Movie Review Analysis

This project was done as part of the coursework for CS6120: Natural Language Processing.

Dataset

1. IMDb 50k movie reviews dataset released by Stanford
2. Reviews of The Shawshank Redemption scraped from IMDb using Selenium

Complete EDA of the above datsets can be found here.

Check out 3-min summary of the movie for better understanding of the results.

Two kinds of analysis were performed on the reviews of the movie, The Shawshank Redemption:

1. Sentiment Analysis

• Traditional supervised ML models with BOW and TFIDF vector representations
  • Naive Bayes
  • Decision Trees
  • Random Forest
• Deep Learning models like LSTM and RNN

2. Topic Modelling

• LDA with BOW and TFIDF vector representations.
• NMF with BOW and TFIDF vector representations.

Code for them can be found in jupyter notebooks inside their respective folders.