The increasing prevalence of social media usage has led to the emergence of mining social media data as a valuable resource for disaster response. Mining their textual data presents opportunities and challenges. Techniques leveraging natural language processing and machine learning extract relevant information while filtering out noise and misinformation. Real-world examples, such as Hurricane Harvey in 2017, demonstrate the value of social media in coordinating relief efforts. Challenges include unstructured and ambiguous data, diverse user credibility, and overwhelming data volume. The aim of this research is to develop a methodology that integrates textual classification of social media data, spatial analysis, and visual analytics to provide rapid responses during natural disasters.
Mining social media data for damage assessment in environmental disasters
Luigi Ippoliti;Lara Fontanella
2023-01-01
Abstract
The increasing prevalence of social media usage has led to the emergence of mining social media data as a valuable resource for disaster response. Mining their textual data presents opportunities and challenges. Techniques leveraging natural language processing and machine learning extract relevant information while filtering out noise and misinformation. Real-world examples, such as Hurricane Harvey in 2017, demonstrate the value of social media in coordinating relief efforts. Challenges include unstructured and ambiguous data, diverse user credibility, and overwhelming data volume. The aim of this research is to develop a methodology that integrates textual classification of social media data, spatial analysis, and visual analytics to provide rapid responses during natural disasters.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.