Open AccessResearch on Intelligent Evaluation System of Influence Model Using Cosine Similarity
Author(s) -
Zhitao Li,
Xin Wang,
Xiaoling Li
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1982/1/012035
Subject(s) - similarity (geometry) , computer science , variance (accounting) , cosine similarity , pop music automation , norm (philosophy) , measure (data warehouse) , artificial intelligence , musical composition , data mining , music education , art , pattern recognition (psychology) , visual arts , image (mathematics) , epistemology , philosophy , accounting , business
Nowadays, music plays an increasingly important role in social development. As time goes by, music influences music, artists, and the times. The purpose of this paper is to create a model to quantify the influence of previously created music on new music and music artists. Firstly, this paper constructs two music influence networks based on artists and genres and defines and explains some meaningful parameters of music influence networks. The parameters of this paper describe the influence of communication between artists, and then this paper calculates and explains the parameters in the subnet. Next, this paper uses cosine similarity to measure similarity between two music samples and innovatively uses variance as the weight of music features to identify differences between music. Then the similarity measure is constructed based on matrix norm. Finally, this paper concludes that artists within schools are more similar than artists between schools.