Movie Recommendation System With Sentiment Analysis Rating

Abstract

Abstract: People’s desires, trends, and interests change in tandem with how the world is changing. People like to see movies based on their interests, and this is also true in the movie industry. There are a lot of web-based movie service providers now, and they aim to keep their members entertained in order to grow their clientele and notoriety. The service provider could suggest movies that customers would enjoy in order to increase business by giving them an excuse to view more entertaining movies. Customers are likely to renew the web-based movie service provider application on a regular basis if this is done. The aim of this project is to develop a machine learning-driven movie recommendation system that can suggest films to users based on their ratings and areas of interest. In order to do this, collaborative filtering is utilized to calculate features based on user and movie information, and content-based filtering is used to recommend movies based on movie-movie similarity. To increase performance, the suggested system makes advantage of the novel ensemble learning algorithm, XGBoost. Keywords– Natural Language Processing (NLP), Machine Learning (ML), Machine Learning, Recommendation System, Content based filtering, Collaborative filtering, sentiment analysis.