Predictive qualities of social media discovered
21 Mar 2017 by Evoluted New Media
Social media has been found to be effective at predicting hurricanes, storms and floods before they occur.
Social media has been found to be effective at predicting hurricanes, storms and floods before they occur.
Scientists from the University of Warwick analysed posts of photo-sharing website Flickr, and found words such as river, water and landscape signalled weather risks developing in specific locations. The researchers say these types of words can act as social sensors when used alongside physical meteorological sensors.
Nataliya Tkachenko, from the Warwick Institute for the Science of Cities, said: “Our analysis demonstrates that metadata in social media image postings enables them to be used as ‘social sensors’, which can serve as a valuable supplement to instrument-based systems for predicting and monitoring floods, and other kinds of natural hazards. The opportunities represented by these new data sources are truly exciting as they can help to protect homes, save lives and design more resilient cities”
Physical sensors have been used traditionally to detect extreme weather events, such as floods, but their scope is limited. They are unable to accurately cover each specific area that could be affected in the same way that people on social media could. The study, funded by the Engineering and Physical Science Research Council, was published in PLOS One.
