A machine learning model that predicts which Tweets are about real disasters and which one’s aren’t
Three different models were considered for the task and hyperoptimized to achieve local optimizations Afformentioned models were; BERT, LSTM, and a simple base model.
Full report visible at https://docs.google.com/document/d/1rkA6aIAxDM6_v-bl2n-GwHFqFl_6oLgaOYnB9hJtXGU/edit?usp=sharing