Aspect-based Sentiment Analysis of IMDb Movie Reviews Using Machine Learning Techniques

Abstract

ABSTRACT Among the ever-growing field of Internet movie reviews, one cannot stress the significance of Internet movie reviews. As digital channels grow, reviews have become an increasingly potent insight into the opinions of viewers, cultivating the narrative surrounding films and impacting the choices made by consumers, studios, and directors alike. The objective of this study is to analyze and assess the sentiments connected to particular aspects or features of movies by using an Aspect-Based Sentiment Analysis (ABSA) technique using IMDb movie reviews. Using machine learning techniques, the trained model classifies movie aspects such as kid-friendliness, character development, directing, acting, story, and music, then categorizes the sentiment connected to each movie aspect. This research executes aspect-based sentiment analysis using sophisticated machine learning models such as Multinomial Naïve Bayes (MNB), Logistic Regression (LR), Support Vector Machines (SVM), KNNeighbors (KNN), Random Forest (RF), Gradient Boosting Machines (GBM) and Multilayer Perceptron (MLP) on a dataset that includes a wide range of user evaluations. The outcomes of this study offer insightful information about the advantages and disadvantages of films from the viewpoint of the audience, which helps filmmakers improve their work and empowers audiences to make wise choices. Additionally, the study looks into how different movie aspects could affect overall user fulfilment, providing insight into those aspects that have a significant impact on the opinions of the audience. This study contributes to the field of sentiment analysis while also offering filmmakers and movie enthusiasts a valuable tool to help them better comprehend the complex dynamics found in IMDb movie reviews and develop a greater appreciation for the richness of cinematic experiences.