Analisis Perbandingan Algoritma Svm Dan Knn Untuk Klasifikasi Anime Bergenre Drama

Vika Vitaloka Pramansah, Dadang Iskandar Mulyana, Titi Silfia


There are many genres of anime such as drama, action, romance, comedy, and so on. However, because there are so many anime genres, it is quite difficult for viewers to find anime whose genre they like, such as the drama genre which tells about everyday human life which is quite light in nature. From these problems, a classification method is needed to classify anime that belongs to the drama genre. Classification has several algorithms including Support Vector Machine (SVM) and K-Nearest Neighbors (KNN). SVM and KNN algorithms have been widely used and have a good level of accuracy. In this study, a comparative analysis will be carried out between the two algorithms, the dataset used is 12,294 data and 2 genre classes, namely drama and non-drama, the attribute of the anime dataset is 7. The results obtained in this study indicate that the K-Nearest Neighbors Algorithm (KNN) ) get a training accuracy value of 100% and a test accuracy value of 84%. And also the Support Vector Machine (SVM) algorithm gets a training accuracy value of 83% and a test accuracy value of 82%. The results of the accuracy values of the two algorithms indicate that the K-Nearest Neighbors (KNN) algorithm has a better testing accuracy than the Support Vector Machine (SVM) with a fairly thin difference between the two algorithms.

Teks Lengkap:



  • Saat ini tidak ada refbacks.

Program Studi Teknik Informatika Unversitas Janabadra