Comparison Of Naive Bayes And Support Vector Machine For Detecting Hoax In Indonesian Tweet Case Study Of Tweet Covid-19

The rise of the infodemic containing false news or hoaxes and rumors about Covid-19 in society can worsen the pandemic situation itself. In addition, the infodemic can also be fatal to cause loss of life. This phenomenon that often appears in the community, such as drinking a cup of hot tea that has been dripped with eucalyptus oil can cure Covid-19 positive patients, making people believe that they ignore the health protocol recommendations. Therefore, to find out the truth or discrepancy of information in tweets, we can create a hoax detection system to minimize the emergence of hoax news. This study compares the Naive Bayes algorithm and the Support Vector Machine with a case study of Covid-19 tweets in Indonesian. The dataset collected is 500 tweets by manual labeling. For testing using the confusion matrix, the Naive Bayes method gets 78% accuracy and the support vector machine method gets 80% accuracy. The results of these tests prove that it can detect the truth of information or tweet using the support vector machine method with the highest accuracy.