Twitter for disaster relief through sentiment analysis for COVID-19 and natural hazard crises

In emergencies and disasters, large numbers of people require basic needs and medical attention. In such situations, online social media comes as a possible solution to aid the current disaster management methods. In this paper, supervised learning approaches are compared for the multi-class classification of Twitter data. A careful setting of Multilayer Perceptron (MLP) network layers and the optimizer has shown promising results for classification of tweets into three categories i.e. ?resource needs?, ?resource availability?, and ?others? being neutral and of no useful information. Public data of Nepal Earthquake (2015) and Italy Earthquake (2016) have been used for training and validation of the models, and original COVID-19 data is acquired, annotated, and used for testing. Detailed data analysis of tweets collected during different disasters has also been incorporated in the paper. The proposed model has been able to achieve 83% classification accuracy on the original COVID-19 dataset. Local Interpretable Model-Agnostic Explanations (LIME) is used to explain the behavior and shortcomings model on COVID-19 data. This paper provides a simple choice for real-world applications and a good starting point for future research.

Automated summary

This paper explores the use of online social media for disaster management and compares supervised learning approaches for the classification of Twitter data. Results show that certain settings of Multilayer Perceptron network layers and optimizers can effectively classify tweets in different disaster scenarios, achieving 83% classification accuracy on the COVID-19 dataset. The study also uses Local Interpretable Model-Agnostic Explanations (LIME) to explain the model's behavior and limitations on COVID-19 data.