Product Sentiment Analysis for Amazon Reviews

Abstract

Recently, Ecommerce has Witnessed Rapid Development. As A Result, Online Purchasing has grown, and that has led to Growth in Online Customer Reviews of Products. The Implied Opinions in Customer Reviews Have a Massive Influence on Customer's Decision Purchasing, Since the Customer's Opinion About the Product is Influenced by Other Consumers' Recommendations or Complaints. This Research Provides an Analysis of the Amazon Reviews Dataset and Studies Sentiment Classification with Different Machine Learning Approaches. First, the Reviews were Transformed into Vector Representation using different Techniques, I.E., Bag-Of-Words, Tf-Idf, and Glove. Then, we Trained Various Machine Learning Algorithms, I.E., Logistic Regression, Random Forest, Naïve Bayes, Bidirectional Long-Short Term Memory, and Bert. After That, We Evaluated the Models using Accuracy, F1-Score, Precision, Recall, and Cross-Entropy Loss Function. Then, We Analyized The Best Performance Model in Order to Investigate Its Sentiment Classification. The Experiment was Conducted on Multiclass Classifications, Then we Selected the Best Performing Model And Re-Trained It on the Binary Classification.