This is a mini project based on an NLP Kaggle Challenge for an IMDB movie review set. Was able to get to 85% accuracy.
The Challenge:- To preprocess the IDMB movie review datasets in any way you find suitable and build your own ML model that can predict the sentiment of movie reviews. Train your model on the first 20000 reviews (with their sentiment as the target variable). The goal is to determine whether a given movie review has a positive or negative sentiment. https://www.kaggle.com/c/word2vec-nlp-tutorial/overview
The python code has been attached. The given datasets are also attached. There is a result analysis report that has also been attached with a detailed explanation of the reasons for choosing some ML models and different steps.