Analisis Sentimen Twitter Terhadap Program MBKM Menggunakan Decision Tree dan Support Vector Machine

Lita Astri Pramesti (Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta)
Nunik Pratiwi (Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta)

JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
Vol 4 No 4 (2023): Juli 2023

The purpose of this research is to analyze Twitter users' opinions on the MBKM program using Decision Tree and Support Vector Machine. The study utilized 849 data with a dataset ratio of 80% for training and 20% for testing. In the dataset, there were 524 instances of positive sentiment and 320 instances of negative sentiment. This indicates that Twitter users' opinions towards the MBKM program tend to be positive. The research evaluation results showed that the Support Vector Machine achieved an accuracy of 84.76%, which is higher than the accuracy of 72.86% obtained by the Decision Tree. Based on these results, it can be concluded that the Support Vector Machine algorithm outperforms the Decision Tree in sentiment analysis of the MBKM program. The findings of this research are expected to provide input for the development of the program.