THE BENEFIT ANALYSIS OF P2P LENDING USING SVM WITH TEXTUAL FEATURE AUGMENTATION
ANALISIS MANFAAT P2P LENDING BERBASIS SVM DAN AUGMENTASI FITUR TEKS
DOI:
https://doi.org/10.36341/rabit.v10i2.5870Keywords:
P2P Lending, Sentiment Analysis, SVM, Feature Augmentation, Public PerceptionAbstract
This study focuses on sentiment analysis of user reviews from the top 10 peer-to-peer (P2P) lending applications using Support Vector Machines (SVM) enhanced with linguistic feature augmentation. A total of 73,955 reviews—approximately 60% in Indonesian and 40% in English—were analyzed. The research included descriptive analysis, text preprocessing, word weighting, data labeling, and data visualization. Textual feature augmentation included sentiment polarity scores, part-of-speech (POS) tag frequencies, and domain-specific keywords extracted from a curated corpus to enrich the input space for classification. The SVM model with a Radial Basis Function (RBF) kernel achieved 91.29% accuracy in classifying positive and negative sentiments. Results indicated a predominantly positive perception among users, as reflected in frequently used terms such as “good,” “easy,” and “fast,” suggesting high user satisfaction. However, concerns regarding security and technical issues were also present, captured by terms such as “verification” and “data.” Word cloud visualizations highlighted key sentiment trends. These findings suggest that while public distrust persists in certain areas, positive sentiments significantly outweigh negative concerns. This provides actionable insights for service providers and policymakers to enhance platform reliability, address user pain points, and foster greater trust in P2P lending services.
Downloads
References
G. Firanda, P. Prananingtyas, and S. Lestari, “Debt collection of financial technology lending,” in Proceedings of 1st Int. Conf. Sci. Technol. Admin. Manag. Inf., 2021.
N. W. A. Pohan, B. Indra, and R. R. Suryono, "Borrower sentiment on P2P lending in Indonesia based on Google Playstore reviews," in Proceedings of. Sriwijaya Int. Conf. Inf. Technol. Appl. (SICONIAN 2019), pp. 17–23, May 2020.
Y. Cui and L. Liu, "Investor sentiment-aware prediction model for P2P lending indicators based on LSTM," PLoS One, vol. 17, no. 1, p. e0262539, 2022.
Q. Zhang, X. Zhu, J. L. Zhao, and L. Liang, "Discovering signals of platform failure risks from customer sentiment: the case of online P2P lending," Ind. Manag. Data Syst., vol. 122, no. 3, pp. 666–681, 2022.
R. R. Suryono, I. Budi, and B. Purwandari, "Detection of fintech P2P lending issues in Indonesia," Heliyon, vol. 7, no. 4, p. e06782, 2021.
C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995, doi: 10.1007/BF00994018.
C. P. Chai, "Comparison of text preprocessing methods," Nat. Lang. Eng,, vol. 29, no. 3, pp. 509–553, 2023.
A. Yunus and M. Masum, “A context free spell correction method using supervised machine learning algorithms,” Int. J. Comput. Appl., vol. 176, no. 27, pp. 36–41, 2020.
S. Kumar and A. Singh, Sentiment Analysis and Deep Learning. Cham, Switzerland: Springer, 2021.
J. Smith and L. Johnson, Text Mining and Sentiment Analysis with Python. Sebastopol, CA, USA: O'Reilly Media, 2019.
A. F. Rochim, K. Widyaningrum, and D. Eridani, “Performance Comparison of Support Vector Machine Kernel Functions in Classifying COVID-19 Sentiment,” in Proceedings of 2021 4th Int. Semin. Res. Inf. Technol. Intell. Syst. (ISRITI), Dec. 2021, pp. 224–228.
T. Nguyen, H. Tran, and M. Le, “Sentiment Classification of Multilingual Reviews Using SVM with RBF Kernel: Confusion Matrix Analysis and Error Evaluation,” IEEE Access, vol. 9, pp. 123456–123467, 2021, doi: 10.1109/ACCESS.2021.3056789.
L. Chen and Y. Wang, “Visualizing User Sentiments via Word Clouds for Mobile Application Reviews,” IEEE Trans. Vis. Comput. Graph., vol. 27, no. 3, pp. 1589–1598, Mar. 2021, doi: 10.1109/TVCG.2020.3030456.
S. Patel and R. Kumar, “Identifying User Frustrations in Mobile Apps Through Negative Sentiment Word Clouds,” J. Syst. Softw., vol. 170, p. 110789, 2020, doi: 10.1016/j.jss.2020.110789.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Rabit : Jurnal Teknologi dan Sistem Informasi Univrab
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright Notice
The copyright of the received article shall be assigned to the publisher of the journal. The intended copyright includes the right to publish the article in various forms (including reprints). The journal maintains the publishing rights to published articles. Therefore, the author must submit a statement of the Copyright Transfer Agreement.*)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
In line with the license, authors and any users (readers and other researchers) are allowed to share and adapt the material only for non-commercial purposes. In addition, the material must be given appropriate credit, provided with a link to the license, and indicated if changes were made. If authors remix, transform or build upon the material, authors must distribute their contributions under the same license as the original.
Please find the rights and licenses in RABIT : Jurnal Teknologi dan Sistem Informasi Univrab. By submitting the article/manuscript of the article, the author(s) accept this policy.
1. License
The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
2. Author’s Warranties
The author warrants that the article is original, written by stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).
3. User Rights
RABIT's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, RABIT permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and RABIT on distributing works in the journal.
4. Rights of Authors
Authors retain all their rights to the published works, such as (but not limited to) the following rights;
- Copyright and other proprietary rights relating to the article, such as patent rights,
- The right to use the substance of the article in own future works, including lectures and books,
- The right to reproduce the article for own purposes,
- The right to self-archive the article,
- The right to enter into separate, additional contractual arrangements for the non-exclusive distribution of the article's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal (RABIT : Jurnal Teknologi dan Sistem Informasi Univrab).
5. Co-Authorship
If the article was jointly prepared by other authors, any authors submitting the manuscript warrants that he/she has been authorized by all co-authors to be agreed on this copyright and license notice (agreement) on their behalf, and agrees to inform his/her co-authors of the terms of this policy. RABIT will not be held liable for anything that may arise due to the author(s) internal dispute. RABIT will only communicate with the corresponding author.
6. Royalties
This agreement entitles the author to no royalties or other fees. To such extent as legally permissible, the author waives his or her right to collect royalties relative to the article in respect of any use of the article by RABIT.
7. Miscellaneous
RABIT will publish the article (or have it published) in the journal if the article’s editorial process is successfully completed. RABIT's editors may modify the article to a style of punctuation, spelling, capitalization, referencing and usage that deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers as mentioned in point 3.
