Cluster Analysis of Musical Attributes for Top Trending Songs

Al-Beitawi, Zayd; Salehan, Mohammad; Zhang, Sonya

doi:10.24251/hicss.2020.017

Cited by 4 publications

(2 citation statements)

References 10 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Music-related datasets are the base for several real-world applications within the MIR field. For instance, Al-Beitawi et al [2020] use K-Means in acoustic features from Spotify to uncover structural patterns related to the songs' popularity. Also, Roy et al [2020] use cluster analysis to assess musical note structures in Indian classical music.…”

Section: Existing Music Datasetsmentioning

confidence: 99%

Musical Success in the United States and Brazil: Novel Datasets and Temporal Analyses

Oliveira

Barbosa²,

Melo³

et al. 2022

jidm

View full text Add to dashboard Cite

Music is not only a worldwide essential cultural industry but also one of the most dynamic. The increasing volume of complex music-related data defines new challenges and opportunities for extracting knowledge, benefiting not only different music segments but also the Music Information Retrieval research field. In this article, we assess musical success in the United States and Brazil, two of the biggest music markets in the world. We first introduce MUHSIC and MUHSIC-BR, two novel datasets with enhanced success information that combine chart-related data with acoustic metadata to describe the temporal evolution of musical careers. Then, we use such enriched and curated data to cluster artists according to their success level by considering their high-impact periods (hot streaks). Our results reveal three groups with distinct success behavior over time. Furthermore, Brazil and the US present specific music success patterns regarding artists and genres, reflecting the importance of analyzing regional markets individually.

show abstract

Section: Existing Music Datasetsmentioning

confidence: 99%

Musical Success in the United States and Brazil: Novel Datasets and Temporal Analyses

Oliveira

Barbosa²,

Melo³

et al. 2022

jidm

View full text Add to dashboard Cite

show abstract

“…Kita tahu bahwa seorang penyanyi tentunya selalu memberikan variasi terhadap musiknya namun tetap dengan mempertahankan identitas uniknya. Hal inilah yang menjadi permasalahan menarik, bagaimana kita bisa memberikan label artist music berdasarkan identitas uniknya tersebut (karakteristik) (Al-Beitawi et al, 2020).…”

Section: Pendahuluanunclassified

Analisis Klasifikasi Artist Music Menggunakan Model Regresi Logistik Biner Dan Analisis Diskriminan

Dani

RATNASARI²,

NI'MATUZZAHROH³

et al. 2022

Jambura J. Probab. Stat.

View full text Add to dashboard Cite

Characteristics of a song are an important aspect that must be kept authentic by a singer. Using the Spotify API feature, we can extract the characteristics or elements of a song sung by a singer. There are eight (8) elements that we can get from the extraction of a song, namely: Danceability, Energy, Loudness, Speechiness, Acousticness, Liveness, Valence, and Tempo. Based on the extraction results, we can label the music artist using the classification analysis method. In this study, the labels are music artists, namely Ariana Grande and Taylor Swift. This study aims to obtain the classification of music artist labels using binary logistic regression methods and discriminant analysis. The response variable used in this study is Artist Music (Y) which is categorized into two categories, namely Ariana Grande (Y=0) and Taylor Swift (Y=1). The data will be divided into training and testing data with the proportion of data 90:10 and 80:20. Based on the results of the analysis, the binary regression model that was built, with the proportion of training testing data that is 90:10 has a classification accuracy for data testing of 90.00%.

show abstract