In this project my aim is to build a supervised machine learning model able to classify movie reviews into positive or negative, by extracting information from the text of the review. This task is known as Sentiment Analysis, where a program must identify the sentiment of a text. My data has been downloaded from [ Kaggle (https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews), however, the original data is available here. i Have split data into 3 groups: - training data: 30,000 reviews annotated with positive and negative labels; - validation data: 10,000 reviews annotated with positive and negative labels; - test data: 10,000 reviews un-labelled which i will predict labels for using machine learning.
Made During a Headstart Course at Sheffield University
See .ipynb file for more