機械学習手法を用いた学生の授業後コメントに基づく成績推定の試み

抄録

This study proposes prediction approaches of students’ grades based on their comments data. Students write their comments freely after each lesson. The proposed methods basically employ latent semantic analysis (LSA) and two types of machine learning technique: SVM (support vector machine) and ANN (artificial neural network) for predicting students’ final grades. Moreover, an overlap method was proposed to improve the accuracy prediction results. The proposed methods achieve 62.6％ and 57.2％ prediction accuracy of students’ grades from lesson 1st to 6th and 50.7％ to 48.7％ from lesson 7th to 15th by SVM and ANN, respectively.