Harnessing Social Media for Natural Disaster Detection

As a pivotal resource, social media facilitates the identification of disasters through content created by users. This content is frequently abundant and open to interpretation, underscoring the pivotal role of artificial intelligence in categorizing disaster-related information to bolster efficient response systems. In our study, we leveraged about 5400 tweets from the CrisisLEX-T26 dataset, conducting both binary and multiclass classification tests to enhance the research outcomes. We have compared the performance of various PLM-based models tailored to this dataset.In our pursuit of effective disaster detection, we propose two approaches. First, our PLM-BiLSTM-CNN model integrates PLMs, Bidirectional Long Short-Term Memory (BiLSTM), and Convolutional Neural Networks (CNN), enabling disaster detection with commendable results: an 88.14% F1-Score in multiclass classification and a 90.83% F1-Score in binary classification. In the second approach, we fine-tune PLMs using our considered dataset and utilize their outputs as an initial input for our PLM-BiLSTM-CNN model. This sequential process enhances disaster detection capabilities by harnessing the strengths of both fine-tuned PLMs and our PLM-BiLSTM-CNN architecture.