In 2021 intense rainfall in Western Europe led to an unprecedented flash flooding that killed many people. Subsequently, the apparent lack of preparation of either authorities or the broader populace became part of the discussion. As knowledge about people’s awareness of a hazard, its impacts, and possible adaptations can improve hazard management, Professor Mirbabaie and his colleagues used social media data to assess situational awareness, sentiments, and behaviour before, during, and after the flood. Here, topics include ‘weather updates’, ‘solidarity, recovery, and aid’, ‘grief and empathy’, and ‘climate change attribution, extreme weather, long-term flood protection measures, and politics’. Besides depending on the phase, many of these topics also depend on the distance from the affected areas. For example, tweets about evacuation (during the peak phase) and damage assessment (during the recovery phase) were particularly prominent near the affected areas. Whereas the high engagement might indicate awareness, the severity of the flood was unexpected. The unprecedented citizen-generated real-time information helps to discuss how rapid automated analysis could contribute to disaster communication and risk mitigation.
