This project contains the code used for training and inference of the news classifier. It also includes the model weights in news_classifier.h5.

The dataset is not included in this GitHub repository. The model was trained on the titles of labeled news articles, not the content.

The NLP used in this project is old. Modern architectures like BERT, which utilizes SOTA tools like transformers, would have performed much better in this task.

That said, this project was an enlightening view into hands-on NLP and working with a real dataset from Kaggle.