NEXTGEN OPINION INTELLIGENCE SYSTEM FOR E-COMMERCE FOOD REVIEW ANALYTICS

Abstract

The exponential growth of e-commerce platforms has led to a substantial increase in online customer reviews, making sentiment analysis an essential tool for understanding consumer opinions and product performance. Amazon food reviews, in particular, provide valuable insights into customer experiences regarding product quality, taste, packaging, and overall satisfaction. Traditional sentiment analysis approaches, such as manual review evaluation and rule-based techniques, often struggle with scalability, efficiency, and accuracy when processing large volumes of unstructured textual data. This research presents a Machine Learning-based framework for automated sentiment prediction of Amazon food reviews using textual features. The proposed system employs advanced Natural Language Processing (NLP) techniques, including text normalization, stopword removal, stemming, lemmatization, punctuation elimination, and noise reduction, to enhance data quality. The processed text data is transformed into numerical feature vectors using the Term Frequency–Inverse Document Frequency (TF-IDF) technique. To identify the most effective classification model, multiple machine learning algorithms are implemented and evaluated, including Multinomial Naïve Bayes (MNB), Support Vector Classifier (SVC), K-Nearest Neighbors (KNN), and Light Gradient Boosting Machine (LightGBM). Comparative performance analysis demonstrates that the LightGBM model achieves superior accuracy and classification performance in multi-class sentiment prediction, making it the proposed model for the system. Furthermore, an interactive Graphical User Interface (GUI) is developed to facilitate dataset uploading, text preprocessing, model training, performance evaluation, visualization, and sentiment prediction for unseen reviews. The proposed framework provides an efficient, accurate, and scalable solution for automated sentiment analysis, enabling businesses and consumers to derive meaningful insights from large-scale Amazon food review data.