<![CDATA[The development of digital services in the telecommunications sector encourages service providers to continuously improve the quality of applications used by customers. The MyTelkomsel application has become one of the main media for users to access various Telkomsel services, so that reviews provided by users on the Google Play Store can be an important source of information to determine the level of satisfaction and problems experienced by users. However, the increasing number of reviews makes the manual analysis process less effective, takes a long time, and has the potential to produce subjective assessments. This study aims to analyze the sentiment of MyTelkomsel application user reviews by applying Term Frequency–Inverse Document Frequency (TF-IDF) weighting as a feature extraction method and the Random Forest algorithm as a sentiment classification method. The research data was obtained through the process of scraping MyTelkomsel application user reviews on the Google Play Store. The research stages include data collection, text preprocessing consisting of cleaning, case folding, normalization, tokenization, stopword removal, and stemming, followed by TF-IDF weighting, sentiment labeling, classification process using Random Forest, and model evaluation using a confusion matrix, accuracy, precision, recall, and F1-score. The results showed that the Random Forest model with TF-IDF features achieved classification performance with an accuracy of 81.91%, a precision of 76.77%, a recall of 81.91%, and an F1-score of 79.11%. These results indicate that the combination of TF-IDF and Random Forest methods is capable of identifying sentiment patterns in user reviews with good performance. This study provides information on the trends in user opinions regarding the service quality of the MyTelkomsel application and can serve as evaluation material for developers in improving service quality and user experience.]]>
Copyrights © 2026
