Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Buchori Anantya Firdaus
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Klusterisasi Popularitas Artist pada Playlist Today's Top Hits Menggunakan Metode K-Means dengan Integrasi Spotify Web API dan Teknologi Amazon SageMaker Buchori Anantya Firdaus; Dian Eka Ratnawati; Buce Trias Hanggara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 1 (2021): Januari 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In a high-volume market like Spotify, it's important to understand what makes an artist valuable. One way to measure the success of a song or album is to check the rankings and charts. Spotify, for example, publishes several charts. Notably, Today's Top Hits, the first number one playlist in the Spotify ecosystem, has 18.2 million followers (about 7.5 million more than the second place playlist, Spotify Global Top 50), and has about 2.5 million daily active listeners. The use of the K-Means Algorithm because this method can handle large music data effectively. The results of the clustering are expected to be used for Record Labels in showing the proportion of Artist popularity that is included in the Today's Top Hits Playlist which is expected to find out what percentage of an Artist who has a certain followers and popularity to enter the Playlist, or maybe to find out the Artist segmentation on the Playlist. As a result, in the clustering process using the K-Means method, it was found that the proportion of artists on Today's Top Hits Playlist was 28.79% for Very Popular, 42.42% for Popular, 28.79% for Unpopular. Meanwhile, in the cluster testing process using the Silhouette Coefficient, the value is 0.536, which means that the results of the cluster are well formed. Meanwhile, using the Davies-Bouldin Index shows the value is 0.554, which means that the results of the cluster are well formed too.
Co-Authors Buce Trias Hanggara Dian Eka Ratnawati