Real-time social media sentiment analysis for rapid impact assessment of floods

Bryan-Smith, Lydia; Godsall, Jake; George, Franky; Egode, Kelly; Dethlefs, Nina; Parsons, Dan

Abstract

Traditional approaches to flood modelling mostly rely on hydrodynamic physical simulations. While these simulations can be accurate, they are computationally expensive and prohibitively so when thinking about real-time prediction based on dynamic environmental conditions. Alternatively, social media platforms such as Twitter are often used by people to communicate during a flooding event, but discovering which tweets hold useful information is the key challenge in extracting information from posts in real time. In this article, we present a novel model for flood forecasting and monitoring that makes use of a transformer network that assesses the severity of a flooding situation based on sentiment analysis of the multimodal inputs (text and images). We also present an experimental comparison of a range of state-of-the-art deep learning methods for image processing and natural language processing. Finally, we demonstrate that information induced from tweets can be used effectively to visualise fine-grained geographical flood-related information dynamically and in real-time.

Citation

Bryan-Smith, L., Godsall, J., George, F., Egode, K., Dethlefs, N., & Parsons, D. (2023). Real-time social media sentiment analysis for rapid impact assessment of floods. Computers & geosciences, 178, Article 105405. https://doi.org/10.1016/j.cageo.2023.105405

• Journal Article Type: Article
• Acceptance Date: Jun 17, 2023
• Online Publication Date: Jun 28, 2023
• Publication Date: Sep 1, 2023
• Deposit Date: Aug 23, 2023
• Publicly Available Date: Aug 24, 2023
• Journal: Computers and Geosciences
• Print ISSN: 0098-3004
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 178
• Article Number: 105405
• DOI: https://doi.org/10.1016/j.cageo.2023.105405
• Keywords: Social media; Sentiment analysis; Flooding; Artificial intelligence
• Public URL: https://hull-repository.worktribe.com/output/4331606