Dynamic cluster structure and predictive modelling of music creation style distributions

Rajsuryan Singh, Eijiro Nakamura

arXiv (Cornell University)(2022)

Cited 0|Views5
No score
Abstract
We investigate the dynamics of music creation style distributions to understand cultural evolution involving advanced intelligence. Using statistical modelling methods and several musical statistics extracted from datasets of popular music created in Japan and the United States (the US), we explored the dynamics of cluster structures and constructed a fitness-based evolutionary model to analyze and predict the evolution of music creation style distributions. We found that intra-cluster dynamics, such as the contraction of a cluster and the shift of a cluster centre, as well as inter-cluster dynamics represented by clusters' relative frequencies, often exhibit notable dynamical modes that hold across the cultures and different musical aspects. Additionally, we found that the evolutionary model incorporating these dynamical modes is effective for predicting the future creation style distributions, with the predictions of cluster frequencies and cluster variances often having comparable contributions. Our results highlight the relevance of intra-cluster dynamics in cultural evolution, which have often been overlooked in previous studies.
More
Translated text
Key words
music creation,dynamic cluster structure,predictive modelling
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined