Research on the College English Teaching Effectiveness Evaluation Algorithm Based on PSO and SVM

The advancement of artificial intelligence has opened new avenues for colleges and universities to assess teaching quality in a scientific and comprehensive way. Previous models for evaluating college English teaching effectiveness suffered from limited algorithms, leading to low accuracy and efficiency due to complex calculations. This paper presents a novel college English teaching quality evaluation model that is grounded in the principles of the particle swarm optimization (PSO) algorithm and support vector machine (SVM). Firstly, a multi-index evaluation system for English teaching effectiveness centered on teachers and students was established. Then the evaluation index data were input into the least squares support vector machine (LSSVM) model as samples, and PSO was used to find the optimal solution of the kernel function parameters and regularization parameters, so as to optimize the evaluation process of LSSVM and realize the evaluation of college English teaching effect. Experimental results indicate that this method yields optimal results for the evaluation of college English teaching effectiveness, with an average evaluation accuracy rate as high as 96.56 %, a short evaluation time, and a testing duration as low as 5 ms, significantly improving the accuracy and efficiency of the evaluation of college English teaching effectiveness.