Zimai Dong, Cailian Xie, Yukun Xiao, Yuxuan Hou, Zhixiong Tao
Dalian Maritime University, Liaoning, Dalian, 116026
Music is the result of human's conscious cultural creation. The creation of some artists has been deeply influenced and inspired by other artists and works of art, thus showing similarities in certain features of songs. There are also revolutionary changes in music, such as the creation of brand-new musical styles, the emergence of new genres, re-creation of genres and so on. Through supervised learning, the paper directly use genre as the label of classification. However, due to the failure of the test, the paper reclassified the artist and music attributes in the only way based on the data. In the process of classification, firstly, the data are normalized, then the principal component analysis ((PCA)) is used to reduce the dimension of the attributes, and then the K-means clustering algorithm is used to cluster the samples to get new classification results. The paper creates the concept of degree coefficient to determine whether the new category reflects the original genre. The paper also introduces the concept of information entropy, which is based on artist data and music data to quantify the similarity between and within genres. As a result, the purpose of developing the measure of music similarity is achieved. The paper uses the degree coefficient to eliminate the general level of music attributes in the environment of influencers and followers and highlight the differences between them and the general population. Therefore, it can truly reflect whether the influencer has influence on his followers, as well as the size of the influence.
Information entropy, Degree coefficients, Two-way pointer search, Fitting
Zimai Dong, Cailian Xie, Yukun Xiao, Yuxuan Hou, Zhixiong Tao. Research on the influence of Music revealed by big data based on the Analysis of Network Theory. Frontiers in Art Research (2021) Vol. 3 Issue 2: 10-14. https://doi.org/10.25236/FAR.2021.030203.
 Y F Huang, S M Lin, H Y Wu, Y S Li. Music genre classification based on local feature selection using a self-adaptive harmony search algorithm. Data & Knowledge Engineering 92 (2014) 60–76.
 C M Wu, Z Cao. Noise distance driven fuzzy clustering based on adaptive the paper lighted local information and entropy-like divergence kernel for robust image segmentation. Digital Signal Processing 111 (2021) 102963.
 Henk Jan Honing. Evolving Musicality. Massachusetts: The MIT Press, 2019.
 Biggs, Norman, E. K Lloyd, and Robin J. Wilson. Graph Theory, 1736-1936. Oxford University Press, 1986. Oja, E., 1982. A simplified neuron model as a principal component analyzer. J. Math. Biol., 267-273.
 S Wang, S X Sa, Introduction to Database System. Beijing: Higher Education Press. 2014.9