Penerapan Algoritma Support Vector Machine (SVM) dengan TF-IDF N-Gram untuk Text Classification

Syntax Journal of Informatics is an information system that contains a collection of scientific articles managed by the Informatics Study Program of Singaperbangsa Karawang University. Currently, Syntax Journal of Informatics does not have a feature for categorizing scientific articles based on their focus and scope. The research is conducted to classify scientific articles into categories according to focus and scope contained on Syntax Journal of Informatics’ page automatically by utilizing the text mining process. Text mining is a process that aims to get important information from the text. The method used in the research is Knowledge Discovery in Database (KDD) with stages of data selection, preprocessing, transformation, modeling and evaluation. This study will compare the classifications based on the title of the article. The algorithm used is the Support Vector Machine (SVM) using four SVM kernels, including the linear kernel, polynomial kernel, sigmoid kernel and RBF kernel. Data are divided into four scenarios by using traintestsplit, namely 60:40, 70:30, 80:30 and 90:10. The results of the study after testing the model are measured by of Accuracy, Precision, Recall and F-measure. The best results are accuracy of 70%, precision of 75%, recall of 69% and fmeasure of 71% in the 90:10 comparison scenario and linear kernel.