Analyses of musical success based on time, genre and collaboration

• Autor(a) principal: Gabriel Pereira de Oliveira
• Data de Publicação: 2021
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Institucional da UFMG
• Texto Completo: http://hdl.handle.net/1843/47347; https://orcid.org/0000-0002-7210-6408
• topic: Hit song science; Music information retrieval; Musical genres; Complex networks; Data science; Data mining; Computação – Teses; Sistemas de recuperação da informação – Música - Teses; Redes complexas – Teses; Mineração de dados (Computação ) – Teses

Music is one of the world's most important cultural forms and one of the most dynamic. Such a dynamic nature can directly influence artists' careers and reflect their success. In this work, we analyze musical success from a genre-oriented perspective. Specifically, we model both artist and genre success timelines to detect and predict continuous periods with higher impact, i.e., hot streaks. As artist collaboration becomes one of the main strategies to promote new songs, we build and characterize success-based genre collaboration networks for nine markets worldwide. From such networks, we detect collaboration profiles directly related to musical success. Furthermore, we mine exceptional genre patterns in the networks where the success deviates from the average. Our findings show that studying genre collaboration is a powerful way to assess musical success by describing similar behaviors within collaborative songs from multiple perspectives. In addition, considering both global and regional markets is fundamental, as each country has its success dynamics and genre preferences. Such a regional approach also reveals local patterns that shape the global environment. Overall, our work contributes to both the academy and the music industry, as we shed light on the underlying factors of the science behind musical success.