Comparison of Support Vector Machine and Random ForestAlgorithms for Analyzing Online Loans on Twitter social media

Abstract

Online loans represent a form of financial service wherein
borrowers can apply for loans through digital platforms
without the need to visit physical offices. The application,
approval, and disbursement processes are conducted online,
leveraging technology to facilitate financial access and
transactions. However, some online lending services impose
high-interest rates, resulting in a significant financial burden
for borrowers. Moreover, there are instances of inappropriate
debt collection practices, such as contacting the borrower's
friends or family, leading to discussions and comments on
social media platforms like Twitter. This research aims to
analyze the patterns of comments in Indonesian society
regarding online lending. The study utilizes sentiment
analysis and compares machine learning algorithms to assess
their accuracy. The algorithms employed in this study are
Support Vector Machine (SVM) and Random Forest. The
results indicate that the SVM algorithm achieves an accuracy
of 93.85%, while Random Forest achieves an accuracy of
91.62%.