When disaster strikes, social media can be a double-edged sword – both a way for people to communicate instantaneously and without extra barriers, but also filled with platforms rife with either deliberate or unintentional misinformation. Researchers at McGill University’s Department of Geography studied ways to cut through the amplification of false data by using deep learning (a subset of artificial intelligence) and social network analysis to examine over 1,200 tweets around the March 2019 Nebraska floods, according to Canadian Geographic.
““Social network analysis can identify where people get their information during an extreme weather event. Deep learning allows us to better understand the content of this information by classifying thousands of tweets into fixed categories, for example, ‘infrastructure and utilities damage’ or ‘sympathy and emotional support’,” said Renee Sieber, associate professor in McGill’s Department of Geography and lead author of the study in a media release from McGill.
Sieber and her team also discovered challenges in universal language and terminology used to describe and categorize disasters, which can hinder emergency management and crisis personnel responding to events. “Our findings tell us that information content varies between different types of events, contrary to the belief that there is a universal language to categorize crisis management; this limits the use of labelled datasets on just a few types of events, as search terms may change from one event to another,” said Sieber in the release.
Source:
