A study on the effect of music on college students’ depression and anxiety based on big data analysis

Abstract

The purpose of this paper is to investigate music’s effect on anxiety regulation among college students, to help them find new ways to improve their negative emotions and enhance their emotion regulation ability. This paper first describes the association rule mining algorithm, then optimizes and improves the association rule mining algorithm by using the particle swarm algorithm to encode and calculate the fitness value to generate the population optimization of the particle swarm. The optimization algorithm iteratively searches for the optimal solution, and the particles achieve the search process by following their own and the population’s optimal particles and using the particle swarm optimization association rule algorithm to mine data on the effect of music intervention on anxiety and depression. When the different interventions were applied, the post-test depressive mood level of the music group was significantly lower than that of the motor training group p=0.008 and significantly lower than that of the blank group p=0.006. And the difference between the pre-test and mid-test results of SAS in the music group was significant p=0.014, and the difference between the pre-test and post-test results of the music group was borderline significant p=0.069. When the intervention was applied with music, the intervention group SDS All four dimensions scores decreased when comparing themselves before and after the intervention, depressive psychological disorder 18.83±3.20 decreased to 14.41±3.39 and psycho-affective disorder decreased from 4.87±0.13 to 2.83±0.84. Thus, it can be seen that music significantly affects the intervention of anxiety and depressive mood.

Keywords

• big data analytics
• music intervention
• optimization algorithm
• association rule mining algorithm
• particle swarm algorithm
• 97m80