Sentiment Analysis of Pospay Application Reviews Using the Bert Deep Learning Method
DOI:
https://doi.org/10.15408/jti.v18i2.41116Keywords:
Sentiment Analysis, e-money application, pospay, Machine Learning, pos indAbstract
E-money usage in Indonesia has grown significantly due to increasing internet penetration and smartphone adoption. Digital transactions are becoming more common, with platforms like GoPay, OVO, and Dana leading the market. The government and financial institutions actively support this shift through regulations and initiatives. This study analyzes user sentiment on the Pospay application using the BERT deep learning method, based on 16,760 Google Play Store reviews. To the best of our knowledge, this is the first study to apply BERT for sentiment analysis of Pospay user reviews in Indonesia. The goal is to understand user perceptions and satisfaction. BERT helps capture subtle nuances in reviews, including informal expressions and abbreviations like "gk" for negative sentiment. The model achieves high accuracy, with precision scores of 0.82 (negative) and 0.93 (positive), and recall scores of 0.92 (negative) and 0.93 (positive). Findings suggest PT Pos should enhance application stability, security, transaction processing, and customer service. Regular updates are recommended to improve performance and user satisfaction.
References
[1] Amri, Y., & Andarsyah, R. (2024). Jurnal Teknik Informatika, Vol. 16, No. 2, April 2024. 16(2), 1–7.
[2] Chevalier, J., & Mayzlin, D. (2006). The Effect of Word of Mouth on Sales: Online Book Reviews. Journal of Marketing Research, 43. https://doi.org/10.1509/jmkr.43.3.345
[3] Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.
[4] Kotler, P., Keller, Manceau, & Hemonnet-Goujot, A. (2016). Marketing Management 15th. In Décisions Marketing (Vol. 83).
[5] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep Learning. Nature, 521, 436–444. https://doi.org/10.1038/nature14539.
[6] Liu, B. (2012). Sentiment Analysis: Mining Opinions, Sentiments, and Emotions, Second Edition. Sentiment Analysis: Mining Opinions, Sentiments, and Emotions, Second Edition, May, 1–432. https://doi.org/10.1017/9781108639286
[7] Mrityunjay, S., Jakhar, A., & Pandey, S. (2021). Sentiment analysis on the impact of coronavirus in social life using the BERT model. Social Network Analysis and Mining, 11. https://doi.org/10.1007/s13278-021-00737-z
[8] Pang, B., & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2, 1–135. https://doi.org/10.1561/1500000011
[9] Putri, A. (2023). Sentiment Analysis of Mobile Provider Application Reviews Using Naive Bayes Algorithm and Support Vector Machine. Sinkron, 8(2), 824–835. https://doi.org/10.33395/sinkron.v8i2.13469
[10] Sun, C., Huang, L., & Qiu, X. (2019). Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings ofthe Conference, 1, 380–385.
[11] Zhao, X., & Sun, Y. (2022). Amazon Fine Food Reviews with BERT Model. Procedia Computer Science, 208, 401–406. https://doi.org/10.1016/j.procs.2022.10.056
[12] Putri, A., & Ramadhani, A. (2023). Sentiment Analysis of Mobile Payment Applications Using Deep Learning. Jurnal Teknologi dan Informasi, 15(2), 120–135. https://journal.ummat.ac.id/index.php/fkip/article/download/25651/
[13] Y. Sujana, “A Comparative Study of Machine Learning Models for Sentiment Analysis of Dana App Reviews,” IJIE (Indonesian J. Informatics Educ., vol. 7, no. 2, 2024, doi: 10.20961/ijie.v7i2.93132.Bibliography}
[14] Bank Indonesia. (2024). Monetary Policy Report - Quarter IV 2023. Retrieved from https://www.bi.go.id/en/publikasi/laporan/Pages/Laporan-Kebijakan-Moneter-Triwulan-IV-2023.aspx
[15] Halimah, H. S., Hurriyati, R., & Hendryati, H. (2024). E-Wom Strategy Through Perceived Usefulness to Increase Repurchase Intention of Pospay PT PI. Proceedings of the 8th Global Conference on Business, Management, and Entrepreneurship (GCBME 2023), 485–486. https://doi.org/10.2991/978-94-6463-443-3_62:contentReference[oaicite:0]{index=0}
[16] Setiawan, A., & Ratri, D. (2022). Comparison of Mooc Application User Experience in Indonesia (Case Studies: Ruang Guru and Zenius). Proceedings of the 2nd ITB Graduate School Conference (IGSC), 1–8. https://seminar.itb.ac.id/igsc/
[17] Titing, A. S., Stiadi, M., & Kumalasari, F. (2023). The Effect of Completeness of Features and Quality of Information on User Satisfaction of the Pospay Application in Kolaka Regency. Jurnal Ekonomi, 12(2), 1168–1171. http://ejournal.seaninstitute.or.id/index.php/Ekonomi/article/view/1753:contentReference[oaicite:2]{index=2}
[18] Hayati, N., & Mahmudah, A. S. (2016). Analysis of Gronroos Service Quality Dimensions for Pospay Service and Mail Delivery on Customer Satisfaction (Study in Indonesia). International Journal of Business Management and Economic Research, 7(4), 717–725. http://www.ijbmer.com/docs/volumes/vol7issue4/ijbmer2016070403.pdf:contentReference[oaicite:0]{index=0}
[19] Pujiati, B., Gunawan, I., Huriyati, R., & Sultan, M. A. (2024). Effect of Differentiation of Pospay Kiosk Services on the Decision to Use an Application as a Consumer Service (Case Study: PT Pos Indonesia (Persero)). Proceedings of the 8th Global Conference on Business, Management, and Entrepreneurship (GCBME 2023), 726–729. https://doi.org/10.2991/978-94-6463-443-3_95:contentReference[oaicite:1]{index=1}
[20] Imron, S., Setiawan, E. I., Santoso, J., & Purnomo, M. H. (2023). Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 7(3), 4751. https://jurnal.iaii.or.id/index.php/RESTI/article/view/4751
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Erna Mulyati, Muhammad Ibnu Choldun Rachmatullah, Adri Sapta Firmansyah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
