Ensemble Learning Approach on Indonesian Fake News Classification
Herley Shaori Al-Ash, Mutia Fadhila Putri, Petrus Mursanto, Alhadi Bustamam · 2019
The news is information about a recently changed situation or a recent event. Serving as popular media information the internet has the power spread the news not only real news but fake news as well. We propose an ensemble learning approach on Indonesian fake news in order to separate fake news from the real one and to tackle imbalanced data problem which we face on the given dataset. Our experiment result shows that random forest classifier as the ensemble classifier which obtained 0.98 f1-score is superior to multinomial naive bayes and support vector machine as non-ensemble classifiers which achieve 0.43 and 0.74 f1-score respectively across 660 evaluation documents. We also compare our result against other research that using the same data and our approach achieved better results.