<![CDATA[This study aims to examine user opinion tendencies toward Gojek services by integrating Random Forest and K-Means Clustering approaches. The dataset consists of 15,000 user reviews collected throughout 2025 using web scraping techniques. The initial stage focuses on data preprocessing, including text cleaning, case normalization, tokenization, removal of non-informative stop words, and lemmatization to restore words to their base forms. Subsequently, sentiment labels are assigned using a lexicon-based approach. The next phase involves classification modeling through Random Forest to identify sentiment tendencies, while K-Means Clustering is employed to uncover latent patterns within the opinion data. The findings indicate that the Random Forest model achieves an accuracy level of 0.878, demonstrating strong performance in distinguishing positive and negative sentiments, as reflected by f1-scores of 0.932 and 0.818, respectively. However, the model shows limitations in consistently identifying neutral sentiment. In contrast, the implementation of K-Means Clustering successfully categorizes the data into three primary clusters, providing a more structured representation of user opinion characteristics. Overall, these results offer empirical insights that can serve as a strategic reference for enhancing the quality of Gojek’s service delivery.]]>
Copyrights © 2026
