GianlucaVico/NLP-Project

Project for NLP course at DKE, Y2, 2020

NLP-Project

Project for NLP course at DKE, Y2, 2020

Data

This folder contains the dataset used (not uploaded on github)

• Amazon Fine food reviews: https://www.kaggle.com/snap/amazon-fine-food-reviews
• Steam Reviews dataset: https://www.kaggle.com/luthfim/steam-reviews-dataset

Images

This folder contains the graph obtained from training the models.

Models

This folder contains the trained models, except for the Bayes Model and the dummy models.

The models are aviable here: https://drive.google.com/open?id=1LfDWTKfBoNHn1o_Kq40sD8hWTtO3h-b7

StatModel.py

• BayesModel Naive Bayes model to predict the score given a sentence

project.ipynb

Notebook used to process the data, train the models and obtain the output.