Twitter has become an important communication channel in times of emergency.
The ubiquitousness of smartphones enables people to announce an emergency they’re observing in real-time.
Because of this, more agencies are interested in programatically monitoring Twitter (i.e. disaster relief organizations and news agencies).
Predict which Tweets are about real disasters and which ones are not using BERT in Tensorflow Keras NLP(natural language processing)
Link to a complete descrition of BERT (Bidirectional Encoder Representations from Transformers):
https://towardsdatascience.com/bert-explained-state-of-the-art-language-model-for-nlp-f8b21a9b6270
Link to tokenisation.py file download : https://raw.githubusercontent.com/tensorflow/models/master/official/nlp/bert/tokenization.py
Link to competition : https://www.kaggle.com/c/nlp-getting-started