ABSTRACT
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.
- Carlos Almada 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.2019.10416Google Scholar
- Carlos V.S. Araujo 2017. Predicting Music Success Based on Users’ Comments on Online Social Networks. In WebMedia. SBC, Brazil, 149–156. https://doi.org/10.1145/3126858.3126885Google ScholarDigital Library
- 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.2019.00149Google Scholar
- Kerstin Bischoff 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_8Google ScholarDigital Library
- 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/10.1145/3148330.3148346Google ScholarDigital Library
- Alberto Cosimato 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.2019.2937743Google Scholar
- 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/10.1145/3428658.3431089Google ScholarDigital Library
- Marcos A. de Almeida 2017. The Fast and Winding Roads that Lead to The Doors: Generating Heterogeneous Music Playlists. In WebMedia. ACM, Brazil, 269–276. https://doi.org/10.1145/3126858.3126891Google ScholarDigital Library
- Ruth Dhanaraj and Beth Logan. 2005. Automatic Prediction of Hit Songs. In ISMIR. Int’l Society for Music Information Retrieval, London, UK, 488–491.Google Scholar
- 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.Google Scholar
- Myra Interiano 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.171274Google ScholarCross Ref
- 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.2021.113535Google ScholarCross Ref
- 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/10.1145/2632188.2632206Google ScholarDigital Library
- 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.Google Scholar
- David Martín-Gutiérrez 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.2020.2976033Google ScholarCross Ref
- Kevin P. Murphy. 2012. Machine learning - a probabilistic perspective. MIT Press, Cambridge, USA.Google ScholarDigital Library
- Yizhao Ni 2011. Hit song science once again a science?. In Intl. Workshop on Mach. Learn. and Music. NIPS, Sierra Nevada, Spain.Google Scholar
- 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/10.1177/1029864914548528Google ScholarCross Ref
- 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.Google Scholar
- 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.Google Scholar
- 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/10.1145/2872518.2889402Google ScholarDigital Library
- Curtis Roads. 1996. The Computer Music Tutorial. MIT Press, Cambridge, England.Google ScholarDigital Library
- Margaret Schedel and John P. Young. 2005. EDITORIAL. Organised Sound 10, 3 (2005), 181–183. https://doi.org/10.1017/S1355771805000919Google ScholarDigital Library
- Arthur C. Serra 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/10.1145/3470482.3479635Google ScholarDigital Library
- 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/10.1145/3323503.3349549Google ScholarDigital Library
- 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 https://doi.org/10.5281/zenodo.4904639.Google Scholar
- 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/10.1145/3297280.3297483Google ScholarDigital Library
- 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.Google Scholar
- Michael Vötter 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/ISM52913.2021.00034Google Scholar
- 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.2017.7952230Google ScholarDigital Library
- 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.Google Scholar
Index Terms
Collaboration as a Driving Factor for Hit Song Classification
Recommendations
An Analysis of Classification Approaches for Hit Song Prediction Using Engineered Metadata Features with Lyrics and Audio Features
Information for a Better World: Normality, Virtuality, Physicality, InclusivityAbstractHit song prediction, one of the emerging fields in music information retrieval (MIR), remains a considerable challenge. Being able to understand what makes a given song a hit is clearly beneficial to the whole music industry. Previous approaches ...
Automated analysis of performance variations in folk song recordings
MIR '10: Proceedings of the international conference on Multimedia information retrievalPerformance analysis of recorded music material has become increasingly important in musicological research and music psychology. In this paper, we present various techniques for extracting performance aspects from field recordings of folk songs. Main ...
Music Genre Classification and Feature Comparison using ML
ICMLT '22: Proceedings of the 2022 7th International Conference on Machine Learning TechnologiesAn essential feature of the music is the genre, which can be considered a high-level description of an individual piece of music. In this sense, genre as a music feature is similar to typical descriptive features from the ML perspective. Although a ...
Comments