Perbandingan Performa Rating-Based Labeling dan Lexicon-Based pada Analisis Sentimen Ulasan Mobile JKN dengan SVM
DOI:
https://doi.org/10.32493/jiup.v11i2.59427Keywords:
Mobile JKN, Sentiment Analysis, Support Vector Machine, Rating-Based, Lexicon-BasedAbstract
This study aims to identify user sentiment toward the Mobile JKN application by comparing lexicon-based labeling using the InSet sentiment lexicon with rating-based labeling derived from users' star ratings. The dataset consisted of 50,000 Google Play Store reviews, which were reduced to 34,317 valid reviews after preprocessing. Sentiment classification was performed using the Support Vector Machine (SVM) algorithm with CountVectorizer for feature extraction, while class imbalance was handled using the Synthetic Minority Over-sampling Technique (SMOTE). The lexicon-based approach achieved 99% accuracy, precision, recall, and F1-score. In contrast, the rating-based approach achieved 76% accuracy, 62% precision, 61% recall, and a macro-average F1-score of 60%, mainly due to lower performance in classifying neutral reviews. Labeling validity was evaluated using 300 manually annotated reviews created by two annotators as the ground truth. The results indicate that lexicon-based labeling is more effective than rating-based labeling for SVM-based sentiment classification. WordCloud visualization shows that negative sentiment is dominated by technical issues, whereas positive sentiment mainly reflects easier access to healthcare services.
References
A. N. Arofah, V. Maiga, M. Noor, F. Endra, B. Setyawan, dan D. Azmi, “Dampak Implementasi Program JKN Terhadap Biaya Kesehatan di Fasilitas Kesehatan Tingkat Lanjutan,” vol. 3, no. 2, hal. 64–72, 2022, doi: https://doi.org/10.37148/comphijournal.v3i2.104.
B. Kesehatan, “Mobile JKN,” 2026. https://play.google.com/store/apps/details?id=app.bpjs.mobile&hl=id (diakses 8 Maret 2026).
M. S. Assyifa dan H. Pratiwi, “Sentiment Analysis of STMIK Widya Cipta Dharma Using a Lexicon-Based Approach Analisis Sentimen Terhadap STMIK Widya Cipta Dharma Menggunakan Pendekatan Lexicon,” hal. 1–7, 2025, [Daring]. Tersedia pada: http://repository.wicida.ac.id/id/eprint/6082
R. R. Suryono, “Perbandingan kinerja model support vector machine dan naïve bayes untuk analisis sentimen super app polri 1) 1,2,3),” vol. 11, no. 1, hal. 1962–1976, 2026, doi: https://doi.org/10.36341/rabit.v11i1.7582.
W. T. Kusuma dan L. C. Kurniawan, “Sentiment Analysis User Reviews of Acupuncture Applications on Play Store Using Naïve Bayes Analisis Sentimen Ulasan Pengguna Aplikasi Akupunktur di Play Store Menggunakan Naïve Bayes,” vol. 6, no. April, hal. 632–639, 2026, doi: https://doi.org/10.57152/malcom.v6i2.2620.
D. Analisis, S. Terhadap, dan P. Publik, “Komparasi model svm, naïve bayes, dan random forest dalam analisis sentimen terhadap percakapan publik tentang pertamina,” vol. 11, no. 1, hal. 92–105, 2026, doi: https://doi.org/10.29100/jipi.v11i1.7699.
T. Setyani, K. Sari, H. N. Heidy, dan R. R. Suryono, “Sentiment Analysis of Jamsostek Mobile Application Reviews on Google Play Store Using Support Vector Machine and Naive Bayes Algorithms Analisis Sentimen Pengguna Aplikasi Jamsostek Mobile Berdasarkan Ulasan Google Play Store Menggunakan Algoritma Support,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 6, no. January, hal. 373–384, 2026, doi: https://doi.org/10.57152/malcom.v6i1.2526.
H. Firda et al., “Perbandingan Pelabelan Rating - based dan Inset Lexicon - based dalam Analisis Sentimen Menggunakan SVM ( Studi Kasus : Ulasan Aplikasi GoBiz di Google Play Store ) Comparison of Rating - based and Inset Lexicon - based Labeling in Sentiment Analysis usin,” Sist. J. Sist. Inf., vol. 14, hal. 516–528, 2025, doi: https://doi.org/10.32520/stmsi.v14i2.4795.
L. E. Naufal, N. Surojudin, dan I. Afriantoro, “Analisis Sentimen Aplikasi Mobile JKN di Google Play Store Menggunakan Algoritma Naive Bayes,” vol. 6, no. 4, hal. 1999–2009, 2025, doi: https://doi.org/10.47065/josh.v6i4.7846.
Y. Wang, W. Liao, H. Shen, Z. Jiang, dan J. Zhou, “Some notes on the basic concepts of support vector machines,” J. Comput. Sci., vol. 82, no. July, hal. 102390, 2024, doi: https://doi.org/10.1016/j.jocs.2024.102390.
M. Ali dan Y. Fissha, “Propose Adjustable Support Vector Machine Approach for Classifying Imbalanced Work Travel Mode Choice Data,” Transp. Res. Interdiscip. Perspect., vol. 35, no. September 2024, 2026, doi: https://doi.org/10.1016/j.trip.2025.101786.
Y. A. Singgalen, “Analisis Sentimen Wisatawan terhadap Kualitas Layanan Hotel dan Resort di Lombok Menggunakan SERVQUAL dan CRISP-DM,” vol. 4, no. 4, hal. 1870–1882, 2023, doi: https://doi.org/10.47065/bits.v4i4.3199.
H. P. Jelita dan M. I. Saad, “Penerapan Algoritma Naïve Bayes Dalam Analisis Sentimen Masyarakat Terhadap STMIK Widya Cipta Dharma,” vol. 6, no. 2, hal. 148–160, 2025, doi: https://doi.org/10.47065/bit.v5i2.2029.
I. Kurniawan et al., “Implementasi Algoritma Random Forest Untuk Menentukan Implementation of Random Forest Algorithm for Determining Recipients of Raskin,” vol. 10, no. 2, hal. 421–428, 2023, doi: https://doi.org/10.25126/jtiik.202396225.
J. J. A. Limbong, I. Sembiring, K. D. Hartomo, U. Kristen, S. Wacana, dan P. Korespondensi, “Analisis Klasifikasi Sentimen Ulasan pada E-Commerce Shopee Berbasis Word Cloud dengan Metode Naive Bayes dan K-Nearest Analysis of Review Sentiment Classification on E-Commerce Shopee Word Cloud Based with Naïve Bayes And K-Nearest Neighbor Methods,” vol. 9, no. 2, hal. 347–356, 2022, doi: https://doi.org/10.25126/jtiik.202294960.
S. A. H. Bahtiar, “Perbandingan Naïve Bayes dan Logistic Regression dalam Sentiment Analysis pada Review Marketplace menggunakan Rating-Based Labeling,” Universitas Islam Indonesia, 2023. [Daring]. Tersedia pada: https://dspace.uii.ac.id/handle/123456789/46497
R. C. A. S, Y. Suhari, S. Informasi, dan U. S. Unisbank, “Analisis Sentimen Ulasan Pelanggan Restoran Menggunakan Support Vector Machine,” JATI (Jurnal Mhs. Tek. Inform., vol. 10, no. 1, hal. 572–576, 2026, doi: https://doi.org/10.36040/jati.v10i1.16813.
R. H. Muhammadi, T. G. Laksana, dan A. B. Arifa, “Combination of Support Vector Machine and Lexicon- Based Algorithm in Twitter Sentiment Analysis,” Khazanah Inform. J. Ilmu Komput. dan Inform., vol. 8, no. 1, hal. 59–71, 2022, doi: https://doi.org/10.23917/khif.v8i1.15213.
R. I. Alhaqq, I. M. K. Putra, dan Y. Ruldeviyani, “Analisis Sentimen terhadap Penggunaan Aplikasi MySAPK BKN di Google Play Store,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 11, no. 2, hal. 105–113, 2022, doi: https://doi.org/10.22146/jnteti.v11i2.3528.
A. Nugroho dan E. Rilvani, “Penerapan Metode Oversampling SMOTE Pada Algoritma Random Forest Untuk Prediksi Kebangkrutan Perusahaan,” Techno.COM, vol. 22, no. 1, hal. 207–214, 2023, doi: https://doi.org/10.33633/tc.v22i1.7527.
M. K. Anam, T. Arita, dan M. Bambang, “Sentiment Analysis for Online Learning using The Lexicon-Based Method and The Support Vector Machine Algorithm,” Ilk. J. Ilm., vol. 15, no. 2, hal. 290–302, 2023, doi: https://doi.org/10.33096/ilkom.v15i2.1590.290-302.
D. Ismafillah, T. Rohana, dan Y. Cahyana, “Analisis Algoritma Pohon Keputusan untuk Memprediksi Penyakit Diabetes Menggunakan Oversampling SMOTE,” INFOTECH J. Inform. Teknol., vol. 4, no. 1, hal. 27–36, 2023, doi: https://doi.org/10.37373/infotech.v4i1.452.
F. Syahputra, D. Yani, H. Tanjung, R. Dewi, dan H. E. Br, “Analisis Sentimen Masyarakat terhadap Isu Transformasi Digital Pemerintah di Twitter Menggunakan Naive Bayes dan Support Vector Machine,” INFOSYS (Journal Inf. Syst., vol. 10, no. 2, hal. 73–85, 2026, doi: https://doi.org/10.22303/infosys.10.2.2026.73-85.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Alya Nurjannah, Wahyuni, Ahmad Fahrijal Pukeng
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Jurnal Informatika Universitas Pamulang have CC-BY-NC or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work.
In developing strategy and setting priorities, Jurnal Informatika Universitas Pamulang recognize that free access is better than priced access, libre access is better than free access, and libre under CC-BY-NC or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.
Jurnal Informatika Universitas Pamulang is licensed under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
YOU ARE FREE TO:
- Share : copy and redistribute the material in any medium or format
- Adapt : remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms
This work is licensed under a 