Analisis Pengelompokan Atribut Musik menggunakan Algoritma K-means++ untuk Top Hits Spotify dari tahun 2000 hingga 2019

This study aims to analyze the clustering of musical attributes of songs that became hits on Spotify during the period from 2000 to 2019 using the K-means++ algorithm. The dataset used in this research was obtained from Kaggle, titled "Top Hits Spotify from 2000-2019," and includes musical attributes such as duration, popularity, danceability, energy, key, loudness, mode, speechiness, acousticness, instrumentalness, liveness, valence, and tempo. The results of this study show that there are three distinct clusters based on the musical attributes. Additionally, this study reveals that musical attributes such as high energy, loudness, and valence can influence a song's success. This indicates that musical characteristics like energy levels, loudness, and happiness can play a significant role in attracting audience interest and increasing a song's popularity.