Work

A Comparative Sentiment Analysis of Learning Management Systems Reviews Using Machine Learning within the SEMMA Framework

Year: 2026
Type: article
Abstract: Mobile Learning Management Systems (LMS) have become essential in supporting digital learning by providing flexible access to academic resources and communication between students and educational institutions. User reviews published on the Google Play Store provide valuable feedback for evaluating service quality; however, their unstructured nature makes systematic analysis challenging. This study aims to analyze user sentiment toward the LMS Mobile application of Universitas XYZ and compare the performance of the Naïve Bayes and Support Vector Machine (SVM) algorithms in sentiment classification. A quantitative experimental approach was employed using 129 user reviews collected through web scraping from the Google Play Store between November 2020 and December 2025. The analysis followed the SEMMA (Sample, Explore, Modify, Model, Assess) framework and applied Natural Language Processing (NLP) techniques, including text cleaning, tokenization, case folding, stopword removal, and stemming. Textual data were transformed into numerical features using the Term Frequency–Inverse Document Frequency (TF-IDF) method before being classified with Naïve Bayes and SVM. Model performance was evaluated using confusion matrix metrics, including accuracy, precision, recall, and F1-score. The results indicate that negative sentiment dominates user reviews, primarily concerning login problems, application errors, and system performance. The Naïve Bayes model achieved a higher accuracy (0.69) than SVM (0.65), whereas SVM demonstrated more balanced classification performance across sentiment categories. These findings provide a data-driven basis for evaluating user feedback and supporting continuous improvement of digital learning services within higher education. Keywords: Sentiment Analysis, Machine Learning, Learning Management System, Support Vector Machine, SEMMA.
Institution: Binus University
Language: English
Open Access status: diamond
OpenAlex ID: W7225697459
FWCI:
Cites: 34
Cited by:
Related to: 10