Musical Success in the United States and Brazil: Novel Datasets and Temporal Analyses

Abstract

Music is not only a worldwide essential cultural industry but also one of the most dynamic. The increasing volume of complex music-related data defines new challenges and opportunities for extracting knowledge, benefiting not only different music segments but also the Music Information Retrieval research field. In this article, we assess musical success in the United States and Brazil, two of the biggest music markets in the world. We first introduce MUHSIC and MUHSIC-BR, two novel datasets with enhanced success information that combine chart-related data with acoustic metadata to describe the temporal evolution of musical careers. Then, we use such enriched and curated data to cluster artists according to their success level by considering their high-impact periods (hot streaks). Our results reveal three groups with distinct success behavior over time. Furthermore, Brazil and the US present specific music success patterns regarding artists and genres, reflecting the importance of analyzing regional markets individually.

Exceptional Collaboration Patterns in Music Genre Networks

“…Besides most studies in HSS being related to prediction tasks, other works focus on further aspects of musical success. For instance, music networks have been used in studies aiming to analyze regional differences [Mondelli et al 2018, Oliveira et al 2020] and user preferences [Pereira et al 2018]. Furthermore, collaboration-aware studies have become promising in HSS, as they provide strong evidence that factors leading to an ideal musical partnership can be understood by exploring collaboration patterns that directly impact its success [Bryan andWang 2011, Silva et al 2022].…”

“…The dataset used is the Music Genre Dataset (MGD) 3 [Oliveira et al 2020], which gathers information from Spotify, the most popular music streaming service today. MGD contains data on songs, artists and music genres based on global weekly rankings (comprises all markets where Spotify operates) and eight of the top ten music markets in 2019: 4 United States, Japan, United Kingdom, Germany, France, Canada, Australia and Brazil.…”

“…For each genre connection (i.e., network edge), we also consider its collaboration profile according to [Oliveira et al 2020]. Such profiles allow to assess musical success by describing similar behaviors within collaborative songs from multiple angles.…”

“…This widely adopted strategy is a strong force driving music nowadays, as such connections usually help artists bridge the gap between styles and genres, overlapping new fan bases and consequently increasing their numbers [Bryan andWang 2011, Silva et al 2022]. In fact, the genre perspective is very important when analyzing the impact of collaborations on musical success, as such partnerships may take place not only through intra-genre collaborations but also through inter-genres, bringing an additional dimension to hit songs [Mondelli et al 2018, Oliveira et al 2020].…”

MGD+: An Enhanced Music Genre Dataset with Success-based Networks

“…Whereas these datasets provide valuable insights into narrowed contexts, they may fail to capture the broader global music landscape and the significant influence of local and cultural aspects. Indeed, recognizing the importance of local artists, genres, and musical traditions is crucial for a comprehensive understanding of the music ecosystem [Oliveira et al 2020. Furthermore, the role of musical collaborations, which constantly transcend genre boundaries, is often overlooked in MIR research, despite being a prominent and influential factor [Silva et al 2019a].…”