Machine Learning Models: A Study of English Essay Text Content Feature Extraction and Automatic Scoring

Abstract

Accurate automatic scoring of English essay is beneficial for both teachers and students in English teaching. This paper briefly introduced an XGBoost-based automated scoring algorithm for English essay. To improve the accuracy of the algorithm, a long short-term memory (LSTM) semantic model was introduced to extract semantic scoring features from essays. Finally, the improved XGBoost algorithm was compared with the traditional XGBoost and LSTM algorithms in a simulation experiment using five types of essay prompts. The results indicate that the improved XGBoost algorithm has the best performance for automatic scoring of English essay and also requires the shortest scoring time.