SENTIMENT ANALYSIS OF THE EDLINK APPLICATION USING SVM AND NAIVE BAYES

Abstract

The growth of Learning Management Systems (LMS) such as Edlink has made sentiment analysis on user feedback crucial for evaluating user satisfaction and improving services. This study aims to implement and compare the performance of Support Vector Machine (SVM) and Naive Bayes algorithms in classifying sentiments in user reviews on the Edlink application. A dataset of 6,000 Indonesian-language comments was collected and preprocessed using standard Natural Language Processing (NLP) techniques such as tokenizing and stemming. Feature extraction was carried out using Term Frequency-Inverse Document Frequency (TF-IDF) and Bag of Words (BoW). The models were evaluated using 10-fold cross-validation. The results show that SVM combined with TF-IDF provides higher accuracy and better classification performance compared to Naive Bayes. These findings support the application of SVM and TF-IDF in Indonesian sentiment analysis tasks and offer insights for Edlink developers to enhance their platform.