Rating-Based Sentiment Analysis on Online Mobile Reviews Using VADER Preprocessing

Online shopping is rapidly increasing nowadays. As a reason when we are going to purchase any kind of item through an e-commerce site, we are always concerned about the reviews and ratings of the product that we are going to purchase. Naturally, review analysis has become very important in today’s era. The reviews are nothing but the opinions which are given by the user who purchased the item. So, opinion classification is very much trending. So, sentiment analysis from the opinion is a very much challenging issue in current days. Sentiment can be classified into different scales that can be good, bad, neutral, etc. and if we are also looking forward to the rating of the products, we are also looking forward to thoughts or judgment and likes or dislikes or other feelings and emotions are there. The dataset was collected from the Kaggle website based on a review of the mobile of Amazon (Rambocas and Gama in Marketing research: The role of sentiment analysis, Universidade do Porto, Faculdade de Economia do Porto, 2013) As Machine Learning (ML) is evolved, here we are going to use ML techniques such as ‘Naïve Bayes’, ‘Decision Tree’, ‘Random Forest’, ‘KNN’, and ‘Logistic Regression’ (Rambocas and Gama in Marketing research: The role of sentiment analysis, Universidade do Porto, Faculdade de Economia do Porto, 2013) for the rating and feature-based sentiment analysis on mobile reviews of Amazon website. Here we are going to use NLP and ML-based techniques to find out the review. So that users can easily buy the product from the analysis. The study verifies the effectiveness of the VADER tool by comparing it with manual tagging. The main contributions of this study are that it extracts the sentiment efficiently, achieves 92% accuracy with a decision tree, and gives practical insights to improve and understand public opinions.