Implementasi Long Short-Term Memory untuk Identifikasi Berita Hoax Berbahasa Inggris pada Media Sosial

Abstract

Hoax or fake news spreads very fast on social media. The news can influence readers and be a poison of the mind. Problems like this must be resolved in a strategic way to identify the news that is read that is disseminated on social media. Some of the methods proposed to predict hoax are to use Support Vector Classifier, Logistic Regression, and MultinomialNaiveBayes. In this study, the researchers applied Long Short-Term Memory to identify hoax. System performance is measured based on the value of precision, recall, accuracy, and F-Measure. Based on the results of experiments conducted on the hoax data obtained the average value of precision, recall, accuracy, and F-Measure respectively 0.94, 0.96, 0.95, and 0.95. Based on the experimental results it was found that the proposed Long Short-Term Memory has better performance compared to the state-of-the-art methods method.