Predicting floods with Flickr tags

• Published in: PloS one Vol. 12; no. 2; p. e0172870
• Main Authors: Tkachenko, Nataliya, Jarvis, Stephen, Procter, Rob
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 24.02.2017; Public Library of Science (PLoS)
• Subjects: Analysis; Computer and Information Sciences; Cyclonic Storms; Data Collection; Digital media; Disaster Planning; Disasters; Earth Sciences; Earthquakes; Ecology and Environmental Sciences; Environmental aspects; Environmental hazards; Environmental Monitoring - methods; Flood predictions; Flooding; Floods; Geography; Humans; Hurricanes; Hydrologic data; Internet; Management; Metadata; Natural disasters; Nowcasting; Outbreaks; Photography; Physical Sciences; Research and Analysis Methods; Risk Assessment - methods; Sensors; Social Media; Social networks; Social Sciences; Tags; User generated content; United Kingdom > UK; New York; United States > US
• DOI: 10.1371/journal.pone.0172870
• ISSN: 1932-6203

Increasingly, user generated content (UGC) in social media postings and their associated metadata such as time and location stamps are being used to provide useful operational information during natural hazard events such as hurricanes, storms and floods. The main advantage of these new sources of data are twofold. First, in a purely additive sense, they can provide much denser geographical coverage of the hazard as compared to traditional sensor networks. Second, they provide what physical sensors are not able to do: By documenting personal observations and experiences, they directly record the impact of a hazard on the human environment. For this reason interpretation of the content (e.g., hashtags, images, text, emojis, etc) and metadata (e.g., keywords, tags, geolocation) have been a focus of much research into social media analytics. However, as choices of semantic tags in the current methods are usually reduced to the exact name or type of the event (e.g., hashtags '#Sandy' or '#flooding'), the main limitation of such approaches remains their mere nowcasting capacity. In this study we make use of polysemous tags of images posted during several recent flood events and demonstrate how such volunteered geographic data can be used to provide early warning of an event before its outbreak.