Predicting Music Popularity on Streaming Platforms

• Carlos Soares Araujo Federal University of Amazonas
• Marco Cristo Federal University of Amazonas
• Rafael Giusti Federal University of Amazonas

DOI: https://doi.org/10.5753/sbcm.2019.10436

Resumo

Online streaming platforms have become one of the most important forms of music consumption. Most streaming platforms provide tools to assess the popularity of a song in the forms of scores and rankings. In this paper, we address two issues related to song popularity. First, we predict whether an already popular song may attract higher-than-average public interest and become “viral”. Second, we predict whether sudden spikes in public interest will translate into long-term popularity growth. We base our findings in data from the streaming platform Spotify and consider appearances in its “Most-Popular” list as indicative of popularity, and appearances in its “Virals” list as indicative of interest growth. We approach the problem as a classification task and employ a Support Vector Machine model built on popularity information to predict interest, and vice versa. We also verify if acoustic information can provide useful features for both tasks. Our results show that the popularity information alone is sufficient to predict future interest growth, achieving a F1-score above 90% at predicting whether a song will be featured in the “Virals” list after being observed in the “Most-Popular”.

Palavras-chave: Music Analysis and Synthesis, Music Information Retrieval

Referências

Chris Molanphy. How the hot 100 became america’s hit barometer, 2013.

Cristian Cibils, Zachary Meza, and Greg Ramel. Predicting a song’s path through the billboard hot 100’, 2015.

Junghyuk Lee and Jong-Seok Lee. Predicting music popularity patterns based on musical complexity and early stage popularity. In Proceedings of the Third Edition Workshop on Speech, Language & Audio in Multimedia, SLAM’15, pages 3–6, New York, NY, USA, 2015. ACM.

Ioannis Karydis, Aggelos Gkiokas, Vassilis Katsouros, and Lazaros Iliadis. Musical track popularity mining dataset: Extension & experimentation. Neurocomputing, 280:76 –85, 2018. Applications of Neural Modeling in the new era for data and IT.

Vasant Dhar and Elaine A. Chang. Does chatter matter? the impact of user-generated content on music sales. Journal of Interactive Marketing, 23(4):300 – 307, 2009.

Benjamin Shulman, Amit Sharma, and Dan Cosley. Predictability of popularity: Gaps between prediction and understanding. In Tenth International AAAI Conference on Web and Social Media, pages 348–357, 2016.

Yekyung Kim, Bongwon Suh, and Kyogu Lee. #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, SoMeRA ’14, pages 51–56, New York, NY, USA, 2014. ACM.

Carlos V.S. Araujo, Rayol M. Neto, Fabiola G. Nakamura, and Eduardo F. Nakamura. Predicting music success based on users’ comments on online social networks. In Proceedings of the 23rd Brazillian Symposium on Multimedia and the Web, WebMedia ’17, pages 149–156, New York, NY, USA, 2017. ACM.

Simon Haykin. Neural Networks: A Comprehensive Foundation. Prentice Hall, 1999.

Shushan Arakelyan, Fred Morstatter, Margaret Martin, Emilio Ferrara, and Aram Galstyan. Mining and forecasting career trajectories of music artists. In Proceedings of the 29th on Hypertext and Social Media, HT ’18, pages 11–19, New York, NY, USA, 2018. ACM.

Dennis M Steininger and Simon Gatzemeier. Using the wisdom of the crowd to predict popular music chart success. In Proceedings of the 21st European Conference on Information Systems, page 215, 2013.

Brian McFee, Colin Raffel, Dawen Liang, Daniel PW Ellis, Matt McVicar, Eric Battenberg, and Oriol Nieto. librosa: Audio and music signal analysis in python. In Proceedings of the 14th python in science conference, pages 18–25, 2015.

S. Dubnov. Generalization of spectral flatness measure for non-gaussian linear processes. IEEE Signal Processing Letters, 11(8):698–701, Aug 2004.

David Harris and Sarah Harris. Digital design and computer architecture. Morgan Kaufmann, 2010.

Jason Brownlee. Introduction to Time Series Forecasting with Python: How to Prepare Data and Develop Models to Predict the Future. Jason Brownlee, 2017.

Bernhard Schölkopf, John C. Platt, John Shawe-Taylor, Alex J. Smola, and Robert C. Williamson. Estimating the support of a high-dimensional distribution. Neural Computation, 13(7):1443–1471, 2001.

R. Giusti, D. F. Silva, and G. E. A. P. A. Batista. Improved time series classification with representation diversity and svm. In 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA), pages 1–6, Dec 2016.

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.

Chih-Chung Chang and Chih-Jen Lin. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1–27:27, 2011. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.

Carlos V.S. Araújo, Rayol M. Neto, Fabiola G. Nakamura, and Eduardo F. Nakamura. Using complex networks to assess collaboration in rap music: A study case of dj khaled. In Proceedings of the 23rd Brazillian Symposium on Multimedia and the Web, WebMedia ’17, pages 425–428, New York, NY, USA, 2017. ACM.

Carlos V. S. Araujo and Eduardo F. Nakamura. Identification of most popular musical genres and their influence factors. In Proceedings of the 24th Brazilian Symposium on Multimedia and the Web, WebMedia ’18, pages 233–236, New York, NY, USA, 2018. ACM.