Using artificial intelligence to identify emergency messages on social media during a natural disaster: A deep learning approach

• Published in: International journal of information management data insights Vol. 3; no. 1; p. 100164
• Main Authors: Powers, Courtney J., Devaraj, Ashwin, Ashqeen, Kaab, Dontula, Aman, Joshi, Amit, Shenoy, Jayanth, Murthy, Dhiraj
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2023; Elsevier
• Subjects: Artificial intelligence; Computational methods; Crisis communication; Disaster; Machine learning; Supervised learning; Twitter; Computational methods; Supervised learning; Machine learning; Twitter; Disaster; Artificial intelligence; Crisis communication
• ISSN: 2667-0968; 2667-0968
• DOI: 10.1016/j.jjimei.2023.100164

•Curates a geographical-based dataset of tweets sent during Hurricane Harvey.•Presents a labeling scheme for relevance and urgency of tweets during a disaster.•Uses artificial intelligence and deep learning to identify calls for help on Twitter.•Develops machine-learning classifiers for signaling first responders of urgent tweets.•Shows effectiveness of using pre-trained language models such as BERT and XLNet. During natural disasters, emergency communication systems become overloaded, and people are forced to turn to social media to make requests for help. This study employs machine learning and artificial intelligence to automatically detect, identify, and categorize tweets relevant to first responders during Hurricane Harvey. We curate a dataset of tweets, present a labeling scheme based on relevance and urgency, and develop neural and non-neural machine learning models to automatically categorize tweets. Our best relevance classifiers, language models BERT and XLNet, perform significantly better than non-neural models and the deep convolutional neural network (CNN) and achieve comparable F1 scores. Ultimately, this study furthers machine learning and crisis communication research by developing methods to automatically categorize tweets that can signal to first responders of individuals’ requests for help in urgent, life-threatening disasters. Our work also finds large pretrained language models promising for the development of well-performing disaster tweet classifiers in future work.