This study aims to propose a novel deep learning (DL)-based framework, iRelevancy, for identifying the disaster relevancy of a social media (SM) message.
It is worth mentioning that a fusion-based DL model is introduced to objectively identify the relevancy of a SM message to the disaster. The proposed system is evaluated with cyclone Fani data and compared with state-of-the-art DL models and the recent relevant studies. The performance of the experiments is assessed by the accuracy, precision, recall, f1-score, area under receiver operating curve and precision–recall curve score.
The iRelevancy leads to a better performance in accuracy, precision, recall, F-score, the area under receiver operating characteristic and area under precision-recall curve, compared to other state-of-the-art methods in the literature.
The predictive performance of the proposed model is illustrated with experimental results on cyclone Fani data, along with misclassifications. Further, to analyze the performance of the iRelevancy, the results on other cyclonic disasters, i.e. cyclone Titli, cyclone Amphan and cyclone Nisarga are presented. In addition, the framework is implemented on catastrophic events of different natures, i.e. COVID-19. The research study can assist disaster managers in effectively maneuvering disasters during distress.
