Klasifikasi dan Pengaruh Trending Youtube Menggunakan Algoritma Neural Network dan Regresi Linear

  • Norhikmah Universitas amikom yogyakarta
  • Rumini Universitas AMIKOM Yogyakarta
Keywords: Klasifikasi, Trending Youtube, Neural Network

Abstract

The development of social media is very influential which includes Facebook, Instagram, Twitter, YouTube and others. One of them is the social media YouTube which has a very important role for the public and community leaders. Youtube provides very interesting content for those who have channels and those who do not. Trending or not a YouTube channel based on likes, dislikes, comments, and video views. Trending data from YouTube can be processed data. The data processing technique that can be used in the process is classification. Classification is a data processing technique that divides objects into classes. Using the backpropagation neural network algorithm in the classification process, which can determine Youtube trending with a very good and quite good ratio. a dataset of 40,880 obtained the best modeling obtained in neuron 10, layer 4, epoch 2000, with an MSE value of 0.03 and 87% validation, with a duration of 24 seconds, followed by a multiple linear regression test which resulted in the equation Y=0.788 + 4.914X1 + 9.458X2 - 1.977X3 - 4.418X4 + e where the more views and likes, the more trending youtube is, and the more dislikes and comments, the trending status of youtube decreases with a significance value of 0.000 which means it has a very significant relationship or at a strong level.

 

 

Author Biography

Rumini, Universitas AMIKOM Yogyakarta

 

 

Published
2023-01-30