A prediction program that classifies tweets into ones which announce a disaster and others which do not. The program implements supervised learning using the multinomial naive Bayes classifier, a probabilistic and generative classifier. To deal with unseen events, Laplace smoothing has been implemented.
The data has been taken from here. Displaying the code and the data publicly here is in compliance with the rules of the competition.
The code has been tested on Python 3.9.5.