Analysis of the Lyrics of the Most Played Brazilian Songs on the Radios of the Last Six Decades

• Italo Lourenço Trindade Federal Institute of Espírito Santo (IFES)
• Leandro Colombi Resendo Federal Institute of Espírito Santo (IFES)
• Jefferson Oliveira Andrade Federal Institute of Espírito Santo (IFES) https://orcid.org/0000-0002-5321-9239
• Karin S. Komati Federal Institute of Espírito Santo (IFES) http://orcid.org/0000-0001-5677-4724

DOI: https://doi.org/10.5753/sbbd_estendido.2021.18155

Abstract

This work carried out an analysis of the most played songs on Brazilian radios over 6 decades, from 1960 to 2019. The goal was to assess whether there was any difference in the characteristics of the songs' lyrics of the songs over the decades in relation to the level of word repetition and word quantities. Software components were developed for finding the lyrics of the most played songs for the desired period, as well as for cleaning and processing the data. The results obtained indicate a great variation in musical styles over the decades, as well as a significant increase in the number of words and the average number of words repeated in the lyrics. Thus, it is possible to see that Brazilian songs have become more repetitive in the last two decades and that they were much shorter in the 1960s.

Keywords: Music Information Retrival, Natural Language Processing, Web Scraping

References

Araujo, C., Cristo, M., and Giusti, R. (2019). Predicting music popularity on streaming platforms. In Anais do XVII Simpósio Brasileiro de Computação Musical, pages 141–148, Porto Alegre, RS, Brasil. SBC.

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 Anais do XXVI Simpósio Brasileiro de Multimídia e Web, pages 305–308, Porto Alegre, RS, Brasil. SBC.

de Araujo Lima, R., de Sousa, R. C. C., Lopes, H., and Barbosa, S. D. J. (2020). Brazilian lyrics-based music genre classification using a BLSTM network. In International Conference on Artificial Intelligence and Soft Computing, pages 525–534. Springer.

de Melo Faria, F. L., Pereira Jr, A. R., and Merschmann, L. H. (2015). Prediction of artists’ rankings by regression. In SBSI, pages 95–102.

Pereira, P. G. (2015). As relações entre língua, cultura, música e o processo de ensino-aprendizagem de língua estrangeira. Revista Estudos Anglo-Americanos, (43):62–83.

Powell-Morse, A. (2015). Lyric intelligence in popular music: A ten year analysis. https://www.seatsmart.com/blog/lyric-intelligence/.

Ribeiro, R. and Silla, C. (2014). Recuperação inteligente de letras de músicas na web. In: Anais do XXXIII Concurso de Trabalhos de Iniciação Científica da SBC, pages 41–50. SBC.

Schedl, M., Gomez, E., and Urbano, J. (2014). Music information retrieval: Recent developments and applications. Foundations and Trends in Information Retrieval, 8:127–261.

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

Solnyshkina, M., Zamaletdinov, R., Gorodetskaya, L., and Gabitov, A. (2017). Evaluating text complexity and flesch-kincaid grade level. Journal of Social Studies Education Research, 8(3):238–248.