A Model for Predicting Music Popularity on Streaming Platforms

Carlos Vicente Soares Araujo; Marco Antônio Pinheiro de Cristo; Rafael Giusti

doi:10.22456/2175-2745.107021

Authors

Carlos Vicente Soares Araujo Federal University of Amazonas
Marco Antônio Pinheiro de Cristo Federal Univeristy of Amazonas
Rafael Giusti Federal University of Amazonas

DOI:

https://doi.org/10.22456/2175-2745.107021

Keywords:

Music, Hit Song Science, Machine Learning, Spotify

Abstract

The global music market moves billions of dollars every year, most of which comes from streaming
platforms. In this paper, we present a model for predicting whether or not a song will appear in Spotify’s Top 50, a ranking of the 50 most popular songs in Spotify, which is one of today’s biggest streaming services. To make this prediction, we trained different classifiers with information from audio features from songs that appeared in this ranking between November 2018 and January 2019. When tested with data from June and July 2019, an SVM classifier with RBF kernel obtained accuracy, precision, and AUC above 80%.

Downloads

Download data is not yet available.

Author Biographies

Carlos Vicente Soares Araujo, Federal University of Amazonas

Institute of Computing

Marco Antônio Pinheiro de Cristo, Federal Univeristy of Amazonas

Institute of Computing

Rafael Giusti, Federal University of Amazonas

Institute of Computing

References

PACHET, F.; SONY, C. Hit song science. Music data mining, Chapman & Hall/CRC Press Boca Raton, FL, p. 305-326, 2011.

LI, T.; OGIHARA, M.; TZANETAKIS, G. Music data mining. [S.l.]: CRC Press, 2011.

ARAUJO, C.; CRISTO, M.; GIUSTI, R. Predicting music popularity on streaming platforms. In: Anais do XVII Simpósio Brasileiro de Computação Musical. Porto Alegre, RS, Brasil: SBC, 2019. p. 141-148. Disponı́vel em: hhttps://sol.sbc.org.br/index.php/sbcm/article/view/10436i.

ARAUJO, C.; CRISTO, M.; GIUSTI, R. Will I Remain Popular? A Study Case on Spotify. In: Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional. Porto Alegre, RS, Brasil: SBC, 2019. p. 599-610. Disponı́vel em: https://sol.sbc.org.br/index.php/eniac/article/view/9318i.

ARAUJO, C. V. S.; CRISTO, M. A. P. de; GIUSTI, R. Predicting music popularity using music charts. In: 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). [S.l.: s.n.], 2019. p. 859-864.

ARAKELYAN, S. et al. Mining and forecasting career trajectories of music artists. CoRR, abs/1805.03324, 2018. Disponı́vel em: hhttp://arxiv.org/abs/1805.03324i.

STEININGER, D. M.; GATZEMEIER, S. Using the wisdom of the crowd to predict popular music chart success. In: ECIS. [S.l.: s.n.], 2013. p. 215.

KIM, Y.; SUH, B.; LEE, K. #Nowplaying the Future Billboard: Mining Music Listening Behaviors of Twitter Users for Hit Song Prediction. In: Proceedings of the First International Workshop on Social Media Retrieval and Analysis. New York, NY, USA: ACM, 2014. (SoMeRA ’14), p. 51-56

HERREMANS, D.; MARTENS, D.; SÖRENSEN, K. Dance hit song prediction. Journal of New Music Research, Routledge, v. 43, n. 3, p. 291-302, 2014.

KARYDIS, I. et al. Musical track popularity mining dataset: Extension & experimentation. Neurocomputing, v. 280, p. 76 - 85, 2018.

PONS, J.; SERRA, X. Randomly weighted cnns for (music) audio classification. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [S.l.: s.n.], 2019. p. 336-340.

MARTÍN-GUTIÉRREZ, D. et al. A multimodal end-to-end deep learning architecture for music popularity prediction. IEEE Access, v. 8, p. 39361-39374, 2020.

REIMAN, M.; ÖRNELL, P. Predicting hit songs with machine learning. In: . [S.l.: s.n.], 2018. (TRITA-EECS-EX, 2018:202).

PEDREGOSA, F. et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, v. 12, p. 2825-2830, 2011.

REBACK, J. et al. pandas-dev/pandas: Pandas 1.1.3. Zenodo, 2020. Disponı́vel em: hhttps://doi.org/10.5281/zenodo.4067057i.

ROSSUM, G. V.; JR, F. L. D. Python tutorial. [S.l.]: Centrum voor Wiskunde en Informatica Amsterdam, 1995. v. 620.

ZHANG, H. The optimality of naive bayes. AA, v. 1, n. 2, p. 3, 2004.

SCHÖLKOPF, B. et al. Estimating the support of a high-dimensional distribution. Neural Computation, v. 13, n. 7, p. 1443-1471, 2001.

HERBRICH, R. Learning kernel classifiers: theory and algorithms. Massachusetts: MIT press, 2001.

FAWCETT, T. An introduction to roc analysis. Pattern Recognition Letters, v. 27, n. 8, p. 861 - 874, 2006. ROC Analysis in Pattern Recognition.

BOUGHORBEL, S.; JARRAY, F.; EL-ANBARI, M. Optimal classifier for imbalanced data using matthews correlation coefficient metric. PLOS ONE, Public Library of Science, v. 12, n. 6, p. 1-17, 06 2017.

OLSON, D. L.; DELEN, D. Advanced data mining techniques. [S.l.]: Springer Science & Business Media, 2008.

PERCINO, G.; KLIMEK, P.; THURNER, S. Instrumentational complexity of music genres and why simplicity sells. PLOS ONE, Public Library of Science, v. 9, n. 12, p. 1-16, 12 2015.

ARAUJO, C. V. et al. Predicting music success based on users’ comments on online social networks. In: Proceedings of the 23rd Brazillian Symposium on Multimedia and the Web. New York, NY, USA: ACM, 2017. (WebMedia ’17), p. 149-156.