From Reviews to Results: Leveraging Amazon Feedback for Product Evolution

This study explores the efficacy of Bidirectional Encoder Representations from Transformers (BERT) in accurately classifying customer sentiment within Amazon product reviews. To determine if BERT surpasses traditional sentiment analysis methods (Logistic Regression, TF-IDF, Random Forest, Naive Bayes, SVM) in understanding and classifying customer opinions expressed in Amazon reviews. By leveraging BERT's contextual understanding, the research aims to overcome the limitations of traditional methods. The performance of each model will be evaluated using metrics such as accuracy, precision, recall, and F1-score. The expected outcomes are advancements in sentiment analysis techniques, valuable insights for businesses to leverage customer feedback for improved product development and encourage wider adoption of sentiment analysis across various industries.