AI analyses tweets to help figure out flood risks

Scientists from the Joint Research Center, the European Commission's science and knowledge service, have come up with an AI system that could predict flooding using social media data.

In a paper titled Integrating Social Media into a Pan-European Flood Awareness System: A Multilingual Approach the researchers detailed how information shared by social media users can be used to map flood risk areas using natural language processing from posts.

"This integration allows the collection of social media data to be automatically triggered by flood risk warnings determined by a hydro-meteorological model," the paper explained. "Then, we adopt a multi-lingual approach to find flood-related messages by employing two state-of-the-art methodologies: language-agnostic word embeddings and language-aligned word embeddings."

The way the system works is by using Europe's Flood Awareness System (EFAS) to find high flood risk areas. When it finds areas exceeding a specified threshold, crawlers hit Twitter, monitoring 400 keywords to identify posts referring to flooding. It can translate posts in 27 languages spoken in the EFAS area and use these to assess areas affected by flooding or likely to flood within a time period.

This allows rescue workers to be deployed and supplies to be delivered in a timely manner.

"During the development of an event, collected messages could be valuable to international rescue coordinators because they provide insights about the local response, about whether alerts that have been issued by authorities, and about some of the concerns that those affected by a flood or a flood alert may have," the report explained.

"As future research activities, one can envision a global system comprising dozens of languages [and] further steps in the direction of using social media as a data source that can feed into a predictive model."