two crucial data sources using advanced geospatial data science and high performance computing. In our case study, we merged 10 Billion Geotweets with about 8.18 Million census blocks in the U.S. Our work creates the most geographically detailed Geotweets dataset, and visualizes it within fine-grained geographic units.

Authors: Devika Jain, Xiaokang Fu, Jack Hayes