GIBD develops a Big Geo-social Data Computing platform that includes a set of innovative parallel processing algorithms, spatiotemporal indexes, and query analytical tools to efficiently manage, analyze and visualize massive amounts of geotagged tweets(geo-tweets) and other big data. With the platform, billions of tweets can be queried, extracted, and visualized within seconds based on the criteria of spatial regions, keywords, time period, and spatial resolutions.
We have been streaming geo-tweets for the whole world since 2015 using the official Twitter Streaming API. Several millions of geo-tweets are being collected on a daily basis. Big geo-tweets coupled with the innovative spatial computing platform offer enormous opportunities for disaster management by examining the physical infrastructure (e.g., road damage), environment (e.g., flood extent), and nature-human interaction (e.g., evacuation) from spatial, temporal, and social dimensions.
The figure below shows the information that can be extracted from geotagged social media (e.g., Twitter) data for supporting different applications.
The screenshot below shows one of the tools we developed to support exploratory analysis of billions of tweets in near real-time. Such a tool is useful for gaining an initial understanding of an event (e.g. Hurricane Matthew) in the Twitter world by exploring the spatiotemporal patterns of the relevant tweets.
Spatial and temporal distribution of Hurricane Matthew-related tweets in the continental U.S. from October 1 to October 20, 2016.