Cluster Analysis of Musical Attributes for Top Trending Songs

dc.contributor.author	Al-Beitawi , Zayd
dc.contributor.author	Salehan, Mohammad
dc.contributor.author	Zhang, Sonya
dc.date.accessioned	2020-01-04T07:09:37Z
dc.date.available	2020-01-04T07:09:37Z
dc.date.issued	2020-01-07
dc.description.abstract	Music streaming services like Spotify have changed the way consumers listen to music. Understanding what attributes make certain songs trendy can help services to create a better customer experience as well as more effective marketing efforts. We performed cluster analysis on Top 100 Trending Spotify Song of 2017, with ten attributes, including danceability, energy, loudness, speechiness, acousticness, instrumentalness, Liveness, valence, tempo, and duration. The results show that music structures with high danceability and low instrumentalness increase the popularity of a song and lead them to chart-topping success.
dc.format.extent	7 pages
dc.identifier.doi	10.24251/HICSS.2020.017
dc.identifier.isbn	978-0-9981331-3-3
dc.identifier.uri	http://hdl.handle.net/10125/63756
dc.language.iso	eng
dc.relation.ispartof	Proceedings of the 53rd Hawaii International Conference on System Sciences
dc.rights	Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri	https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject	AI and Cognitive Assistants in Collaboration
dc.subject	clustering
dc.subject	music streaming
dc.subject	recommender systems
dc.title	Cluster Analysis of Musical Attributes for Top Trending Songs
dc.type	Conference Paper
dc.type.dcmi	Text

Now showing 1 - 1 of 1