With the development of technology, many applications and social media make it easier for users to do various desires, one of which is borrowing money online on the Online Loan Application with easy terms. The convenience provided causes many violations committed by irresponsible people, such as the breach of important information and data of online loan application users. This causes many people to express their comments and opinions on social media, especially on twitter. Sentiment analysis is conducted to see the tendency of public opinion to fall into negative, neutral, or positive sentiment. Furthermore, public opinion will be classified using two algorithms, namely the Support Vector Machine and Decision Tree algorithms. The aim of this research is to compare the performance of SVM and Decision Tree classification algorithms on the tendency of public opinion on twitter regarding online loans. Furthermore, optimization is carried out using SMOTE to optimize the accuracy of the two algorithms. The results obtained neutral sentiment as much as 78.96%, positive sentiment as much as 14.98%, and negative sentiment as much as 6.06%, people are more inclined to neutral sentiment. Then classification using SVM gets an accuracy of 87% and on Decision Tree gets an accuracy of 89%.. Then to optimize the performance results of the two algorithms, optimization using SMOTE is carried out. After SMOTE optimization, the accuracy produced by SVM is 99% and Decision Tree is 97%. Optimization using SMOTE proves that the SVM algorithm is better than Decision Tree.
Copyrights © 2023