Towards resilient and smart cities: A real-time urban analytical and geo-visual system for social media streaming data

Cities worldwide are vulnerable to unpredictable extreme events such as disasters and public health crises. Urban big data and data-driven technologies have played an increasingly important role in building smart and resilient cities that can respond rapidly to these perturbations. However, many existing approaches had limited capabilities for processing big data, which has led to time-consuming and costly decision-making. Thus, we develop a real-time data-driven analytical and geo-visual system to enable smart and rapid responses to urban extreme events. The system is built on ArcGIS's GeoEvent Server and Apache Spark and processes streaming data from social media with high speed, massive volume, and multiple modalities. The system employs online topic modeling and domain-adaptive sentiment analysis to track small-scale, undefined events, visualizes their spatial and semantic dynamics, and provides early alerts for crises and emergencies via an interactive online GIS platform. The proposed system has been applied during a large-scale hurricane and demonstrated effectiveness and agility in tracking and reporting emerging small-scale crises. The developed system can be applied in various urban scenarios to enable timely situation awareness and rapid response. This research contributes to the smart city safety and building rapidity of resilient cities.