From Exploration to Exploitation: Understanding the Evolution of Music Careers through a Data-driven Approach
Open Access
- 25 September 2023
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 244-255
Abstract
We propose a data-driven methodology to analyze how music artists spread their interest (explore) and focus their attention (exploit) on distinct music topics (genres) while having peaks of success (hot streaks). Music topics are identified through community detection over a complex network modeling of artists, songs and their genres. Then, we analyze exploration and exploitation by measuring the entropy and quantifying it in three periods: before, during and after hot streaks. Results show artists explore topics before hitting their first hot streak and during their most successful period. After, they tend to reduce the range of topics by going deeper in a handful only. Such findings are relevant for identifying and nurturing creative talent in the music industry.Keywords
This publication has 8 references indexed in Scilit:
- Adaptive Fast XGBoost for Binary Classification2022
- Understanding the onset of hot streaks across artistic, cultural, and scientific careersNature Communications, 2021
- A Multimodal End-to-End Deep Learning Architecture for Music Popularity PredictionIEEE Access, 2020
- The Conundrum of Success in Music: Playing it or Talking About it?IEEE Access, 2019
- Hot streaks in artistic, cultural, and scientific careersNature, 2018
- Exploration and exploitation in evolutionary algorithmsACM Computing Surveys, 2013
- Problems of music information retrieval in the real worldInformation Processing & Management, 2002
- Scaling up dynamic time warping for datamining applications2000