<![CDATA[MarineTraffic is a digital-based vessel monitoring application that provides real-time vessel position and movement tracking services. User reviews on the Google Play Store contain important information regarding user satisfaction levels, complaints, and experiences. However, the lack of an automated sentiment analysis system in MarineTraffic application reviews means that complaints and satisfaction cannot be identified quickly, objectively, and measurably, thus requiring automated sentiment analysis. This study aims to implement vector feature extraction and compare the performance of several classification algorithms in analyzing MarineTraffic application review sentiment. Data were obtained through a process of scraping user reviews on the Google Play Store, followed by preprocessing including cleaning, case folding, word normalization, tokenization, and stopword removal. Sentiment labeling was performed using the Lexicon Based method, while text representation was formed using vector feature extraction. The classification process was carried out using the Support Vector Machine (SVM), Naïve Bayes, Decision Tree, and Neural Network algorithms. Model evaluation was carried out using a Confusion Matrix based on accuracy, precision, recall, and F1-score values. The results of this study are expected to provide an overview of user sentiment towards the MarineTraffic application and produce an effective classification model to support application service development. Keywords: Sentiment Analysis, MarineTraffic, Vector Feature Extraction, Lexicon-Based, Machine Learning, Text Classification.]]>
Copyrights © 2026
