PENERAPAN DATA MINING UNTUK MEMPREDIKSI KLASIFIKASI JUMLAH PEMBACA SEBUAH ARTIKEL PADA SITUS BERANDA.CO.ID MENGGUNAKAN ALGORITMA BAYESIAN CLASSIFICATION

YOGA PRATAMA, NIM. 12650014 (2016) PENERAPAN DATA MINING UNTUK MEMPREDIKSI KLASIFIKASI JUMLAH PEMBACA SEBUAH ARTIKEL PADA SITUS BERANDA.CO.ID MENGGUNAKAN ALGORITMA BAYESIAN CLASSIFICATION. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (PENERAPAN DATA MINING UNTUK MEMPREDIKSI KLASIFIKASI JUMLAH PEMBACA SEBUAH ARTIKEL PADA SITUS BERANDA.CO.ID MENGGUNAKAN ALGORITMA BAYESIAN CLASSIFICATION) 12650014_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf Download (3MB) | Preview
	Text (PENERAPAN DATA MINING UNTUK MEMPREDIKSI KLASIFIKASI JUMLAH PEMBACA SEBUAH ARTIKEL PADA SITUS BERANDA.CO.ID MENGGUNAKAN ALGORITMA BAYESIAN CLASSIFICATION) 12650014_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf Restricted to Registered users only Download (3MB)

Abstract

Sometimes, the number readers of article from websites is not stabilize. One of them is Beranda.co.id site. There are some element that can influence, one of them is the writing element of article. It is includes the number of words, the number of tags, and the Yoast SEO value. The problem can be solve if Beranda.co.id site can predict the potential article that have many readers classification. This research applies bayesian classification algorithm into an application that can be used to calculate a prediction of an article classification. This algorithm was chosen because it is shown to have a high speed and accuracy when applied into the database with big data. The prediction calculation obtains a value of prediction accuracy. This value of prediction accuracy further is conducted interpretation process to be an information or knowledge that can be used by Beranda.co.id in using the application. This research is successful in applying bayesian classification algorithm into the application. The results of the first scenario prediction accuracy percentage is 56%, the second scenario is 62%, the third scenario is 42%, and the fourth scenario is 60%. While the knowledge which is got are normal data can produce results better prediction accuracy and the prediction accuracy getting decreased goes hand in hand with the expired date of training data.

Share this knowledge with your friends :

Actions (login required)

View Item