Disaster Related Tweets Analysis with Machine Learning Approaches

Abstract

It's no secret that the microblogging service Twitter (X) has quickly risen to prominence as one of the most reliable places to get the latest updates on breaking events. Tweets, Twitter's information streams, are sent out voluntarily by registered users and can reach even non-registered users, often before more conventional sources of mass news. In this research, we use machine learning to create models that can find helpful tweets on disasters automatically. Social media users provide massive amounts of data during natural catastrophe situations, some of which are useful for relief operations and emergency management. In this work, we analyze the material shared on social media during two hurricanes and one earthquake. This research has shown a machine-learning approach to categorizing tweets in relation to disasters and labeling Twitter data. This study has applied five machine learning algorithms to predict disaster and nondisaster tweets. In our model and among these five machine learning algorithms three perform similarly, but Logistic Regression has achieved the best 80.5% model accuracy among all other algorithms.