Musical Success in the United States and Brazil: Novel Datasets and Temporal Analyses
DOI:
https://doi.org/10.5753/jidm.2022.2350Keywords:
hot streaks, hit song science, music information retrieval, open data, time series analysisAbstract
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.
Downloads
References
Aggarwal, C. C. (2016). Recommender Systems - The Textbook. Springer, Switzerland. doi:10.1007/978-3-319-29659-3.
Al-Beitawi, Z., Salehan, M., and Zhang, S. (2020). Cluster analysis of musical attributes for top trending songs. In HICSS, pages 1–7.
Barbosa, G. R. G., Melo, B. C., Oliveira, G. P., Silva, M. O., Seufitelli, D. B., and Moro, M. M. (2021). Hot Streaks in the Brazilian Music Market: A Comparison Between Physical and Digital Eras. In Brazilian Symposium on Computer Music (SBCM), pages 155–162, Recife, Brazil.
Bertin-Mahieux, T. et al. (2011). The Million Song Dataset. In Int’l Society for Music Information Retrieval Conf., pages 591–596, Miami, USA.
Bertoni, A. and Lemos, R. (2021). Três datasets criados a partir de um banco de canções populares brasileiras de sucesso e não-sucesso de 2014 a 2019. In Brazilian Symposium on Databases: Dataset Showcase Workshop, pages 11–20, Rio de Janeiro, Brazil. doi:10.5753/dsw.2021.17410.
Bholowalia, P. and Kumar, A. (2014). Ebk-means: A clustering technique based on elbow method and k-means in wsn. Int’l J. of Computer Applications, 105(9):17–24.
Bogdanov, D., Porter, A., Schreiber, H., Urbano, J., and Oramas, S. (2019). The acousticbrainz genre dataset: Multi-source, multi-level, multi-label, and large-scale. In Int’l Society for Music Information Retrieval Conf., pages 360–367.
Byrd, D. and Crawford, T. (2002). Problems of music information retrieval in the real world. Information Processing & Management, 38(2):249–272. doi:10.1016/S0306-4573(01)00033-4.
Castel-Branco, G. et al. (2021). Puremic: A new audio dataset for the classification of musical instruments based on convolutional neural networks. J. Signal Process. Syst., 93(9):977–987. doi:10.1007/s11265-021-01661-3.
Castillo, J. R. and Flores, M. J. (2021). Web-based music genre classification for timeline song visualization and analysis. IEEE Access, 9:18801–18816. doi:10.1109/ACCESS.2021.3053864.
Çimen, A. and Kayis, E. (2021). A longitudinal model for song popularity prediction. In Int’l Conf. on Data Science, Technology and Applications (DATA), pages 96–104, Online Streaming. doi:10.5220/0010607700960104.
Cosimato, A. et al. (2019). The conundrum of success in music: Playing it or talking about it? IEEE Access, 7:123289–123298. doi:10.1109/ACCESS.2019.2937743.
Feng, M. and Feng, W. (2021). Evaluation of parallel and sequential deep learning models for music subgenre classification. Math. Found. Comput., 4(2):131. doi:10.3934/mfc.2021008.
Ferraro, A. et al. (2021). Melon playlist dataset: A public dataset for audio-based playlist generation and music tagging. In Int’l Conf. on Acoustics, Speech and Signal Processing, pages 536–540, Toronto, Canada.
Garimella, K. and West, R. (2019). Hot streaks on social media. In Int’l Conf. on Web and Social Media, pages 170–180, Munich, Germany.
Georges, P. and Nguyen, N. (2019). Visualizing music similarity: clustering and mapping 500 classical music composers. Scientometrics, 120(3):975–1003.
Janosov, M., Battiston, F., and Sinatra, R. (2020). Success and luck in creative careers. EPJ Data Sci., 9(1):9. doi:10.1140/epjds/s13688-020-00227-w.
Karydis, I., Gkiokas, A., and Katsouros, V. (2016). Musical track popularity mining dataset. In IFIP Int’l Conf. on Artificial Intelligence Applications and Innovations, pages 562–572, Greece. doi:10.1007/978-3-319-44944-9_50.
Keogh, E. J. and Pazzani, M. J. (2000). Scaling up dynamic time warping for datamining applications. In ACM SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining, pages 285–289, Boston, USA. doi:10.1145/347090.347153.
Kowald, D., Müllner, P., Zangerle, E., Bauer, C., Schedl, M., and Lex, E. (2021). Support the underground: characteristics of beyond-mainstream music listeners. EPJ Data Sci., 10(1):14. doi:10.1140/epjds/s13688-021-00268-9.
Liu, C., Feng, L., Liu, G., Wang, H., and Liu, S. (2021a). Bottom-up broadcast neural network for music genre classification. Multim. Tools Appl., 80(5):7313–7331.
Liu, L., Dehmamy, N., Chown, J., Giles, C. L., and Wang, D. (2021b). Understanding the onset of hot streaks across artistic, cultural, and scientific careers. Nature Communications, 12(5392):249–272. doi:10.1038/s41467-021-25477-8.
Liu, L., Wang, Y., Sinatra, R., Giles, C. L., Song, C., and Wang, D. (2018). Hot streaks in artistic, cultural, and scientific careers. Nature, 559(7714):396–399. doi:10.1038/s41586-018-0315-8.
Melchiorre, A. B. et al. (2021). Investigating gender fairness of recommendation algorithms in the music domain. Information Processing & Management, 58(5):102666. doi:10.1016/j.ipm.2021.102666.
Oliveira, G. P., Barbosa, G. R. G., Melo, B. C., Silva, M. O., Seufitelli, D. B., Lacerda, A., and Moro, M. M. (2021a). MUHSIC: An Open Dataset with Temporal Musical Success Information. Zenodo. doi:10.5281/zenodo.4779002. https://doi.org/10.5281/zenodo.4779002.
Oliveira, G. P., Barbosa, G. R. G., Melo, B. C., Silva, M. O., Seufitelli, D. B., and Moro, M. M. (2021b). MUHSIC: An Open Dataset with Temporal Music Success Information. In Brazilian Symposium on Databases: Dataset Showcase Workshop, pages 65–76, Rio de Janeiro, Brazil. doi:10.5753/dsw.2021.17415.
Oliveira, G. P., Silva, M. O., Seufitelli, D. B., Lacerda, A., and Moro, M. M. (2020). Detecting collaboration profiles in success-based music genre networks. In Int’l Society for Music Information Retrieval Conf., Montreal, Canada.
Oramas, S., Barbieri, F., Nieto, O., and Serra, X. (2018). Multimodal deep learning for music genre classification. Trans. Int. Soc. Music. Inf. Retr., 1(1):4–21.
Pachet, F. (2011). Hit song science. In Tao Li, Mitsunori Ogihara, G. T., editor, Music Data Mining, chapter 10, pages 305–326. CRC Press, New York, USA.
Pati, A., Gururani, S. K., and Lerch, A. (2020). dmelodies: A music dataset for disentanglement learning. In Int’l Society for Music Information Retrieval Conf., pages 125–133, Montreal, Canada.
Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics, 20:53–65.
Roy, S., Biswas, M., and De, D. (2020). imusic: a session-sensitive clustered classical music recommender system using contextual representation learning. Multim. Tools Appl., 79(33-34):24119–24155.
Scaringella, N., Zoia, G., and Mlynek, D. (2006). Automatic genre classification of music content: a survey. IEEE Signal Process. Mag., 23(2):133–141. doi:10.1109/MSP.2006.1598089.
Silva, M. O., Rocha, L. M., and Moro, M. M. (2019). MusicOSet: An Enhanced Open Dataset for Music Data Mining. In Brazilian Symposium on Databases: Dataset Showcase Workshop, pages 408–417, Fortaleza, Brazil.
Zangerle, E., Huber, R., and Yang, M. V. Y.-H. (2019). Hit Song Prediction: Leveraging Low- and High-Level Audio Features. In Int’l Society for Music Information Retrieval Conf., pages 319–326, Delft, The Netherlands.
