Comparative analysis of Indonesian news validity detection accuracy using machine learning

Rachelita Embun Safira (Universitas Negeri Yogyakarta)
Akhsin Nurlayli (Universitas Negeri Yogyakarta)

Journal of Engineering and Applied Technology
Vol 4, No 1 (2023): (March)

Hoax news prediction is required to anticipate the growth of hoax news in social media. This study aimed to determine the best model for predicting whether the news is a hoax or valid based on the dataset taken from Kaggle.com. This study used several data prediction methods: Support Vector Machine (SVM), Random Forest, Logistic Regression, and Naïve Bayes. After the research processes and data testing, the results showed that the best model for predicting hoax news was SVM, which had the highest accuracy, precision, and recall score of the others.