Hello everyone! This notebook represents my submission to the Natural Language Processing with Disaster Tweets competition from Kaggle. The task was to create a machine learning model that can identify which Tweets are about real disasters and which aren't. For this purpose, a dataset of 10,000 Tweets classified by hand was provided.
This notebook also offers a quick introduction on how to use HuggingFace transformers. The main lines of code related to transformers will be discussed in detail. I don't go very in depth with the data analysis, but if you're interested you can check this notebook: https://www.kaggle.com/code/gunesevitan/nlp-with-disaster-tweets-eda-cleaning-and-bert. Enjoy coding!