Sentiment Analysis in Transportation Apps
Sunneng Sandino Berutu, Stephen Anugerah Wau, Haeni Budiati, Jatmika Jatmika · Advances in computational intelligence and robotics book series · 2025
This research investigates the application of Machine Learning in the context of sentiment classification of user reviews on online transportation applications in Indonesia. This research aims to develop a model to accurately classify positive, negative, or neutral sentiments from customer reviews. Review data collected from the Gojek, Grab, and Maxim applications is utilized to train and test Machine Learning models, including natural language processing (NLP) techniques to extract significant features. Sentiment analysis results show that approximately 63.1% have negative sentiment reviews, 27.7% have positive sentiments, and 9.2% have neutral sentiments. Furthermore, the Support Vector Machine (SVM) algorithm achieved the highest level of accuracy at 92%, followed by Random Forest (RF) with an accuracy level of 91%, Naive Bayes (NB) at 79%, Decision Tree (DT) at 80%, and Logistic Regression (LR) with an accuracy level of 83%. In general, the SVM model performs better than others.