Comparison of Sentiment Analysis Algorithms with SMOTE Oversampling and TF-IDF Implementation on Google Reviews for Public Health Centers

Abstract

Sentiment analysis, or opinion mining, is a key area of natural language processing that identifies sentiments in free text. As digital business services grow and user-generated content increases, analyzing sentiments in online reviews is vital for enhancing business operations and customer satisfaction. This study focuses on sentiment analysis of user reviews from Google Reviews for Public Health Centers (PHCs) in Bali, Indonesia, using five machine learning models: Logistic Regression, Support Vector Machine (SVM), XGBoost, Naive Bayes, and Random Forest. These models classified sentiments into positive and negative categories using a dataset balanced with SMOTE to improve accuracy. We divided a total of 1.834 reviews, using 20% for testing and 80% for training, to ensure a thorough evaluation under real-world conditions. Logistic Regression and Naive Bayes performed best, both achieving an accuracy of 0.89, with Logistic Regression providing a balanced precision and recall. The study enhances academic understanding of sentiment analysis in healthcare and offers insights for business administrators on handling online customer feedback. The findings stress the importance of choosing suitable machine learning techniques based on specific data characteristics and project requirements to optimize both technological and business outcomes.