Note that this is a Natural Language Processing (NLP) dataset, so you are expected to do extensive research on how to tackle NLP problems. Here are some hints to guide you -

- Analyze the text data and perform appropriate preprocessing steps such as text cleaning, tokenization, or stemming/lemmatization. 
- You can create features using basic techniques like Bag of words or TF-IDF.
- The above two steps will affect your model performance a lot, so do play around with different preprocessing techniques and feature engineering hyperparameters.
- This is a multi-class classification problem. The class distribution might be skewed towards higher ratings (1-star ratings are always rare). How would you tackle class imbalance? 
- Remember that you don't have test data labels. Use validation techniques to test your model before submitting on Kaggle.
- Lastly, this is a fairly large dataset. Don't waste time by running time-consuming code again and again. Save your preprocessed data and read about saving models with pickle.

Best of Luck!