Caracterizando e quantificando inovação em redes de similaridade musical.

Abstract

Music investigations with main focus in the study of similarity relationships between songs, albums and artists play an important role when trying to understand trends in the history of music genres. The influence exercised by these entities in a similarity network can be categorized in a multitude of points-of-view, including disruption. A disruptive object is one that creates a new stream of events, changing the traditional way of how a context operates. Such class of innovative initiatives can be observed many times during the history of music, as in the emergence of the rock and roll at the end of the 1940’s, passing by the punk rock revolution three decades later, and finally reflecting here in Brazil during the boom of the national rock in the early eighties. The proper categorization of innovation and measurement of disruption remain as a tasks with large room for improvement, and these gaps are even more evident in the music domain, where the topic has not received much attention so far. This work builds on preliminary studies focused on the analysis of music disruption derived from metadata-based similarity networks, demonstrating that the raw audio can augment similarity information. We developed a case study based on a collection of a Brazilian local music tradition called Forró, that emphasizes the analytical and musicological potential of a musical disruption metric to describe and explain a genre trajectory over time.