Collaboration-Aware Hit Song Analysis and Prediction
Resumo
We propose tackling the Hit Song Prediction problem through a multimodal form with songs’ features fused together. Specifically, we describe songs from three feature modalities: music, artist and album. Initially, we identify collaboration profiles in a success-based musical network, unveiling how professional connections can significantly impact their success. Then, we use time series and the Granger Causality test for assessing whether there is a causal relationship between collaboration profiles and artists’ popularity. Finally, we model the Hit Song Prediction problem as two distinct tasks: classification and placement. The former is a classical binary classification model and directly applies our fusion strategies. The latter is a modeling approach that ranks a song relative to a given chart, predicts hit songs, and provides comparative popularity information of a set of songs. Furthermore, we emphasize collaboration artists’ profiles as important features when describing their songs. Overall, our empirical studies confirm the effectiveness of our method that fuses heterogeneous data for both tasks.
Palavras-chave:
Collaboration Profiles, Hit Song Science, Musical Success, Social Networks, Machine Learning, Multimodal
Referências
Carlos V. S. Araújo et al. 2017. Predicting Music Success Based on Users’ Comments on Online Social Networks. In Braz Symp on Multimedia and the Web WebMedia. 149–156. https://doi.org/10.1145/3126858.3126885.
Carlos Vicente Soares Araujo et al. 2019. Predicting Music Popularity Using Music Charts. In ICMLA. 859–864. https://doi.org/10.1109/ICMLA.2019.00149
Gabriel R. G. Barbosa, Bruna C. Melo, Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufitelli, and Mirella M. Moro. 2021. Hot Streaks in the Brazilian Music Market: A Comparison Between Physical and Digital Eras. In Simp. Bras. Computação e Música.
Kerstin Bischoff et al. 2009. Social Knowledge-Driven Music Hit Prediction. In ADMA. 43–54. https://doi.org/10.1007/978-3-642-03348-3_8
Ruth Dhanaraj and Beth Logan. 2005. Automatic Prediction of Hit Songs. In Procs Int’l Conf on Music Information Retrieval, ISMIR. 488–491.
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.
Junghyuk Lee and Jong-Seok Lee. 2018. Music Popularity: Metrics, Characteristics, and Audio-Based Prediction. IEEE Trans. Multimedia 20, 11 (2018), 3173–3182. https://doi.org/10.1109/TMM.2018.2820903
D. 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
Siobhan McAndrew and Martin Everett. 2015. Music as Collective Invention: A Social Network Analysis of Composers. Cultural Sociology 9, 1 (2015), 56–80. https://doi.org/10.1177/1749975514542486
Gabriel Oliveira, Gabriel R. G. Barbosa, Bruna C. Melo, Mariana O. Silva, Danilo Seufitelli, and Mirella M. Moro. 2021. MUHSIC: An Open Dataset with Temporal Musical Success Information. In SBBD: Dataset Showcase Workshop.
Gabriel Oliveira, Mariana Santos, Danilo Seufitelli, Anisio Lacerda, and Mirella M. Moro. 2020. Detecting Collaboration Profi les in Success-based Music Genre Networks. In ISMIR. 726–732.
Gabriel P. Oliveira, Gabriel R. G. Barbosa, Bruna C. Melo, Mariana O. Silva, Danilo B. Seufitelli, Anisio Lacerda, and Mirella M. Moro. 2021. Hot Streaks in Musical Careers. WWWJ (2021). [under submission].
Gabriel P. Oliveira, Gabriel R. G. Barbosa, Bruna C. Melo, Mariana O. Silva, Danilo B. Seufitelli, Anisio Lacerda, and Mirella M. Moro. 2021. MUHSIC: An Open Dataset with Temporal Musical Success Information. Zenodo. https://doi.org/10.5281/zenodo.5168695
Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufi telli, Anisio Lacerda, and Mirella M. Moro. 2020. MGD: Music Genre Dataset. Zenodo. https://doi.org/10.5281/zenodo.4778563
François Pachet and Pierre Roy. 2008. Hit Song Science Is Not Yet a Science. In Procs Int’l Conf on Music Information Retrieval, ISMIR. 355–360.
João Felipe Pimentel, Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufitelli, and Mirella M. Moro. 2021. Ciência de Dados com Reprodutibilidade usando Jupyter. In Jornada de Atualização em Informática 2021, Aline Maria Santos Andrade and Raul Sidnei Wazlawick (Eds.). SBC, Chapter 1, 13–62. https://doi.org/10.5753/sbc.6757.3.1
Jing Ren, Jialie Shen, and Robert J. Kauff man. 2016. What Makes a Music Track Popular in Online Social Networks?. In Procs Int’l Conf World Wide Web – Companion Volume. https://doi.org/10.1145/2872518.2889402
Clarisse Scofield, Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufitelli, and Mirella M. Moro. 2021. Hit Song Science: A Comprehensive Survey and Research Directions. (2021). [under submission].
Mariana Silva et al. 2021. Exploring Brazilian Cultural Identity Through Reading Preferences. In BraSNAM. 115–126. https://doi.org/10.5753/brasnam.2021.16130
M.O. Silva, Laís Rocha, and M.M. Moro. 2019. MusicOSet: An Enhanced Open Dataset for Music Data Mining. In SBBD: Dataset Showcase Workshop.
Mariana O. Silva et al. 2019. MusicOSet: An Enhanced Open Dataset for Music Data Mining. Zenodo. https://doi.org/10.5281/zenodo.4904639
Mariana O. Silva et al. 2021. PPORTAL: Public Domain Portuguese-language Literature Dataset. In SBBD: Dataset Showcase Workshop.
Mariana O. Silva and Clarisse Scofi eld Mirella M. Moro. 2021. PPORTAL: Public domain Portuguese-language literature Dataset. Zenodo. https://doi.org/10.5281/zenodo.5178063
Mariana O. Silva and Mirella M. Moro. 2019. Causality Analysis Between Collaboration Profiles and Musical Success. In Braz Symp on Multimedia and the Web -WebMedia. 369–376. https://doi.org/10.1145/3323503.3349549
Mariana O. Silva, Laís Mota, and Mirella M. Moro. 2019. CoMusic: Good things come to those who collaborate. Zenodo. https://doi.org/10.5281/zenodo.4904676
Mariana O. Silva, Gabriel P. Oliveira, Anísio Lacerda, and Mirella M. Moro. 2021. Collaboration-Aware Multimodal Hit Song Prediction. Information Processing and Management (2021). [under submission].
Mariana O. Silva, Laís M. Rocha, and Mirella M. Moro. 2019. Collaboration Profiles and Their Impact on Musical Success. In ACM/SIGAPP SAC. https://doi.org/10.1145/3297280.3297483
Li-Chia Yang et al. 2017. Revisiting the problem of audio-based hit song prediction using convolutional neural networks. In ICASSP. https://doi.org/10.1109/ICASSP.2017.7952230
Haiqing Yu et al. 2019. Popularity Prediction for Artists Based on User Songs Dataset. In ICCAI. 17–24. https://doi.org/10.1145/3330482.3330493
Eva Zangerle et al. 2019. Hit Song Prediction: Leveraging Low- and High-Level Audio Features. In ISMIR. 319–326.
Carlos Vicente Soares Araujo et al. 2019. Predicting Music Popularity Using Music Charts. In ICMLA. 859–864. https://doi.org/10.1109/ICMLA.2019.00149
Gabriel R. G. Barbosa, Bruna C. Melo, Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufitelli, and Mirella M. Moro. 2021. Hot Streaks in the Brazilian Music Market: A Comparison Between Physical and Digital Eras. In Simp. Bras. Computação e Música.
Kerstin Bischoff et al. 2009. Social Knowledge-Driven Music Hit Prediction. In ADMA. 43–54. https://doi.org/10.1007/978-3-642-03348-3_8
Ruth Dhanaraj and Beth Logan. 2005. Automatic Prediction of Hit Songs. In Procs Int’l Conf on Music Information Retrieval, ISMIR. 488–491.
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.
Junghyuk Lee and Jong-Seok Lee. 2018. Music Popularity: Metrics, Characteristics, and Audio-Based Prediction. IEEE Trans. Multimedia 20, 11 (2018), 3173–3182. https://doi.org/10.1109/TMM.2018.2820903
D. 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
Siobhan McAndrew and Martin Everett. 2015. Music as Collective Invention: A Social Network Analysis of Composers. Cultural Sociology 9, 1 (2015), 56–80. https://doi.org/10.1177/1749975514542486
Gabriel Oliveira, Gabriel R. G. Barbosa, Bruna C. Melo, Mariana O. Silva, Danilo Seufitelli, and Mirella M. Moro. 2021. MUHSIC: An Open Dataset with Temporal Musical Success Information. In SBBD: Dataset Showcase Workshop.
Gabriel Oliveira, Mariana Santos, Danilo Seufitelli, Anisio Lacerda, and Mirella M. Moro. 2020. Detecting Collaboration Profi les in Success-based Music Genre Networks. In ISMIR. 726–732.
Gabriel P. Oliveira, Gabriel R. G. Barbosa, Bruna C. Melo, Mariana O. Silva, Danilo B. Seufitelli, Anisio Lacerda, and Mirella M. Moro. 2021. Hot Streaks in Musical Careers. WWWJ (2021). [under submission].
Gabriel P. Oliveira, Gabriel R. G. Barbosa, Bruna C. Melo, Mariana O. Silva, Danilo B. Seufitelli, Anisio Lacerda, and Mirella M. Moro. 2021. MUHSIC: An Open Dataset with Temporal Musical Success Information. Zenodo. https://doi.org/10.5281/zenodo.5168695
Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufi telli, Anisio Lacerda, and Mirella M. Moro. 2020. MGD: Music Genre Dataset. Zenodo. https://doi.org/10.5281/zenodo.4778563
François Pachet and Pierre Roy. 2008. Hit Song Science Is Not Yet a Science. In Procs Int’l Conf on Music Information Retrieval, ISMIR. 355–360.
João Felipe Pimentel, Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufitelli, and Mirella M. Moro. 2021. Ciência de Dados com Reprodutibilidade usando Jupyter. In Jornada de Atualização em Informática 2021, Aline Maria Santos Andrade and Raul Sidnei Wazlawick (Eds.). SBC, Chapter 1, 13–62. https://doi.org/10.5753/sbc.6757.3.1
Jing Ren, Jialie Shen, and Robert J. Kauff man. 2016. What Makes a Music Track Popular in Online Social Networks?. In Procs Int’l Conf World Wide Web – Companion Volume. https://doi.org/10.1145/2872518.2889402
Clarisse Scofield, Gabriel P. Oliveira, Mariana O. Silva, Danilo B. Seufitelli, and Mirella M. Moro. 2021. Hit Song Science: A Comprehensive Survey and Research Directions. (2021). [under submission].
Mariana Silva et al. 2021. Exploring Brazilian Cultural Identity Through Reading Preferences. In BraSNAM. 115–126. https://doi.org/10.5753/brasnam.2021.16130
M.O. Silva, Laís Rocha, and M.M. Moro. 2019. MusicOSet: An Enhanced Open Dataset for Music Data Mining. In SBBD: Dataset Showcase Workshop.
Mariana O. Silva et al. 2019. MusicOSet: An Enhanced Open Dataset for Music Data Mining. Zenodo. https://doi.org/10.5281/zenodo.4904639
Mariana O. Silva et al. 2021. PPORTAL: Public Domain Portuguese-language Literature Dataset. In SBBD: Dataset Showcase Workshop.
Mariana O. Silva and Clarisse Scofi eld Mirella M. Moro. 2021. PPORTAL: Public domain Portuguese-language literature Dataset. Zenodo. https://doi.org/10.5281/zenodo.5178063
Mariana O. Silva and Mirella M. Moro. 2019. Causality Analysis Between Collaboration Profiles and Musical Success. In Braz Symp on Multimedia and the Web -WebMedia. 369–376. https://doi.org/10.1145/3323503.3349549
Mariana O. Silva, Laís Mota, and Mirella M. Moro. 2019. CoMusic: Good things come to those who collaborate. Zenodo. https://doi.org/10.5281/zenodo.4904676
Mariana O. Silva, Gabriel P. Oliveira, Anísio Lacerda, and Mirella M. Moro. 2021. Collaboration-Aware Multimodal Hit Song Prediction. Information Processing and Management (2021). [under submission].
Mariana O. Silva, Laís M. Rocha, and Mirella M. Moro. 2019. Collaboration Profiles and Their Impact on Musical Success. In ACM/SIGAPP SAC. https://doi.org/10.1145/3297280.3297483
Li-Chia Yang et al. 2017. Revisiting the problem of audio-based hit song prediction using convolutional neural networks. In ICASSP. https://doi.org/10.1109/ICASSP.2017.7952230
Haiqing Yu et al. 2019. Popularity Prediction for Artists Based on User Songs Dataset. In ICCAI. 17–24. https://doi.org/10.1145/3330482.3330493
Eva Zangerle et al. 2019. Hit Song Prediction: Leveraging Low- and High-Level Audio Features. In ISMIR. 319–326.
Publicado
05/11/2021
Como Citar
SILVA, Mariana O.; MORO, Mirella M..
Collaboration-Aware Hit Song Analysis and Prediction. In: CONCURSO DE TESES E DISSERTAÇÕES - SIMPÓSIO BRASILEIRO DE SISTEMAS MULTIMÍDIA E WEB (WEBMEDIA), 27. , 2021, Minas Gerais.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 11-14.
ISSN 2596-1683.
DOI: https://doi.org/10.5753/webmedia_estendido.2021.17603.
