A machine learning model to predict article category using some text of the article. Data from BBC News Clssification | Kaggle.
Using LSTM is not effcient for such a small data set, so replaced it with MultinomialNB.
- Data Loading
- Data Cleaning
- Data Preprocessing
- Model Training
- Testing
- 1490 instances
- 3 columns(ArticleId, Article, Category)
- 5 Categories ('business', 'tech', 'politics', 'sport', 'entertainment')