Analisis Perbandingan Algoritma Machine Learning Terhadap Sentimen Analis Pemindahan Ibu Kota Negara

Arif Rahman Hakim (Universitas Nusa Mandiri)
Windu Gata (Universitas Nusa Mandiri)
Alda Zevana Putri Widodo (Universitas Nusa Mandiri)
Oky Kurniawan (Universitas Nusa Mandiri)
Arief Rama Syarif (Universitas Nusa Mandiri)

Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi)
Vol 7 No 2 (2023): APRIL-JUNE 2023

The Indonesian nation was enlivened with news about the relocation of the State Capital (IKN). The government's plan to move IKN is based on Indonesia's vision and mission in 2045, namely advanced Indonesia. Twitter is one of the microblogging communication tools used to express opinions. Various algorithms have been used to analyze sentiment towards an opinion such as Support Vector Machine, Naive Bayes and Random Forest. This study aims to compare the performance of three classification algorithms, namely Support Vector Machine, Naïve Bayes and Random Fores. The highest accuracy results are using the Support Vector Machine algorithm and added with the Synthetic Minority Oversampling Technique Method (SMOTE) feature of 82.82%, Precision 79.34%, Recall 88.75%, 87.78% and ROC AUC 82.82%. Naive Bayes accuracy is 81.18%, Precision 84.89%, Recall 75.86%, 80.13% and ROC AUC 81.18%. and Random Forest accuracy of 79.55, precision 84.48%, recall 72.39%, 77.97% and ROC AUC 77.55%.