PENERAPAN METODE RANDOM FOREST DALAM MENDETEKSI BERITA HOAX

Abstract

Hoax is information that is not true. The Ministry of Communication and Informatics (Kominfo) found that there was 2,099 hoax news that was spread thousands of times via social media. This generally impacts the community so it can lead to a crisis of confidence in the government. This arises because many message recipients have different literacy levels, which will affect how people analyze the information conveyed. This research uses the Random Forest method, which is used to classify large amounts of data to detect hoax news. The research results show that the Random Forest method is proven to be able to classify hoax news based on data that has been weighted and entered into the system. From the results of the study using 200 data sets, which were divided by 80% in the form of training data and 20% of testing data, the classification results obtained from the testing data were in the form of 28 positive sentiments and 23 negative sentiments with an accuracy rate of 98%.