Sentiment Analysis of Google Play Reviews of Online Lending Platforms in Indonesia
DOI:
https://doi.org/10.3991/itdaf.v4i3.62761Keywords:
sentiment analysis, machine learning, online lending, Google Play, classificationAbstract
Sentiment analysis is often useful for grouping sentiments and understanding the general perspective toward a particular topic. There are several models developed for online lending platforms. However, they do not focus on Indonesia, which might have unique characteristics compared to other countries. This paper presents a sentiment analysis model focusing on Indonesian online lending platforms. It features either multinomial naïve bayes, logistic regression, and support vector machine (SVM). Based on our evaluation of 10,000 reviews, our sentiment analysis model achieves approximately 85% precision and 90% recall. The model is highly effective. Our analysis of the reviews shows that while many borrowers appreciate the time efficiency and accessibility, some perceive the platforms as predatory, using aggressive and unethical debt-collection tactics.
References
[1] T. Balyuk and S. Davydenko, “Reintermediation in FinTech: Evidence from Online Lending,” Journal of Financial and Quantitative Analysis, vol. 59, no. 5, pp. 1997–2037, 2024.
[2] R. H. Huang, “Online P2P Lending and Regulatory Responses in China: Opportunities and Challenges,” European Business Organization Law Review 2018 19:1, vol. 19, no. 1, pp. 63–92, 2018.
[3] B. Dömötör, F. Illés, and T. Ölvedi, “Peer-to-peer lending: Legal loan sharking or altruistic investment? Analyzing platform investments from a credit risk perspective,” Journal of International Financial Markets, Institutions and Money, vol. 86, p. 101801, 2023.
[4] Y. Yoon, Y. Li, and Y. Feng, “Factors affecting platform default risk in online peer-to-peer (P2P) lending business: an empirical study using Chinese online P2P platform data,” Electronic Commerce Research 2018 19:1, vol. 19, no. 1, pp. 131–158, 2018.
[5] M. Wankhade, A. C. S. Rao, and C. Kulkarni, “A survey on sentiment analysis methods, applications, and challenges,” Artificial Intelligence Review 2022 55:7, vol. 55, no. 7, pp. 5731–5780, 2022.
[6] M. Mujahid et al., “Sentiment Analysis and Topic Modeling on Tweets about Online Education during COVID-19,” Applied Sciences, vol. 11, no. 18, p. 8438, 2021.
[7] H. Toba, O. Karnalim, M. C. Johan, T. Tada, Y. M. Djajalaksana, and T. Vivaldy, “Inappropriate benefits and identification of ChatGPT misuse in programming tests: A controlled experiment,” in International Conference on Interactive Collaborative Learning, 2023, pp. 520–531.
[8] Y. A. Mulyono and O. Karnalim, “Sentiment Analysis and Topic Modelling for Academic Integrity in the Era of AI,” IETI Transactions on Data Analysis and Forecasting (iTDAF), vol. 3, no. 3, pp. 61–73, 2025.
[9] I. Întorsureanu, S. V. Oprea, A. Bâra, and D. Vespan, “Generative AI in Education: Perspectives Through an Academic Lens,” Electronics., vol. 14, no. 5, p. 1053, 2025.
[10] Z. Song, C. Lai, X. Huang, and C. H. Lin, “What teachers discuss and how they perceive and feel: Topic modeling and sentiment analysis of a generative artificial intelligence learning group on facebook,” Comput. Educ., vol. 251, p. 105654, 2026.
[11] M. K. Hassan, F. A. Hudaefi, and R. E. Caraka, “Mining netizen’s opinion on cryptocurrency: sentiment analysis of Twitter data,” Studies in Economics and Finance, vol. 39, no. 3, pp. 365–385, 2022.
[12] N. Aslam, F. Rustam, E. Lee, P. B. Washington, and I. Ashraf, “Sentiment Analysis and Emotion Detection on Cryptocurrency Related Tweets Using Ensemble LSTM-GRU Model,” IEEE Access, vol. 10, pp. 39313–39324, 2022.
[13] J. V. Naga Ramesh, V. Veeraiah, D. Bhattacharya, V. Jain, S. K. Jain, and A. Gupta, “Twitter Sentiment Mining for Marketing Decision-Making in Blockchain-Based Digital Assets,” in International Conference on Innovations and Emerging Technologies in AI and Communication Systems: Unifying AI and Communication for a Smarter Tomorrow, Institute of Electrical and Electronics Engineers Inc., 2025, pp. 1005–1011.
[14] A. Al-Adaileh, M. Al-Kfairy, M. Tubishat, and O. Alfandi, “A sentiment analysis approach for understanding users’ perception of metaverse marketplace,” Intelligent Systems with Applications, vol. 22, p. 200362, 2024.
[15] S. Khan, R. Singh, H. K. Baker, and G. Jain, “Public Perception of Online P2P Lending Applications,” Journal of Theoretical and Applied Electronic Commerce Research 2024, Vol. 19, Pages 507-525, vol. 19, no. 1, pp. 507–525, 2024.
[16] B. Niu, J. Ren, A. Zhao, and X. Li, “Lender Trust on the P2P Lending: Analysis Based on Sentiment Analysis of Comment Text,” Sustainability, vol. 12, no. 8, p. 3293, 2020.
[17] M. Wang, G. Zhan, K. K. Lai, L. Zhang, and L. Meng, “Posts and reviews in P2P online lending platforms: a sentiment analysis and cross-culture comparison,” Behaviour & Information Technology, vol. 41, no. 16, pp. 3591–3597, 2022.
[18] M. Hofmann and R. Klinkenberg, RapidMiner: Data Mining Use Cases and Business Analytics Applications - Google Books. CRC Press, 2016.
[19] W. B. Croft, D. Metzler, and T. Strohman, Search Engines: Information Retrieval in Practice. 2010.
[20] Zhi-Hua Zhou, Machine Learning. Springer, 2021.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Hendry Joellyo Pattiasina, Jason Nathanael Kosasih, Nur Bagus Sajiwo, Christian Batista Evro Irawadi, Oscar Karnalim, Gabriel Xiao-Guang Yue
This work is licensed under a Creative Commons Attribution 4.0 International License.
