Intelligent Evaluation Algorithm for English Teaching Quality Based on HMIPSO-Optimized BP Neural Networks

Traditional methods for assessing English teaching quality in higher education have gradually revealed their limitations, failing to reflect the dynamic changes comprehensively and accurately in the teaching process and the multidimensional nature of teaching outcomes. This study proposes an English teaching quality evaluation model based on the combination of a hybrid multi-strategy improved particle swarm optimization (HMIPSO) and backpropagation (BP) neural network. A teaching quality evaluation system is constructed using teaching content, teaching methods, and teaching outcomes. Experimental results show that the HMIPSO-BP model outperforms the traditional BP neural network model, with the mean squared error reduced by approximately 27.8% and the minimum error decreased by approximately 28.2%. This approach significantly reduces computation time while maintaining evaluation accuracy. The proposed method provides a novel and effective technical pathway for monitoring and improving the quality of English teaching in higher education.