<![CDATA[This research examines public sentiment toward online lending services in Indonesia by analyzing opinions from social media platforms, specifically YouTube and Twitter, collected from January 2021 to January 2024. The objective of this study is to develop an accurate sentiment classification system that can effectively categorize public opinions into positive, negative, and neutral sentiments, thereby providing valuable insights for regulatory bodies and service providers to understand consumer concerns and improve service quality. The collected data underwent thorough preprocessing, semi-automatic labeling, and Term Frequency-Inverse Document Frequency (TF-IDF) weighting. Four classification models were evaluated: Support Vector Machine (SVM) with Linear, Polynomial, and Radial Basis Function (RBF) kernels, and Logistic Regression. Results demonstrate that Linear SVM achieves the best performance with an accuracy of 90.17% and an F1-score of 0.902, effectively categorizing sentiments across all classes while excelling particularly in negative and neutral categories. The expected impact of this analysis is to provide evidence-based recommendations for policymakers in financial technology regulation and help online lending service providers understand consumer satisfaction levels to improve their service delivery. This study offers valuable insights for service providers and regulatory bodies seeking to better understand and address public concerns in this domain.]]>
Copyrights © 2025
