Analysis of Sentiments in Movie Reviews using Supervised Machine Learning Technique

Abstract

Nearly all high-flying branches of machine learning technique is sentiment analysis. A mechanism text summarization process is used determine to decide that document's author's intent. This article proposes to implement and test a system for the automated sentiment analysis of film reviews. In comparison to other studies that foe us solely on sentimental orientation (Positive versus negative), the proposed approach conducts fine-grained research to evaluate both the viewer's sentimental orientation and sentimental intensity against different facets of the film. This article presents an evaluation of the outcome achieved by applying Variational Forest, XGBoost, Linear Regression, Naive Bayes (NB), Maximum Entropy, and Vector Support Machine (SVM). The experimentation shows that by providing lofty dynamic factors to the film, acting, and storyline facets of a film, we achieved the maximum accurateness in the study of the film reviews.