WATERSensing: A smart warning system for natural disasters in Spain

Floods are expected to increase in the coming years due to global warming. The early identification of water-based disasters can be life-saving, and the challenge is to identify appropriate and timely warning measures. Social media tools such as Twitter provide citizens with a real-time communication channel for reporting problems related to our environment, which allows humans to act as social sensors. In this paper, we show the main results and lessons learned from the research project WATERoT, funded by the Spanish government. In this project, we designed a social sensing application (called WATERSensing) for the prevention and evaluation of water-related disasters with the participation of individuals through social networks. This tool crawls micro-texts from different social networks such as Twitter, RSS feeds or Telegram, that are analyzed with natural language processing (NLP) techniques. A case study of Storm Gloria, a Mediterranean storm that heavily affected eastern Spain last January 2020, is presented to evidence that the system can correlate data from social media with actual events. We demonstrate that the analysis of different sources of information opens up new opportunities in the development of warning-systems for the prevention, early identification, and management of natural disasters.