Automatic English Essay Scoring Based on Machine Learning

Abstract—With the development of natural language processing(NLP) technology and machine learning, the research task of automatic English scoring(AES) is becoming clearer and clearer, and the research difficulties arise due to the mutual constraints of research methods and annotation data. How to build a perfect and reliable scoring system has become a great challenge under today's research. In this paper, we designed an English AES system, and verified the effectiveness of RF on English scoring model by analyzing the prediction effect of RF on non-text features and text features, and then compared the Pearson correlation coefficients(PCC) of RF(RF), GBDT, and XGBoost, and the study showed that the performance of RF algorithm is higher than the other two composition scoring methods. Keywords—machine learning, random forest algorithm, automatic scoring of English essays, Pearson correlation coefficient.