Music Emotion Analysis Based on PSO-BP Neural Network and Big Data Analysis

Area of Science:

• Computational intelligence in musicology
• Affective computing
• Digital signal processing for music analysis

Background:

• Current music teaching indirectly enhances students' musical emotional expression.
• Quantitative research on music emotional expression is a growing trend.
• The Particle Swarm Optimization-Backpropagation (PSO-BP) neural network offers a promising approach for this analysis.

Purpose of the Study:

• To investigate the influence factors of music emotion expression.
• To develop and validate a quantitative music emotion analysis model using PSO-BP neural networks and big data.
• To accurately analyze emotions within music expression through advanced algorithms.

Main Methods:

• Proposed a music emotion expression analysis model based on the PSO-BP neural network algorithm.
• Utilized the autocorrelation function to simulate and restore vocal music signals for emotion analysis.
• Employed an improved PSO-BP algorithm, multidimensional data models, fuzzy evaluation, and analytic hierarchy process for comprehensive analysis and quality assessment.

Main Results:

• Successfully restored vocal music signals by analyzing the maximum value of the autocorrelation function curve.
• The improved PSO-BP algorithm and multidimensional data models provided accurate music emotion analysis.
• Experimental validation confirmed the effectiveness and reliability of the proposed music emotion analysis model.

Conclusions:

• The PSO-BP neural network, combined with big data analysis, is effective for quantitative music emotion research.
• The developed model accurately identifies and analyzes emotional expression in music.
• This approach advances the field of computational musicology and affective computing.