Analyzing Amazon Products Sentiment: A Comparative Study of Machine and Deep Learning, and Transformer-Based Techniques

• DOI: 10.3390/electronics13071305
• Publication Date: 2024-03-31T17:28:00Z
• Authors: Hashir Ali; Ehtesham Hashmi; Sule Yayilgan Yil...; Sarang Shaikh
• Keywords: Sentiment Analysis

In recent years, online shopping has surged in popularity, with customer reviews becoming a crucial aspect of the decision-making process. Reviews not only help potential customers make informed choices, but also provide businesses valuable feedback and build trust. this study, we conducted thorough analysis Amazon dataset, which includes several product categories. Our primary objective was to accurately classify sentiments using natural language processing, machine learning, ensemble deep learning techniques. research workflow encompassed steps. We explore data collection procedures; preprocessing steps, including normalization tokenization; feature extraction, utilizing Bag-of-Words TF–IDF methods. experiments employing variety algorithms, Multinomial Naive Bayes, Random Forest, Decision Tree, Logistic Regression. Additionally, harnessed Bagging as an technique. Furthermore, explored learning-based such CNNs, Bidirectional LSTM, transformer-based models, like XLNet BERT. comprehensive evaluations, metrics accuracy, precision, recall, F1 score, revealed that BERT algorithm outperformed others, achieving impressive accuracy rate 89%. This provides insights into sentiment reviews, aiding both consumers making decisions enhancing service quality.