Citation:

Nana Varian Januardi, Afina Hasya. "Crashes, Fees, and Customer Service: Theme-Level Correlates of E-Wallet App Ratings in Indonesia" International Research Journal of Economics and Management Studies, Vol. 5, No. 6, pp. 120-131, 2026. Crossref. http://doi.org/10.56472/25835238/IRJEMS-V5I6P112

Abstract:

A star rating signals that users are unhappy without saying why. We open that black box for Indonesian e-wallets by mining 69,006 Indonesian-language Google Play reviews of six leading apps and asking which review themes move with the star a user leaves. We recover 10 latent themes using topic modeling, map them to e-service-quality (e-S-QUAL) dimensions, and regress the rating on theme prevalence, controlling for app and month fixed effects, within a balanced seven-month window (November 2025 to May 2026; standalone wallets as the primary, the Gojek super-app as a comparison). Relative to a general satisfaction theme, reviews dominated by e-S-QUAL failure dimensions fulfillment (failed top-ups, transfers, fees), system availability (crashes, lost access), and responssiveness (customer service) carry lower ratings; a realistic interquartile shift maps to roughly a tenth of a star. The association is not a within-review artifact: theme prevalence computed from other reviews in the same app-month still predicts a review's rating for 8 of 9 themes, and the pattern survives after removing all sentiment words from the topic model. Eight of nine associations remain significant under a Webb six-point wild-cluster bootstrap across the six apps, and the result is stable to dropping any app, equal-weighting apps, dropping the crash-spike months, and including single-token reviews. Two qualifications are explicit: the broad ordering (failure dimensions below satisfaction) is robust, but the fine ranking among failure dimensions is sensitive to the topic-model seed; and promotional content, often assumed central, appears in only ~4% of reviews and skews toward complaints. We read the results as a reproducible, associative map of where rating risk concentrates across e-S-QUAL dimensions, not as causal effects.

References:

[1] Aryanti, F. A. D., Luthfiarta, A., & Soeroso, D. A. I. (2025). Aspect-based sentiment analysis with LDA and the IndoBERT algorithm on the mental health app Riliv. JOURNAL OF APPLIED INFORMATICS AND COMPUTING. https://doi.org/10.30871/jaic.v9i2.8958
[2] Asri, Y., Kuswardani, D., Suliyanti, W. N., Manullang, Y. O., & Ansyari, A. R. (2025). Sentiment analysis based on Indonesian language lexicon and IndoBERT on user reviews of the PLN mobile application. Indonesian Journal of Electrical Engineering and Computer Science. https://doi.org/10.11591/ijeecs.v38.i1.pp677-688
[3] Blei, D. M. (2012). Probabilistic topic models. Communications of the ACM. https://doi.org/10.1145/2133806.2133826
[4] Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research. https://doi.org/10.5555/944919.944937
[5] Çallı, L. (2022). Exploring mobile banking adoption and service quality features through user-generated content: The application of a topic modeling approach to Google Play Store reviews. International Journal of Bank Marketing. https://doi.org/10.1108/ijbm-08-2022-0351
[6] Cameron, A. C., Gelbach, J. B., & Miller, D. L. (2008). Bootstrap-based improvements for inference with clustered errors. The Review of Economics and Statistics. https://doi.org/10.1162/rest.90.3.414
[7] Cao, X., Yu, L., Liu, Z., Gong, M., & Luqman, A. (2018). Understanding mobile payment users' continuance intention: A trust transfer perspective. Internet Research. https://doi.org/10.1108/intr-11-2016-0359
[8] Chen, X., & Li, S. (2016). Understanding continuance intention of mobile payment services: An empirical study. Journal of Computer Information Systems. https://doi.org/10.1080/08874417.2016.1180649
[9] Egami, N., Fong, C., Grimmer, J., Roberts, M. E., & Stewart, B. (2022). How to make causal inferences using texts. Science Advances. https://doi.org/10.1126/sciadv.abg2652
[10] Fainusa, A. F., Nurcahyo, R., & Dachyar, M. (2019). Conceptual framework for digital wallet user satisfaction. 2019 IEEE 6th International Conference on Engineering Technologies and Applied Sciences (ICETAS). https://doi.org/10.1109/icetas48360.2019.9117285
[11] Furinto, A., Tamara, D., Hartono, D., & Simamora, E. (2023). Continuation use of the digital wallet using the extended ECM model in Indonesia. https://doi.org/10.46254/au01.20220079
[12] Genc-Nayebi, N., & Abran, A. (2016). A systematic literature review: Opinion mining studies from mobile app store user reviews. Journal of Systems and Software. https://doi.org/10.1016/j.jss.2016.11.027
[13] Gentzkow, M., Kelly, B., & Taddy, M. (2019). Text as data. Journal of Economic Literature. https://doi.org/10.1257/jel.20181020
[14] Grimmer, J., & Stewart, B. (2013). Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political Analysis. https://doi.org/10.1093/pan/mps028
[15] Guo, Y., Barnes, S. J., & Jia, Q. (2016). Mining meaning from online ratings and reviews: Tourist satisfaction analysis using latent Dirichlet allocation. Tourism Management. https://doi.org/10.1016/j.tourman.2016.09.009
[16] Guzmán, E., & Maalej, W. (2014). How do users like this feature? A fine-grained sentiment analysis of app reviews. https://doi.org/10.1109/re.2014.6912257
[17] Harman, M., Jia, Y., & Zhang, Y. (2012). App store mining and analysis: MSR for app stores. https://doi.org/10.1109/msr.2012.6224306
[18] Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. https://doi.org/10.1145/1014052.1014073
[19] Humbani, M., & Wiese, M. (2019). An integrated framework for the adoption and continuance intention to use mobile payment apps. International Journal of Bank Marketing. https://doi.org/10.1108/ijbm-03-2018-0072
[20] Jelodar, H., Wang, Y., Yuan, C., Feng, X., Jiang, X., Li, Y., & Zhao, L. (2018). Latent dirichlet allocation (LDA) and topic modeling: Models, applications, and a survey. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-018-6894-4
[21] Jha, N., & Mahmoud, A. (2019). Mining non-functional requirements from app store reviews. Empirical Software Engineering. https://doi.org/10.1007/s10664-019-09716-7
[22] Koto, F., Rahimi, A., Lau, J. H., & Baldwin, T. (2020). IndoLEM and IndoBERT: A benchmark dataset and pre-trained language model for Indonesian NLP. https://doi.org/10.18653/v1/2020.coling-main.66
[23] Koto, F., & Rahmaningtyas, G. Y. (2017). Inset lexicon: Evaluation of a word list for indonesian sentiment analysis in microblogs. https://doi.org/10.1109/ialp.2017.8300625
[24] Kumar, A., Adlakaha, A., & Mukherjee, K. (2018). The effect of perceived security and grievance redressal on continuance intention to use m-wallets in a developing country. International Journal of Bank Marketing. https://doi.org/10.1108/ijbm-04-2017-0077
[25] Kumar, A., Chakraborty, S., & Bala, P. K. (2023). Text mining approach to explore determinants of grocery mobile app satisfaction using online customer reviews. Journal of Retailing and Consumer Services. https://doi.org/10.1016/j.jretconser.2023.103363
[26] Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature. https://doi.org/10.1038/44565
[27] Leem, B., & Eum, S.-W. (2021). Using text mining to measure mobile banking service quality. Industrial Management & Data Systems. https://doi.org/10.1108/imds-09-2020-0545
[28] Luiz, W., Viegas, F., Alencar, R. O. de, Mourão, F., Salles, T., Carvalho, D. B. F., Gonçalves, M. A., & Rocha, L. (2018). A feature-oriented sentiment rating for mobile app reviews. https://doi.org/10.1145/3178876.3186168
[29] MacKinnon, J. G., & Webb, M. D. (2016). Wild bootstrap inference for wildly different cluster sizes. Journal of Applied Econometrics. https://doi.org/10.1002/jae.2508
[30] Mimno, D., Wallach, H., Talley, E. M., Leenders, M., & McCallum, A. (2011). Optimizing semantic coherence in topic modelsScholarWorks@UMassAmherst (University of Massachusetts Amherst).
[31] [31] Nayebi, M., Cho, H., & Ruhe, G. (2018). App store mining is not enough for app improvement. Empirical Software Engineering. https://doi.org/10.1007/s10664-018-9601-1
[32] Oh, Y. K., & Kim, J.-M. (2022). What improves customer satisfaction in mobile banking apps? An application of text mining analysis. ASIA MARKETING JOURNAL. https://doi.org/10.53728/2765-6500.1581
[33] Pang, B., & Lee, L. (2008). Opinion mining and sentiment analysis. Now Publishers, Inc. eBooks. https://doi.org/10.1561/9781601981516
[34] Paramita, E. D., & Cahyadi, E. R. (2024). The determinants of behavioral intention and QRIS use behavior as a digital payment method using the extended UTAUT model. Indonesian Journal of Business and Entrepreneurship. https://doi.org/10.17358/ijbe.10.1.132
[35] Parasuraman, A., Zeithaml, V. A., & Malhotra, A. (2005). E-s-QUAL. Journal of Service Research. https://doi.org/10.1177/1094670504271156
[36] Pranatawijaya, V. H., Sari, N. N. K., Rahman, R. A., Christian, E., & Geges, S. (2024). Unveiling user sentiment: Aspect-based analysis and topic modeling of ride-hailing and Google Play app reviews. Journal of Information Systems Engineering and Business Intelligence. https://doi.org/10.20473/jisebi.10.3.328-339
[37] Prasetyo, I. D., & Irawan, H. (2025). Assessing m-government service quality: A transformer-based sentiment and topic modeling analysis of Indonesia's police super app. 2025 13th International Conference on Cyber and IT Service Management (CITSM). https://doi.org/10.1109/citsm67730.2025.11291473
[38] Rachman, A., Julianti, N., & Arkoyah, S. (2024). Challenges and opportunities for QRIS implementation as a digital payment system in Indonesia. EkBis Jurnal Ekonomi Dan Bisnis. https://doi.org/10.14421/ekbis.2024.8.1.2134
[39] Röder, M., Both, A., & Hinneburg, A. (2015). Exploring the space of topic coherence measures. https://doi.org/10.1145/2684822.2685324
[40] Sihaloho, J. E., Ramadani, A., & Rahmayanti, S. (2020). Implementasi sistem pembayaran Quick Response Indonesia Standard untuk perkembangan UMKM di Medan. Jurnal Manajemen Bisnis. https://doi.org/10.38043/jmb.v17i2.2384
[41] Soelasih, Y., & Sumani, S. (2022). Factors influencing millennials' intention to continue using digital wallets in Indonesia. Binus Business Review. https://doi.org/10.21512/bbr.v13i3.8561
[42] Sulistiyani, D., Nurchayati, D., Nurchayati, D., & D, N. D. H. (2024). User experience of mobile banking application in Indonesia: New technology of banking. GLOBAL BUSINESS & FINANCE REVIEW. https://doi.org/10.17549/gbfr.2024.29.2.127
[43] Uncovska, M., Freitag, B., Meister, S., & Fehring, L. (2023). Rating analysis and BERTopic modeling of consumer versus regulated mHealth app reviews in Germany. Npj Digital Medicine. https://doi.org/10.1038/s41746-023-00862-3
[44] Webb, M. D. (2023). Reworking wild bootstrap‐based inference for clustered errors. Canadian Journal of Economics/Revue Canadienne d Économique. https://doi.org/10.1111/caje.12661
[45] Widodo, M., Irawan, M. I., & Sukmono, R. A. (2019). Extending UTAUT2 to explore digital wallet adoption in Indonesia. 2019 International Conference on Information and Communications Technology (ICOIACT). https://doi.org/10.1109/icoiact46704.2019.8938415
[46] Widyanto, H. A., Kusumawardani, K. A., & Yohanes, H. (2021). Safety first: Extending UTAUT to better predict mobile payment adoption by incorporating perceived security, perceived risk, and trust. Journal of Science and Technology Policy Management. https://doi.org/10.1108/jstpm-03-2020-0058
[47] Zhou, T. (2012). An empirical examination of continuance intention of mobile payment services. Decision Support Systems. https://doi.org/10.1016/j.dss.2012.10.034

Keywords:

E-Wallet, Digital Payment, Online Reviews, Topic Modeling, E-Service Quality, Indonesia JEL, G23, G41, M31, O33, L86.