<![CDATA[With the rapid development of information technology, especially in Indonesia, information is more easily obtained through online media. Therefore, the dissemination of information in online media becomes uncontrollable and a lot of information is not in accordance with the facts or can be said to be a hoax. Readers should be more careful when reading news headlines to avoid hoaxes. The purpose of this research is to find out how to apply the K-Nearest Neighbor (KNN) algorithm in classifying news including hoaxes or not hoaxes. In the process, the classification of hoaxes or non-hoaxes uses the KDD method in text mining and goes through several stages, namely preprocessing, word weighting with TF-IDF and classification using the KNN algorithm. There are 3 scenarios in the data split process, namely 90:10, 80:20, and 70:30. Evaluation is done by using a confusion matrix. The results of this study obtained the highest accuracy of 93.33% with a k value of 3 in the 90:10 scenario. So, the K-Nearest Neighbor algorithm is suitable for classifying hoax news titles.]]>
Copyrights © 2022
