Understanding user satisfaction in digital banking: Sentiment analysis and topic modeling of Indonesian bank reviews
Abstract
The development of digital banks in Indonesia has changed the way consumers access financial services, especially through mobile applications. This research aims to evaluate user satisfaction and engagement with five leading digital banks in Indonesia: Blu, Jago, Jenius, NeoBank, and SeaBank. The approach used includes sentiment analysis using the VADER, method and topic modeling with TF-IDF as well as temporal analysis to identify user review patterns from 2018 to mid-2024. Results show a positive correlation between sentiment scores and user ratings, where apps with high sentiment, such as Jenius and SeaBank, also have better ratings. In addition, there are spikes in reviews in certain periods, such as 2021 for NeoBank and Jenius, and 2024 for SeaBank, which coincides with the launch of new features or app updates. Quadrant analysis reveals the competitive position of digital banks based on user sentiment and engagement. The findings show the importance of app stability and service quality for user satisfaction. This research provides practical insights for digital banks in optimizing their service strategies and improving the overall user experience.
Downloads
References
Mohanty A. (2023) Sentiment analysis on banking feedback and news data using synonyms and antonyms. International Journal of Advanced Computer Science and Applications, vol. 14, no. 12. https://doi.org/10.14569/ijacsa.2023.0141294
Rahman N.A., Idrus S.D., Adam N.L. (2022) Classification of customer feedbacks using sentiment analysis towards mobile banking applications. IAES International Journal of Artificial Intelligence (IJ-AI), vol. 11, no. 4, pp. 1579–1587. https://doi.org/10.11591/ijai.v11.i4.pp1579-1587
Kumaresan C., Thangaraju P. (2023) Sentiment analysis in multiple languages: A review of current approaches and challenges. JDAAI, vol. 2, no. 1, pp. 8–15. https://doi.org/10.46632/jdaai/2/1/2
Riani R., Rusydiana A.S., Ikhwan I. (2022) Sentiment analysis of multilingual tweets on cash waqf. International Journal of Waqf, vol. 2, no. 1. https://doi.org/10.58968/ijf.v2i1.96
Wardani N.S., Prahutama A., Kartikasari P. (2020) Sentiment analysis of the relocation of the national capital using naive Bayes classification for Bernoulli and multinomial models. Jurnal Gaussian, vol. 9, no. 3, pp. 237–246 (in Indonesian). https://doi.org/10.14710/j.gauss.v9i3.27963
Mu’adzah N. (2022) Sentiment analysis on sharia credit card using senti-strength. Review on Islamic Accounting, vol. 2, no. 1. https://doi.org/10.58968/ria.v2i1.137
Shah S., Ghomeshi H., Vakaj E., Cooper E., Nassr R.M. (2023) An ensemble-learning-based technique for bimodal sentiment analysis. Big Data and Cognitive Computing, vol. 7, no. 2, article 85. https://doi.org/10.3390/bdcc7020085
Maskat R., Rahman N.A. (2020) Categorization of Malay social media text and normalization of spelling variations and vowel-less words. International Journal on Advanced Science Engineering and Information Technology, vol. 10, no. 4, pp. 1380–1386. https://doi.org/10.18517/ijaseit.10.4.10237
Zagirova D. (2023) Biomedical generative pre-trained based transformer language model for age-related disease target discovery. Aging, vol. 15, no. 18, pp. 9293–9309. https://doi.org/10.18632/aging.205055
Haq I., Qiu W., Jie G., Tang P. (2023) NLPashto: NLP toolkit for low-resource pashto language. International Journal of Advanced Computer Science and Applications, vol. 14, no. 6. https://doi.org/10.14569/ijacsa.2023.01406142
Névéol A., Dalianis H., Velupillai S., Savova G., Zweigenbaum P. (2018) Clinical natural language processing in languages other than english: Opportunities and challenges. Journal of Biomedical Semantics, vol. 9, no. 1, article 12. https://doi.org/10.1186/s13326-018-0179-8
Thaha A.R., Purnamasari R., Antoro A.F.S. (2024) Taxpayer satisfaction transformation: A text mining analysis of service delivery at Jakarta’s tax offices. Journal of Tax Reform, vol. 10, no. 3, pp. 441–458. https://doi.org/10.15826/jtr.2024.10.3.177
Joon R., Singhal A. (2017) Analysis of MWES in hindi text using NLTK. International Journal on Natural Language Computing, vol. 6, no. 1, pp. 13–22. https://doi.org/10.5121/ijnlc.2017.6102
Dima A.A., Massey A.K. (2022) Keyphrase extraction for technical language processing. Journal of Research of the National Institute of Standards and Technology, vol. 126, article 126053. https://doi.org/10.6028/jres.126.053
Dharsono S. (2023) The impact of implementing the digital technology innovation on banking performance in Indonesia. IJAEB, vol. 1, no. 2, pp. 310–316. https://doi.org/10.24912/ijaeb.v1i2.310-316
Tarigan H.A.A.B., Paulus D.H. (2020) Protection of customers for management of digital banking services (Study at PT. BRI Unit Boyolali). Hang Tuah Law Journal, vol. 3, no. 2, article 170. https://doi.org/10.30649/htlj.v3i2.128
Nurbakti R. (2023) Analysis of the influence of digital promotions, perception of ease, transparency and service features toward public intention to use digital bank in money saving. Jurnal Sistim Informasi Dan Teknologi, vol. 5, no. 3, pp. 79–84. https://doi.org/10.60083/jsisfotek.v5i3.308
Noei E., Zhang F., Zou Y. (2021) Too many user-reviews! What should app developers look at first? IEEE Transactions on Software Engineering, vol. 47, no. 2, pp. 367–378. https://doi.org/10.1109/tse.2019.2893171
Frie K., Hartmann‐Boyce J., Jebb S.A., Albury C., Nourse R., Aveyard P. (2017) Insights from Google Play Store user reviews for the development of weight loss apps: Mixed-method analysis. JMIR Mhealth and Uhealth, vol. 5, no. 12, article e203. https://doi.org/10.2196/mhealth.8791
Wu S., Ren M., Pitafi A.H., Islam T. (2020) Self-image congruence, functional congruence, and mobile app intention to use. Mobile Information Systems, vol. 2020, no. 1, article 5125238. https://doi.org/10.1155/2020/5125238
Fang F., Zhou Y., Shi Y., Li Z. (2023) A study of the ping an health app based on user reviews with sentiment analysis. International Journal of Environmental Research and Public Health, vol. 20, no. 2, article 1591. https://doi.org/10.3390/ijerph20021591
Copyright (c) 2025 HSE University
This work is licensed under a Creative Commons Attribution 4.0 International License.
