A study of music revolution based on influence network and similarity test

Authors

  • Wenchun Jing
  • Yaxuan Chen
  • Quanrun Qiu

DOI:

https://doi.org/10.54097/ehss.v3i.1544

Keywords:

Influence network, Visual analysis, Similarity test, Music genres

Abstract

This paper develops a method to quantify the evolution of music and understand the role of humans in the evolution of music. First, a directional music influence network was set to show the parameters of "music influence". Then, a sub-network of the direct influencer network was established to obtain influence relationships, and "musical influence" was described and stored in this sub-network. Finally, a music similarity test model is used to compare which is more similar between artists of the same genre and artists of different genres. By comparing the influence and similarity between genres, the difference and connection of genres was got. Analyze whether "influencers" can actually influence their artists and their music through the above-mentioned similarity data. Then analyze the influence of music characteristics. Identify features representing major evolutions in the development of music from the data and get influencers in the network that represent major evolutions; analyze the evolution of a musical genre over time and explain how the genre or artist has changed over time; and illustrate how the model Express the social, political or technological change at the time.

Downloads

Download data is not yet available.

References

Bergstra J, Casagrande N, Erhan D, et al. Aggregate features and AdaBoost for music classification[J]. Machine learning, 2006, 65(2): 473-484.

Georges P. Western classical music development: a statistical analysis of composers similarity, differentiation and evolution[J]. Scientometrics, 2017, 112(1): 21-53.

Wang X, Kang Y, Zhang Y, et al. Analysis and Modeling of the Music Influence and Evolution[C]//2021 International Conference on Big Data, Artificial Intelligence and Risk Management (ICBAR). IEEE, 2021: 152-162.

Simonetta F, Carnovalini F, Orio N, et al. Symbolic music similarity through a graph-based representation[M]//Proceedings of the M Audio ostly 2018 on Sound in Immersion and Emotion. 2018: 1-7.

Berenzweig A, Logan B, Ellis D P W, et al. A large-scale evaluation of acoustic and subjective music-similarity measures[J]. Computer Music Journal, 2004: 63-76.

Dan Shi. Research on music style similarity detection algorithm[D]. Dalian University of Technology,2013.

Patrick George, Nguyen Nguyen, Zhang Jia-Ming. Visualizing musical similarity: clustering and mapping of 500 classical music composers[J]. Digital Humanities Research,2022,2(01):68-85.

Shen Guoming. Design and implementation of a music recommendation system based on original tags [D]. Beijing University of Posts and Telecommunications.

Aucouturier J J, Pachet F. Representing musical genre: A state of the art[J]. Journal of new music research, 2003, 32(1): 83-93.

Mauch M, MacCallum R M, Levy M, et al. The evolution of popular music: USA 1960–2010[J]. Royal Society open science, 2015, 2(5): 150081.

Downloads

Published

22-09-2022

How to Cite

Jing, W., Chen, Y., & Qiu, Q. (2022). A study of music revolution based on influence network and similarity test. Journal of Education, Humanities and Social Sciences, 3, 17-25. https://doi.org/10.54097/ehss.v3i.1544