Perbandingan Algoritma Random Forest Classifier, Support Vector Machine dan Logistic Regression Clasifier Pada Masalah High Dimension (Studi Kasus: Klasifikasi Fake News)

Fake news is false information that looks like it is true. News can also be said as a political weapon whose truth cannot be accounted for which is spread intentionally to achieve a certain goal. Classification of news texts requires calculating a method for each word in the document. Each word processed per document means that the number of data dimensions is equal to the number of words. The more the number of words in a document, the more the number of dimensions in each data (high dimension). The large number of dimensions (high dimension), causes the model-making process (training) to be long and the shortcomings are also clearly visible in seeing the similarity of documents (document similarity). The dataset used in this study amounted to 20000 and 17 attributes. The method used in this study uses a Random Forest Classifier (RFC), Support Vector Machine (SVM) and Logistic Regression (LR) with high dimensions and the results of this study are to obtain a comparison of the accuracy values for each method used