User Reviews of the SEVIMA EdLink Application Using the Machine Learning Method
Article Sidebar
Main Article Content
Abstract
This research aims to conduct sentiment analysis on user reviews of the EdLink application using the Knowledge Discovery in Database (KDD) approach, which consists of data selection, preprocessing, transformation, data mining, and evaluation stages. A total of 2,509 reviews were successfully collected using the google-play-scraper, followed by text cleaning and automatic labeling based on rating scores. The text data was transformed using the TF-IDF method before classification was performed using three machine learning algorithms: Naive Bayes, Support Vector Machine (SVM), and Logistic Regression. The test results using three data splitting schemes (50-50, 70-30, and 80-20) showed that the Naive Bayes model performed best with the highest accuracy reaching 0.77 in the 80-20 split, followed by Logistic Regression at 0.76, while SVM had the lowest accuracy. These findings illustrate that although the EdLink application is considered beneficial, users still frequently experience technical obstacles. This research is expected to serve as evaluation material for developers to improve the quality of the application.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1] I. S. K. Idris, Y. A. Mustofa, and I. A. Salihi, “Analisis Sentimen Terhadap Penggunaan Aplikasi Shopee Mengunakan Algoritma Support Vector Machine ( SVM ),” Jambura J. Electr. Electron. Eng., vol. 5, no. 1, p. hal 32-35, 2023.
[2] B. A. Maulana, M. J. Fahmi, A. M. Imran, and N. Hidayati, “Analisis Sentimen Terhadap Aplikasi Pluang Menggunakan Algoritma Naive Bayes dan Support Vector Machine ( SVM ),” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 2, p. hal 375-384, 2024.
[3] A. Sukmawati, D. E. Ratnawati, and N. Y. Setiawan, “Analisis Sentimen Aplikasi Glints Berdasarkan Ulasan Google Play Store Menggunakan Metode Support Vector Machine,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 1, pp. 1–7, 2021.
[4] A. Srirahayu and L. S. Pribadie, “Review Paper Data Mining Klasifikasi Data Mining,” J. Ilm. Inform. Glob., vol. 14, no. 01 April, p. hal 7-12, 2023.
[5] R. V. Alif and A. H. Hasugian, “Analisis Sentimen Ulasan Pelanggan Aplikasi Hokben Di Google Playstore Menggunakan Metode Support Vector Machine,” Jatilima J. Multimed. dan Teknol. Inf., vol. 07, no. 02, p. hal 201-211, 2025.
[6] H. P. Rajagukguk and R. Fauzi, “Pendekatan Data Mining untuk Memilih Produk Terlaris Menggunakan Algoritma,” J. Comasie, vol. 09, no. 07, p. hal 908-917, 2023.
[7] R. Asgari, “Analisis Sentimen Ulasan pada Google Playstore Penggunaan Aplikasi Dompet Digital (Dana) Menggunakan Metode Naive Bayes,” Comput. Sci., pp. 1–8, 2023.
[8] B. Z. Ramadhan, I. Riza, and I. Maulana, “Analisis Sentimen Ulasan Pada Aplikasi E-Commerce Dengan Menggunakan Algoritma Naïve Bayes,” J. Appl. Informatics Comput., vol. 6, no. 2, p. hal 220-225, 2022.
[9] A. Novanto, D. Indra, and W. Astuti, “Analisis Pre-processing Sentimen Terhadap Komentar Layanan Indihome Pada Twitter,” LINIER (Literatur Inform. Komput., vol. 1, no. 2, p. hal 145-152, 2024.
[10] A. A. Syam, G. H. M, A. Salim, D. F. Surianto, and M. Fajar B, “Analisis teknik preprocessing pada sentimen masyarakat terkait konflik israel-palestina menggunakan support vector machine,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 9, no. 3, p. hal 1464-1472, 2024.
[11] Musfiroh, A. Tholib, and Z. Arifin, “Analisis Sentimen Terhadap Ulasan Aplikasi Shopee di Google Play Store Menggunakan Metode TF-IDF dan Long Short-Term Memory ( LSTM ),” J. Electr. Eng. Comput., vol. 6, no. 2, p. hal 371-381, 2024, doi: 10.33650/jeecom.v4i2.
[12] I. K. W. Dananjaya and I. G. A. A. D. Inradewi, “Perbandingan Metode Pembobotan TF-RF Dan TF-ABS Pada Kategorisasi Berita Di BDI Denpasar,” SINTECH (Science Inf. Technol. J., vol. 6, no. 1, p. hal 16-25, 2023.
[13] K. C. Astuti, A. Firmansyah, and A. Riyadi, “Implementasi Text Mining untuk Analisis Sentimen Masyarakat terhadap Ulasan Aplikasi Digital Korlantas Polri pada Google Play Store,” Remik Ris. dan E-Jurnal Manaj. Inform. Komput., vol. 8, no. 1, p. hal 383-394, 2024.
[14] V. Fitriyana, L. Hakim, D. C. R. Novitasri, and A. H. Asyhar, “Analisis Sentimen Ulasan Aplikasi Jamsostek Mobile Menggunakan Metode Support Vector Machine,” J. Buana Inform., vol. 14, no. 1, p. hal 40-49, 2023.
[15] Syafrizal, M. Afdal, and R. Novita, “Analisis Sentimen Ulasan Aplikasi PLN Mobile Menggunakan Algoritma Naïve Bayes Classifier dan K-Nearest Neighbor,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 1, p. hal 10-19, 2024.
[16] A. R. Putra and D. E. Ratnawati, “Analisis Sentimen Berbasis Aspek pada Aplikasi Mobile Menggunakan Naive Bayes Berdasarkan Ulasan Pengguna Playstore (Studi Kasus: JConnect Mobile),” J. Teknol. Inf. dan Ilmu Komput., vol. 12, no. 2, p. hal 293-300, 2025, doi: 10.25126/jtiik.2025127556.