Pardede, Jasman and Ibrahim, Raka Gemi (2020) Implementasi Long Short-Term Memory Untuk Identifikasi Berita Hoax Berbahasa Inggris Pada Media Sosial. Journal of Computer Science and Informatics Engineering (J-Cosine), 4 (2). ISSN P-ISSN:2540-8895; E-ISSN:2541-0806 ;

Preview

Text 8. Implementasi Long Short-Term Memory untuk Identifikasi Berita Hoax Berbahasa Inggris pada Media Sosial.pdf Download (858kB) | Preview

Abstract

Hoax or fake news spreads very fast on social media. The news can influence readers and poisoning their mind. It is important to identify the hoax news broadcasted on social media. Some methods to predict hoax are to use Support Vector Classifier, Logistic Regression, and MultinomialNaiveBayes. In this study, we applied Long Short-Term Memory to identify the hoaxes. System performance was measured based on the precision, recall, accuracy, and F-Measure scores. The experimental results, conducted on the hoaxes data obtained the average value of precision, recall, accuracy, and F-Measure of 0.94, 0.96, 0.95, and 0.95 respectively. The results shows that the proposed Long Short-Term Memory has better performance compared to the latest method.

Actions (login required)

View Item