EventMapper: Detecting Real-World Physical Events Using Corroborative and Probabilistic Sources
This addresses the need for accurate and timely event detection for crisis management, though it builds on existing methods by combining sources.
The paper tackles the problem of real-time global physical event detection by integrating social media and physical sensors, achieving resilience to concept drift and demonstrating applications for landslides, wildfires, and flooding.
The ubiquity of social media makes it a rich source for physical event detection, such as disasters, and as a potential resource for crisis management resource allocation. There have been some recent works on leveraging social media sources for retrospective, after-the-fact event detection of large events such as earthquakes or hurricanes. Similarly, there is a long history of using traditional physical sensors such as climate satellites to perform regional event detection. However, combining social media with corroborative physical sensors for real-time, accurate, and global physical detection has remained unexplored. This paper presents EventMapper, a framework to support event recognition of small yet equally costly events (landslides, flooding, wildfires). EventMapper integrates high-latency, high-accuracy corroborative sources such as physical sensors with low-latency, noisy probabilistic sources such as social media streams to deliver real-time, global event recognition. Furthermore, EventMapper is resilient to the concept drift phenomenon, where machine learning models require continuous fine-tuning to maintain high performance. By exploiting the common features of probabilistic and corroborative sources, EventMapper automates machine learning model updates, maintenance, and fine-tuning. We describe three applications built on EventMapper for landslide, wildfire, and flooding detection.