<![CDATA[This study presents a sentiment analysis of user reviews for the Grab application on Google Play Store using both machine learning and deep learning approaches. The objective is to compare the performance of four algorithms—Random Forest, XGBoost, BiLSTM, and IndoBERT—in classifying positive, negative, and neutral sentiments in Indonesian-language texts. The dataset consists of 2,000 user reviews collected through web scraping, followed by preprocessing steps such as case folding, stopword removal, and tokenization. Feature representation was conducted using TF-IDF for machine learning models and word embeddings for deep learning models. The experimental results using 5-fold cross-validation show that IndoBERT achieved the highest accuracy of 91%, followed by Random Forest (88%), XGBoost (88%), and BiLSTM (84%). These results indicate that IndoBERT demonstrates superior capability in capturing the semantic context of Indonesian text, making it the most effective model for sentiment analysis of mobile application reviews written in the Indonesian language.]]>
Copyrights © 2025
