Sentiment analysis of Indonesian e-commerce product reviews using machine learning classifiers

Abstract

The rapid growth of e-commerce in Indonesia has generated a massive volume of user-generated content in the form of product reviews. This textual data is a rich resource for businesses to understand customer satisfaction and product performance. This study aims to perform sentiment analysis on Indonesian e-commerce product reviews to automatically classify them into positive and negative sentiments. A publicly available dataset of Indonesian marketplace product reviews was utilized. The methodology involved text preprocessing steps, including case folding, tokenization, stopword removal, and stemming, followed by feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF). Two common machine learning classifiers, Naïve Bayes and Support Vector Machine (SVM), were trained and evaluated on the dataset. The performance of the models was measured using accuracy, precision, recall, and F1-score. The results indicate that the Support Vector Machine (SVM) classifier achieved a higher accuracy of 89.5% compared to the Naïve Bayes classifier, which achieved an accuracy of 84.2%. These findings demonstrate the effectiveness of machine learning techniques in analyzing consumer sentiment in the Indonesian language, providing a valuable tool for market intelligence and business decision-making.