Big Five Factor Based Movie Rate Prediction Using Machine Learning Techniques

Abstract

Predicting ratings make up a big part of our cultural environment, but little research has been done on what such films indicate about our personalities. Using the Big Five-Factor model of personality as a guide, we set out to see if there were any links between film and movie interests and individual personalities. Ratings-based recommender systems may fail to provide ideal levels of diversity, popularity, and serendipity for their users because the type of movie one watches is tied to one’s personality. Individual user’s preferences in recommendation lists for diversity, popularity, and serendipity cannot be inferred just from their ratings. When we incorporate user’s personality qualities into the process of creating recommendations, we can boost user satisfaction. The proposed model can be used to recommend movies to users. In this paper, the dataset having 1834 users with 12 different movie ratings. Then the data set is used to analyze the movie rating based on the individual user personality. The Big Five Factor model algorithm determines an individual’s personality. The experimental result is then analyzed, and it shows that the proposed methodology calculates movie ratings more accurately. Our trials on predicting user enjoyment of movie lists were conducted using a variety of machine learning methods, with LGBM providing the lowest Mean Absolute Error.