Model Matematika Hibrida Lexicon–Harris Hawks Optimization untuk Analisis Sentimen Ulasan Produk Shopee

Abstract

This research presents a hybrid Lexicon–Harris Hawks Optimization (HHO) mathematical model designed to improve sentiment analysis performance on Shopee product reviews. The rapid growth of e-commerce platforms has resulted in a large volume of user-generated content, making accurate sentiment classification essential for understanding customer opinions. Traditional lexicon-based methods are simple and interpretable but often limited by static sentiment scores that fail to capture contextual nuances in real-world review data. To overcome these limitations, this study integrates a lexicon-based scoring approach with HHO to dynamically optimize sentiment weights and enhance classification accuracy. The proposed method involves four main stages: data preprocessing, baseline lexicon-based sentiment scoring, lexicon weight optimization using HHO, and final sentiment classification. HHO is employed to search for optimal lexicon weight configurations through exploration and exploitation mechanisms modeled after the cooperative hunting behavior of Harris hawks. The optimized weights are then applied to recalculate sentiment scores and classify reviews into positive, negative, or neutral categories. Performance is evaluated using accuracy, precision, recall, and F1-score. Experimental results show that the hybrid model significantly outperforms the baseline lexicon method, achieving near-perfect classification performance. The confusion matrix reveals extremely low misclassification rates, while evaluation metrics exceed 90% across all categories. The convergence curve further demonstrates stable and efficient optimization behavior. Analysis of sentiment score outputs indicates improved sensitivity for both positive and negative expressions, as well as more accurate representation of reviewer intent.