Abstract
The distribution of information in the form of online news is so massive in the wider community, that it is difficult to distinguish between haox news and positive news. So that a classification is needed regarding public sentiment about the implementation of elections using mainstream media news article data using 1064 dataset test data. The methods used in this study are the naive Bayes algorithm, the random forest algorithm, and the support vector machine algorithm. The test model uses smote where the performance results are carried out by the algorithm used using smote and not using smote, where random forest produces an accuracy of 91.88%, while without using a smote support vector machine it produces an accuracy of 92.05%.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
