Text Analytics for Resilience-Enabled Extreme Events Reconnaissance
This research aims to improve the efficiency and accuracy of post-hazard reconnaissance for engineers and disaster response teams by automating data collection and report generation.
This study applies natural language processing (NLP) to automate data collection from news and social media for post-hazard reconnaissance, focusing on generating reports and extracting recovery times. The results show promise for improving the accuracy and efficiency of natural hazard reconnaissance.
Post-hazard reconnaissance for natural disasters (e.g., earthquakes) is important for understanding the performance of the built environment, speeding up the recovery, enhancing resilience and making informed decisions related to current and future hazards. Natural language processing (NLP) is used in this study for the purposes of increasing the accuracy and efficiency of natural hazard reconnaissance through automation. The study particularly focuses on (1) automated data (news and social media) collection hosted by the Pacific Earthquake Engineering Research (PEER) Center server, (2) automatic generation of reconnaissance reports, and (3) use of social media to extract post-hazard information such as the recovery time. Obtained results are encouraging for further development and wider usage of various NLP methods in natural hazard reconnaissance.