Research on Automatic Scoring Algorithms for English Essays Based on Machine Learning

With the rise of machine learning and natural language processing, automatic scoring of English compositions has received more robust technical support. However, current research still faces several challenging issues, such as article structure and coherence, originality, and expressiveness. Due to challenges involving subjectivity, diversity, and cultural differences, accurate evaluation remains a difficult problem for automatic scoring. To address these issues, this paper employs machine learning algorithms, including Random Forest, Gradient Boosting Decision Tree, Extreme Gradient Boosting, Light Gradient Boosting Machine, Support Vector Regression, and K-Nearest Neighbor, to learn the features and patterns of compositions from a large set of training data, thereby achieving automatic scoring. The model's predictive results are evaluated based on Mean Squared Error, Root Mean Square Error, and Mean Absolute Error. Lastly, the interpretation and feedback of the scoring results are discussed, along with how to derive scoring results from the model's output and provide targeted suggestions and improvements as needed.