User Perceptions of Digital Public Service Quality: Sentiment Analysis of the MyPertamina Application Using Stochastic Gradient Descent
Abstract
Digital public service applications are increasingly used to support the distribution of subsidized services and improve administrative efficiency. However, user perceptions of system reliability, transaction processes, and data verification procedures remain critical factors influencing service acceptance. This study aims to analyze public sentiment toward the quality of a digital public service application by examining user reviews and identifying dominant service issues affecting user experience. A quantitative approach was applied using user review data collected from the Google Play Store. The textual data were processed through several stages of preprocessing and then classified into positive, neutral, and negative sentiments using the Stochastic Gradient Descent algorithm. In addition, aspect based analysis was conducted to examine issues related to system reliability, transaction processes, and data management and verification. The results show that system reliability and application stability, particularly login processes, verification mechanisms, and system updates, are the most influential factors shaping user sentiment. Transaction related issues such as payment failures and barcode scanning problems also contribute to negative perceptions, although some users acknowledge the convenience and speed of digital transactions. The study concludes that improving system stability and simplifying verification procedures are essential to enhance user satisfaction and strengthen the effectiveness of digital public service implementation.
References
Afyare, A., & Orey, M. A. H. (2025). The Influence of Social Media on Political Discourse and Public Opinion. Architecture Image Studies, 6(3), 1634–1667. https://doi.org/10.62754/ais.v6i3.506
Alharbi, Y., & Khan, S. S. (2025). Classifying Multi-Lingual Reviews Sentiment Analysis in Arabic and English Languages Using the Stochastic Gradient Descent Model. Computers, Materials and Continua, 83(1), 1275–1290. https://doi.org/10.32604/cmc.2025.061490
Ananda Febryan, F. (2025). Analisis Dampak Modernisasi Digital Terhadap Efektivitas Pelayanan Kepolisian Sektor Manyar. Paradigma POLISTAAT: Jurnal Ilmu Sosial Dan Ilmu Politik, 8(2), 19–30. https://doi.org/10.23969/paradigmapolistaat.v8i2.39139
Arifin, D. A. N., Pada, S., Teks, D., Indonesia, B., Pardede, J., & Darmawan, D. (2025). Perbandingan Algoritma Stemming Porter , Sastrawi , Idris , Comparison of Stemming Algorithms Porter , Sastrawi , Idris , and Arifin Setiono on Indonesian Text Documents. 12(1), 69–76. https://doi.org/10.25126/jtiik.2025128860
Ba, Y., & Tan, H. (2025). Moral foundations of energy transitions in the United States: A cross-sector discourse analysis. Energy Research and Social Science, 125. https://doi.org/10.1016/j.erss.2025.104090
Baqach, A., & Battou, A. (2024). A new sentiment analysis model to classify students’ reviews on MOOCs. Education and Information Technologies, 29(13), 16813–16840. https://doi.org/10.1007/s10639-024-12526-0
Chu, Y. (2025). Dynamic response and disposal strategies for public opinion crises driven by reinforcement learning. Discover Artificial Intelligence, 5(1). https://doi.org/10.1007/s44163-025-00699-7
Chaniago, H., Hidayat, H., & Efawati, Y. (2025). Intrinsic Motivation and the Use of Artificial Intelligence (AI) in the Public Sector: Evidence from Indonesia. Revista Brasileira de Políticas Públicas, 15(2). https://doi.org/10.5102/rbpp.v15i2.10066
Chaniago, H., & Efawati, Y. (2026). Individual absorptive capacity as a stepping stone for digitalization, digital transformation, and small business performance; Entrepreneurial perspectives. Contaduría y administración, 71(2), 1-36.https://doi.org/10.22201/fca.24488410e.2026.5126
Demircan, M., Seller, A., Abut, F., & Akay, M. F. (2021). Developing Turkish sentiment analysis models using machine learning and e-commerce data. International Journal of Cognitive Computing in Engineering, 2(July), 202–207. https://doi.org/10.1016/j.ijcce.2021.11.003
Dimalanta, V. A. R., & Fajardo, A. (2025). Optimizing Multinomial Naïve Bayes in Sentiment Analysis through Hybrid Ensemble Techniques. ACM International Conference Proceeding Series, December 2024, 131–136. https://doi.org/10.1145/3718391.3718418
Faris Abdi El Hakim, & M Adamu Islam Mashuri. (2025). Analisis Sentimen Pengguna Aplikasi Mobile JKN Menggunakan Metode Stochastic Gradient Descent (SGD). Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI), 4(1), 284–294. https://doi.org/10.62712/juktisi.v4i1.409
Gaye, B., Zhang, D., & Wulamu, A. (2021). Sentiment classification for employees reviews using regression vectorstochastic gradient descent classifier (RV-SGDC). PeerJ Computer Science, 7, 1–27. https://doi.org/10.7717/peerj-cs.712
Gopal, S. V., Sollapur, S. B., Chaudhary, R., Thakur, R., Shree, A. S., & Ray, A. K. (2025). Decision Support Systems for Library Policy and Governance. Indian Journal of Information Sources and Services, 15(3), 266–275. https://doi.org/10.51983/ijiss-2025.IJISS.15.3.30
Handojo, P., Hardjosoekarto, S., Hayadi, L. F., Luayya, L., Lestari, H. M., & Amalia, R. (2026). Public Reactions to Indonesia’s KRIS Policy: A Textual Network Analysis of Digital Legitimacy. Journal of Public Health and Pharmacy, 6(1), 158–170. https://doi.org/10.56338/jphp.v6i1.7401
Javed, M., Khademi, S., Hickman, J., Buttery, J., Clothier, H., & Dimaguila, G. L. (2025). VaxPulse: Monitoring of Online Public Concerns to Enhance Post-Licensure Vaccine Surveillance. Studies in Health Technology and Informatics, 329, 728–732. https://doi.org/10.3233/SHTI250936
Kholifah, B., Syarif, I., & Badriyah, T. (2025). Analysis of Mental Health Disorders via Social Media Mining Using LSTM and Bi-LSTM. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 4(3). https://doi.org/10.22219/kinetik.v10i3.2205
Krajewski, P., Weidgang, J., Lipsa, J., & Lebiedzińska, M. (2026). Integrating social media and survey data to map social landscape value in diverse municipal contexts. Landscape and Urban Planning, 267(September 2025). https://doi.org/10.1016/j.landurbplan.2025.105542
Mohammadi, N., & Mohammadian, B. (2025). Employee value proposition mining: A novel approach to employer brand development based on social media data using aspect-based sentiment analysis. Results in Engineering, 28(September), 107973. https://doi.org/10.1016/j.rineng.2025.107973
Nóra, Julianna, G., Artúr, V., Szilvia, B. S., & Roland, M. (2025). Investigating banks’ social media content and consumer reactions with machine learning. Journal of Open Innovation: Technology, Market, and Complexity, 11(2). https://doi.org/10.1016/j.joitmc.2025.100512
Pardede, A. M., Mustafid, M., & Sugito, S. (2025). Implementasi Metode Convolutional Neural Network Untuk Klasifikasi Sentimen Ulasan Pengguna Aplikasi Mypertamina. Jurnal Gaussian, 14(2), 345–355. https://doi.org/10.14710/j.gauss.14.2.345-355
Patil, S. S., Suryawanshi, V. P., Patil, S. M., Girase, S. P., & Bhagat, D. A. (2025). Review of sentiment analysis in social media using big data: techniques, tools, and frameworks. International Journal of Basic and Applied Sciences, 14(2), 34–48. https://doi.org/10.14419/mhv83077
Pinilla-Dominguez, P., & Pinilla-Dominguez, J. (2025). Challenges and reforms in Spain’s health technology assessment system: analysis of criteria influencing medicines’ reimbursement decisions between 2019 and 2022 in Spain. European Journal of Health Economics, 26(9), 1569–1579. https://doi.org/10.1007/s10198-025-01790-7
Putra, J. M., & Menorizah, M. (2025). An Analysis of the Use of the MyPertamina Application in Reducing the Misuse of Government-Subsidised Pertalite (A Literature Review). JERIT: Journal of Educational Research and Innovation Technology, 2(2), 62–72. https://doi.org/10.34125/jerit.v2i2.30
Qhal, E. M. A. (2025). Data-Driven Knowledge Management Frameworks for Effective Risk and Crisis Management: A Cross-Industry Approach. Journal of Applied Data Sciences, 6(2), 1437–1453. https://doi.org/10.47738/jads.v6i2.780
Rifaldy, F., Sibaroni, Y., & Prasetiyowati, S. S. (2025). Effectiveness of Word2Vec and TF-IDF in Sentiment Classification on Online Investment Platforms Using Support Vector Machine. JIPI (Jurnal Ilmiah Penelitian Dan Pembelajaran Informatika), 10(2), 863–874. https://doi.org/10.29100/jipi.v10i2.6055
Sclocchi, A., & Wyart, M. (2024). On the different regimes of stochastic gradient descent. Proceedings of the National Academy of Sciences of the United States of America, 121(9), 1–8. https://doi.org/10.1073/pnas.2316301121
Shapa, T., Adristi, V., Setiawan, N. Y., & Wijoyo, S. H. (2025). Heritage Berdasarkan Analisis Sentimen Dan Root Cause Analysis ( Rca ). 9(3). https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/14608
Thariq, F., & Efawati, Y. (2024). The Influence of Website Quality on Buying Interest Consumer. International Journal Administration, Business & Organization, 5(2), 64-74.
Wardana, D. A. B., Muflikhah, L., & Perdana, R. S. (2025). Analisis Sentimen Ulasan Pengguna Aplikasi Mypertamina Pada Google Play Store Menggunakan Metode Xgboost Dan Word2Vec Embedding. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 9(8), 1–10. https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/15247
Wijaya, H., Akbar, M. N., Irawati, F. E., & Hayati, N. (2025). Observasi Penggunaan Aplikasi Mypertamina di SPBU Cangkring Karanganyar Demak. Jurnal Bakti Nusantara, 3(1), 19–29. https://doi.org/10.63763/jutira.v3i1.106
Yakura, T., Ngoc, A. M., & Shiomi, Y. (2026). Adapting to new mobility conditions: Evidence from a Japanese survey on the substitution of in-person mobility with online services for daily necessities. Travel Behaviour and Society, 43(June 2025), 101221. https://doi.org/10.1016/j.tbs.2025.101221
Yang, Y., Lin, Y. W., & Cheng, L. C. (2025). Impact of real-time public sentiment on herding behavior in Taiwan’s stock market: Insights across investor types and industries. International Review of Economics and Finance, 102. https://doi.org/10.1016/j.iref.2025.104397
Yulian Surya Saputra, Sucitra Sahara, & Agung Permana, R. (2025). Assessing the Role of E-Govqual in Improving Public Satisfaction with the MyPertamina Application in Setiabudi District. Nuansa Informatika, 19(2), 18–24. https://doi.org/10.25134/ilkom.v19i2.379
Yuliyanti, A. Y., Septiana, P. M., Sari, W. W. S. P., & Sari, T. (2025). Analyzing Public Sentiment on Indonesia’s Constitutional Court Post-2024 Election Ruling: Insights from Appraisal Theory and Data Mining. Traduction et Langues, 24(1), 77–103. https://doi.org/10.52919/translang.v24i01.1027
Copyright (c) 2026 Moch. Badrus Sholeh, Faris Abdi El Hakim, Ahmad Abdullah Zawawi, Rabiyya Museyibzada
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish in this journal agree to the following terms:
- The authors confirm that they are the authors of the submitted article, which will be published (online) in the journal IJABO (International Journal Administration, Business & Organization) by the Asosiasi Ahli Administrasi Indonesia (A3i), Bandung, Indonesia. The author’s name will be evident in the article. The publisher makes all decisions regarding the layout and distribution of the work.
- Authors guarantee that the work is their own original creation and does not infringe any statutory or common-law copyright or any proprietary right of any third party. In case of claims by third parties, authors commit themself to defend the interests of the publisher and shall cover any potential costs.
- Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0). This license allows the redistribution and reuse of papers provided the authorship is properly credited.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., posting it to an institutional repository or publishing it in a book), with an acknowledgment 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 this can lead to productive exchanges and earlier and greater citations of published work.
