Title: The application and research of double-layer music emotion classification model based on random forest algorithm in digital music

Authors: Linna Huang

Addresses: School of Preschool Education and Humanities, Dongguan Polytechnic, Dongguan, 523808, China

Abstract: It is urgent to solve the problem of music emotion classification. The stochastic forest algorithm is easy to operate and performs better than other single-layer classification models. Aiming at the problems of feature extraction and classification in conventional music emotion classification methods, music features are divided into long-term features and short-term features, and a two-layer music emotion classification model integrating a random forest (RF) algorithm is designed. The experimental results showed that the SVM model using the Gaussian radial basis kernel function had the highest classification accuracy of 90.78% in training the SVM model. The overall classification accuracy of the two-layer music emotion classification model was 98.92%, the recall rate was 97.63%, and its indicators in different emotion categories were the highest, with an average F1 value of 0.919. To sum up, the two-layer music emotion classification model based on the RF algorithm proposed in the research has excellent recognition and classification capabilities.

Keywords: random forest; RF; emotional classification; double layer model; music characteristics; SVM.

DOI: 10.1504/IJNVO.2023.133878

International Journal of Networking and Virtual Organisations, 2023 Vol.28 No.2/3/4, pp.445 - 460

Received: 28 Dec 2022
Accepted: 12 Jun 2023
Published online: 04 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article