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

Linna Huang

International Journal of Networking and Virtual Organisations, 2023, vol. 28, issue 2/3/4, 445-460

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. (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=133878 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:445-460

Access Statistics for this article

More articles in International Journal of Networking and Virtual Organisations from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().