Collaboration as a Driving Factor for Hit Song Classification

• Mariana O. Silva UFMG
• Gabriel P. Oliveira UFMG
• Danilo B. Seufitelli UFMG
• Anisio Lacerda UFMG
• Mirella M. Moro UFMG

Resumo

The Web has transformed many services and products, including the way we consume music. In a currently streaming-oriented era,predicting hit songs is a major open issue for the music industry.Indeed, there are many efforts in finding the driving factors that shape the success of songs. Yet another feature that may improve such efforts is artistic collaboration, as it allows the songs to reach a wider audience. 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 model the issue as a binary classification task by using 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.

Palavras-chave: Hit Song Science, Hit Song Prediction, Music Information Retrieval, Music Data Mining, Machine Learning

Referências

Carlos Almada et al. 2019. J-Analyzer: A Software for Computer-Assisted Analysis of Antônio Carlos Jobims Songs. In SBCM. SBC, Brazil, 12–16. https://doi.org/10.5753/sbcm.2019.10416

Carlos V.S. Araujo et al. 2017. Predicting Music Success Based on Users’ Comments on Online Social Networks. In WebMedia. SBC, Brazil, 149–156. https://doi.org/10.1145/3126858.3126885

Carlos V.S. Araujo, Marco A. P. de Cristo, and Rafael Giusti. 2019. Predicting Music Popularity Using Music Charts. In ICMLA. IEEE, Boca Raton, Florida, USA, 859–864. https://doi.org/10.1109/ICMLA.2019.00149

Kerstin Bischoff et al. 2009. Social Knowledge-Driven Music Hit Prediction. In Advanced Data Mining and Applications. Springer, Berlin, Heidelberg, 43–54. https://doi.org/10.1007/978-3-642-03348-3_8

Fabio Calefato, Giuseppe Iaffaldano, and Filippo Lanubile. 2018. Collaboration Success Factors in an Online Music Community. In Proceedings of the ACM Conference on Supporting Groupwork. ACM, Sanibel Island, USA, 61–70. https://doi.org/10.1145/3148330.3148346

Alberto Cosimato et al. 2019. The Conundrum of Success in Music: Playing it or Talking About it? IEEE Access 7 (2019), 123289–123298. https://doi.org/10.1109/ACCESS.2019.2937743

Angelo C. M. da Silva, Diego F. Silva, and Ricardo M. Marcacini. 2020. 4MuLA:A Multitask, Multimodal, and Multilingual Dataset of Music Lyrics and Audio Features. In WebMedia. ACM, Brazil, 145–148. https://doi.org/10.1145/3428658.3431089

Marcos A. de Almeida et al. 2017. The Fast and Winding Roads that Lead to The Doors: Generating Heterogeneous Music Playlists. In WebMedia. ACM, Brazil, 269–276. https://doi.org/10.1145/3126858.3126891

Ruth Dhanaraj and Beth Logan. 2005. Automatic Prediction of Hit Songs. In ISMIR. Int’l Society for Music Information Retrieval, London, UK, 488–491.

Aurélien Géron. 2019. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media, USA.

Myra Interiano 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 (2018), 171274. https://doi.org/10.1098/rsos.171274

Seon Tae Kim and Joo Hee Oh. 2021. Music intelligence: Granular data and prediction of top ten hit songs. Decis. Support Syst. 145 (2021), 113535. https://doi.org/10.1016/j.dss.2021.113535

Yekyung Kim, Bongwon Suh, and Kyogu Lee. 2014. # nowplaying the future Billboard: mining music listening behaviors of Twitter users for hit song prediction. In SoMeRA. ACM, Gold Coast, Australia, 51–56. https://doi.org/10.1145/2632188.2632206

Scott M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In NIPS. Curran Associates Inc., Long Beach, California, USA,4768–4777.

David Martín-Gutiérrez et al. 2020. A Multimodal End-to-End Deep Learning Architecture for Music Popularity Prediction. IEEE Access 8 (2020), 39361–39374. https://doi.org/10.1109/ACCESS.2020.2976033

Kevin P. Murphy. 2012. Machine learning - a probabilistic perspective. MIT Press, Cambridge, USA.

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

Joseph C. Nunes and Andrea Ordanini. 2014. I like the way it sounds: The influence of instrumentation on a pop song’s place in the charts. Musicae Scientiae 18, 4 (2014), 392–409. https://doi.org/10.1177/1029864914548528

François Pachet. 2011. Hit song science. In Music Data Mining, Tao Li, Mitsunori Ogihara, and George Tzanetakis (Eds.). CRC Press, USA, Chapter 10, 305–326.

François Pachet and Pierre Roy. 2008. Hit Song Science Is Not Yet a Science. In ISMIR. Int’l Society for Music Information Retrieval, Philadelphia, USA, 355–360.

Jing Ren, Jialie Shen, and Robert J. Kauffman. 2016. What Makes a Music Track Popular in Online Social Networks?. In WWW. ACM, Montreal, Canada, 95–96. https://doi.org/10.1145/2872518.2889402

Curtis Roads. 1996. The Computer Music Tutorial. MIT Press, Cambridge, England.

Margaret Schedel and John P. Young. 2005. EDITORIAL. Organised Sound 10, 3 (2005), 181–183. https://doi.org/10.1017/S1355771805000919

Arthur C. Serra et al. 2021. Quality Enhancement of Highly Degraded Music Using Deep Learning-Based Prediction Models for Lost Frequencies. In WebMedia. ACM, Brazil, 205–211. https://doi.org/10.1145/3470482.3479635

Mariana O. Silva and Mirella M Moro. 2019. Causality Analysis Between Collaboration Profiles and Musical Success. In WebMedia. ACM, Rio de Janeiro, 369–376. https://doi.org/10.1145/3323503.3349549

Mariana O. Silva, Laís Mota, and Mirella M. Moro. 2019. MusicOSet: An Enhanced Open Dataset for Music Data Mining. https://doi.org/10.5281/zenodo.4904639

Mariana O. Silva, Laís M. Rocha, and Mirella M. Moro. 2019. Collaboration Profiles and Their Impact on Musical Success. In SAC. ACM, Limassol, Cyprus, 2070–2077. https://doi.org/10.1145/3297280.3297483

Mariana O. Silva, Laís Mota de Alencar Rocha, and Mirella M. Moro. 2019. MusicOSet: An Enhanced Open Dataset for Music Data Mining. In XXXII Simpósio Brasileiro de Banco de Dados: Dataset Showcase Workshop, SBBD 2019 Companion. SBC, Fortaleza, CE, Brazil, 8–17.

Michael Vötter et al. 2021. Novel Datasets for Evaluating Song Popularity Prediction Tasks. In IEEE International Symposium on Multimedia (ISM). IEEE, Los Alamitos, USA, 166–173. https://doi.org/10.1109/ISM52913.2021.00034

Li-Chia Yang, Szu-Yu Chou, Jen-Yu Liu, Yi-Hsuan Yang, and Yi-An Chen. 2017. Revisiting the problem of audio-based hit song prediction using convolutional neural networks. In ICASSP. IEEE, New Orleans, USA, 621–625. https://doi.org/10.1109/ICASSP.2017.7952230

Eva Zangerle, Michael Vötter, Ramona Huber, and Yi-Hsuan Yang. 2019. Hit Song Prediction: Leveraging Low- and High-Level Audio Features. In ISMIR. Int’l Society for Music Information Retrieval, Delft, Netherlands, 319–326.