Automated essay scoring based on the enhanced chimp optimization algorithm-back propagation (ENChOA-BP) and K-means

Traditional essay scoring methods not only consume tremendous manpower and financial resources, but also the scoring results are easily affected by subjective factors. To improve the efficiency of essay scoring and reduce scoring errors, this paper proposes an automated essay scoring method based on the enhanced chimp optimization algorithm-back propagation neural network (ENChOA-BP) and K-means clustering. Firstly, this paper utilized K-means to select representative samples near cluster centers for experiments, decreasing the subjectivity influences of examiners. Then, three improvement strategies are introduced to the chimp optimization algorithm (ChOA) to improve its search capability, which is named the enhanced chimp optimization algorithm (ENChOA). In this algorithm, the good point set of initialization improves the global search ability of the ChOA algorithm. The teaching and memory strategies achieve group communication and experiential learning, enabling chimps to learn independently and approach optimal individuals. 15 benchmark functions are used to validate the superiority of the proposed algorithm by comparing it with 9 other algorithms. The experimental results indicate that ENChOA is more powerful than ChOA and other meta-heuristics algorithms. Finally, the ENChOA is used to optimize the parameters of back propagation neural network (BP), which is the ENChOA-BP model applied to essay scoring. The experimental results show that using the ENChOA-BP model for essay scoring has a correlation coefficient of up to 90% between the predicted score and the actual score.