Modelling simulation of college vocal music teaching development path based on big data analysis

Abstract

This paper uses big data analysis to determine user similarity and calculate the bias in selecting nearest neighbors. The temporal factor is introduced to fully reflect the changing status of users’ interest degrees so that the recommendation accuracy can be significantly improved. According to the nearest neighbors’ rating of experimental teaching resources, the collected data on the effectiveness of vocal music teaching in colleges and universities are clustered, and the results are reflected using degree weights and biases for updating. It was discovered that seven samples had actual student vocal rating values above 0.5, and the overall vocal test scores could reach 86 or higher. To be more energetic in contemporary times, vocal music teaching in colleges and universities should be reformed and innovated to incorporate big data analysis technology.

Keywords

• big data analysis
• time factor
• recommendation accuracy
• college vocal teaching
• degree weights
• 97d60