Collaboration-Aware Hit Song Prediction

Authors

DOI:

https://doi.org/10.5753/jis.2023.3137

Keywords:

Hit Song Science, Hit Song Prediction, Music Information Retrieval, Music Data Mining, Machine Learning

Abstract

In a streaming-oriented era, predicting which songs will be successful is a significant challenge for the music industry. Indeed, there are many efforts in determining the driving factors that contribute to a song’s success, and one potential solution could be incorporating artistic collaborations, as it allows for a wider audience reach. Therefore, we propose a multi-perspective approach that includes collaboration between artists as a factor for hit song prediction. Specifically, by combining online data from Billboard and Spotify, we tackle the problem as both classification and hit song placement tasks, applying five different model variants. Our results show that relying only on music-related features is not enough, whereas models that also consider collaboration features produce better results.

Downloads

Download data is not yet available.

References

Almada, C. et al. (2019). J-analyzer: A software for computer-assisted analysis of antônio carlos jobims songs. In SBCM, pages 12–16, Brazil. SBC.

Araujo, C. V., de Cristo, M. A. P., and Giusti, R. (2019). Predicting music popularity using music charts. In ICMLA, pages 859–864, Boca Raton, Florida, USA. IEEE.

Araujo, C. V. et al. (2017). Predicting music success based on users’ comments on online social networks. In WebMedia, pages 149–156, Brazil. SBC.

Bischoff, K. et al. (2009). Social knowledge-driven music hit prediction. In Advanced Data Mining and Applications, pages 43–54, Berlin, Heidelberg. Springer.

Calefato, F., Iaffaldano, G., and Lanubile, F. (2018). Collaboration success factors in an online music community. In Proceedings of the ACM Conference on Supporting Groupwork, pages 61–70, Sanibel Island, USA. ACM.

Celma, Ò. and Cano, P. (2008). From hits to niches? or how popular artists can bias music recommendation and discovery. In Netflix-KDD Work., pages 1–8.

Collins, A., Hand, C., and Snell, M. C. (2002). What makes a blockbuster? economic analysis of film success in the united kingdom. Managerial and Decision Economics, 23(6):343–354.

Cosimato, A. et al. (2019). The conundrum of success in music: Playing it or talking about it? IEEE Access, 7:123289–123298.

Costa, W. d. L., Filgueira, D., Ananias, L., Barioni, R., Figueiredo, L. S., and Teichrieb, V. (2020). Songverse: a digital musical instrument based on virtual reality. Journal on Interactive Systems, 11(1):57–65.

da Silva, A. C. M., Silva, D. F., and Marcacini, R. M. (2020). 4mula: A multitask, multimodal, and multilingual dataset of music lyrics and audio features. In WebMedia, pages 145–148, Brazil. ACM.

de Almeida, M. A. et al. (2017). The fast and winding roads that lead to the doors: Generating heterogeneous music playlists. In WebMedia, pages 269–276, Brazil. ACM.

Dewan, S. and Ramaprasad, J. (2014). Social media, traditional media, and music sales. Mis Quarterly, 38(1).

Dhanaraj, R. and Logan, B. (2005). Automatic prediction of hit songs. In ISMIR, pages 488–491, London, UK. Int’l Society for Music Information Retrieval.

Fraiberger, S. P. et al. (2018). Quantifying reputation and success in art. Science, 362(6416):825–829.

Géron, A. (2019). Hands-on machine learning with ScikitLearn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media, USA.

Hsu, D. J. and Sabato, S. (2016). Loss minimization and parameter estimation with heavy tails. J. Mach. Learn. Res., 17:18:1–18:40.

Interiano, M. et al. (2018). Musical trends and predictability of success in contemporary songs in and out of the top charts. Royal Society open science, 5(5):171274.

Kim, S. T. and Oh, J. H. (2021). Music intelligence: Granular data and prediction of top ten hit songs. Decis. Support Syst., 145:113535.

Kim, Y., Suh, B., and Lee, K. (2014). # nowplaying the future billboard: mining music listening behaviors of twitter users for hit song prediction. In SoMeRA, pages 51–56, Gold Coast, Australia. ACM.

Lee, J. and Lee, J. (2018). Music popularity: Metrics, characteristics, and audio-based prediction. IEEE Transactions on Multimedia, 20(11):3173–3182.

Lundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. In NIPS, page 4768–4777, Long Beach, California, USA. Curran Associates Inc.

Martín-Gutiérrez, D. et al. (2020). A multimodal end-to-end deep learning architecture for music popularity prediction. IEEE Access, 8:39361–39374.

Martins, G., Gomes, G., Conceição, J. L., Marques, L., da Silva, D., Castro, T., Gadelha, B., and de Freitas, R. (2021). Bumbometer digital crowd game: collaboration through competition in entertainment events. Journal on Interactive Systems, 12(1):294–307.

Murphy, K. P. (2012). Machine learning - a probabilistic perspective. MIT Press, Cambridge, USA.

Ni, Y. et al. (2011). Hit song science once again a science? In Intl. Workshop on Mach. Learn. and Music, Sierra Nevada, Spain. NIPS.

Nunes, J. C. and Ordanini, A. (2014). I like the way it sounds: The influence of instrumentation on a pop song’s place in the charts. Musicae Scientiae, 18(4):392–409.

Pachet, F. (2011). Hit song science. In Li, T., Ogihara, M., and Tzanetakis, G., editors, Music Data Mining, chapter 10, pages 305–326. CRC Press, USA.

Pachet, F. and Roy, P. (2008). Hit song science is not yet a science. In ISMIR, pages 355–360, Philadelphia, USA. Int’l Society for Music Information Retrieval.

Ren, J., Shen, J., and Kauffman, R. J. (2016). What makes a music track popular in online social networks? In WWW, pages 95–96, Montreal, Canada. ACM.

Ren, L. et al. (2010). Dynamic Nonparametric Bayesian Models for Analysis of Music. Journal of the American Statistical Association, 105:458–472.

Roads, C. (1996). The Computer Music Tutorial. MIT Press, Cambridge, England.

Salganik, M. J. et al. (2006). Experimental study of inequality and unpredictability in an artificial cultural market. Science, 311(5762):854–856.

Schedel, M. and Young, J. P. (2005). Editorial. Organised Sound, 10(3):181–183.

Serra, A. C. et al. (2021). Quality enhancement of highly degraded music using deep learning-based prediction models for lost frequencies. In WebMedia, pages 205–211, Brazil. ACM.

Serrà, J. et al. (2012). Measuring the evolution of contemporary western popular music. Scientific Reports, 2(521).

Silva, M. O. and Moro, M. M. (2019). Causality Analysis Between Collaboration Profiles and Musical Success. In WebMedia, pages 369–376, Rio de Janeiro. ACM.

Silva, M. O., Mota, L., and Moro, M. M. (2019a). MusicOSet: An Enhanced Open Dataset for Music Data Mining. https://doi.org/10.5281/zenodo.4904639.

Silva, M. O., Oliveira, G. P., Seufitelli, D. B., Lacerda, A., and Moro, M. M. (2022). Collaboration as a driving factor for hit song classification. In Silva, T. H., Dorini, L. B., Almeida, J. M., and Marques-Neto, H. T., editors, WebMedia ’22: Brazilian Symposium on Multimedia and Web, Curitiba, Brazil, November 7 - 11, 2022, pages 66–74. ACM.

Silva, M. O., Rocha, L. M., and Moro, M. M. (2019b). Col- laboration Profiles and Their Impact on Musical Success. In SAC, pages 2070–2077, Limassol, Cyprus. ACM.

Silva, M. O., Rocha, L. M., and Moro, M. M. (2019c). Musicoset: An enhanced open dataset for music data mining. In XXXII Simpósio Brasileiro de Banco de Dados: Dataset Showcase Workshop, SBBD 2019 Companion, pages 8–17, Fortaleza, CE, Brazil. SBC.

Singhi, A. and Brown, D. G. (2015). Can song lyrics predict hits. In Proceedings of the 11th International Symposium on Computer Music Multidisciplinary Research, pages 457–471.

Vötter, M. et al. (2021). Novel datasets for evaluating song popularity prediction tasks. In IEEE International Symposium on Multimedia (ISM), pages 166–173, Los Alamitos, USA. IEEE.

Wang, X. et al. (2019). Success in books: predicting book sales before publication. EPJ Data Science, 8(1):31.

Yang, L., Chou, S., Liu, J., Yang, Y., and Chen, Y. (2017). Revisiting the problem of audio-based hit song prediction using convolutional neural networks. In ICASSP, pages 621–625, New Orleans, USA. IEEE.

Zangerle, E., Vötter, M., Huber, R., and Yang, Y. (2019). Hit song prediction: Leveraging low- and high-level audio features. In ISMIR, pages 319–326, Delft, Netherlands. Int’l Society for Music Information Retrieval.

Downloads

Published

2023-06-26

How to Cite

SILVA, M. O.; OLIVEIRA, G. P.; SEUFITELLI, D. B.; MORO, M. M. Collaboration-Aware Hit Song Prediction. Journal on Interactive Systems, Porto Alegre, RS, v. 14, n. 1, p. 201–214, 2023. DOI: 10.5753/jis.2023.3137. Disponível em: https://journals-sol.sbc.org.br/index.php/jis/article/view/3137. Acesso em: 16 jun. 2024.

Issue

Section

Regular Paper

Most read articles by the same author(s)