Determining Impact Scores of Tweets in Turkish at Disaster Times

Abstract

AbstractNatural disasters, particularly earthquakes, occur frequently and result in significant damage in Türkiye. Addressing the challenges that emerge in the aftermath of such events is of paramount importance. This study presents a system designed to ...This graphical abstract shows how earthquake-related tweets from Türkiye are analysed. First, they are classified by a large language model as urgent, related, and other. Then the urgent and related ones are sent to an impact calculator that produces an ...Practical ApplicationsThis study shows how social media messages can be turned into a powerful tool for disaster response. After major events such as the February 2023 earthquakes in Türkiye, thousands of tweets were shared, but it is difficult for ...