Main Article Content
The current intelligent grading methods in English education have issues of feedback lag and incompatibility with manual grading, and manual grading is easily influenced by subjective consciousness. Based on this, this research selects Adaboost algorithm in ML algorithm to realize intelligent grading. The experiment improves the Adaboost algorithm according to the actual needs, constructs the Adaboost/CT algorithm, and verifies its effectiveness. The experimental results show that in the English intelligent scoring module, the adjacency accuracy of the Adaboost/CT algorithm for high- and low-quality English is 95.33%; 95.45% in the middle score; 94% in the breakdown. The comparison between Adaboost/CT model and DFA method shows that the accuracy and proximity accuracy of Adaboost/CT are 79.66% and 94% respectively, which are much higher than 55% and 92% of DFA. In addition, compared with Adaboost, the accuracy of Adaboost/CT is also significantly better than Adaboost. In practical application, the use of Adaboost/CT in the evaluation of English compositions can not only get more accurate scores, but also find out the shortcomings of each student, so as to improve them pertinently. Meanwhile, the accuracy, recall, and F1 values of the Adaboost/CT algorithm are 96%, 95%, and 95%, respectively, which are higher than those of the comparison algorithm. Overall, the improved Adaboost/CT algorithm has shown high effectiveness and practicality, and has high applicability and effectiveness in practical intelligent grading.