北京邮电大学学报(社会科学版) ›› 2020, Vol. 22 ›› Issue (6): 90-100.doi: 10.19722/j.cnki.1008-7729.2020.0043

• 教育研究 • 上一篇    下一篇

基于LSTM的学习成绩预测及其影响因素方法研究

曹洪江(1972—),男,湖南双峰人,博士,副教授   

  1. 武汉理工大学 经济学院,湖北 武汉430000
  • 收稿日期:2020-03-02 出版日期:2020-12-30 发布日期:2021-01-25
  • 通讯作者: 曹洪江(1972—),男,湖南双峰人,博士,副教授
  • 作者简介:曹洪江(1972—),男,湖南双峰人,博士,副教授
  • 基金资助:
    教育部人文社会科学研究规划基金项目(17YJA870006);武汉理工大学教学研究项目(w2019129)

LSTM-based Learning Achievement Prediction and Its Influencing Factors

  1. School of Economics, Wuhan University of Technology, Wuhan 430000, China
  • Received:2020-03-02 Online:2020-12-30 Published:2021-01-25

摘要: 关于学生成绩预测的研究普遍存在数据结构单一和学习器浅层线性的问题。针对学生历史成绩的时序性及学习过程的遗忘特征,引入LSTM网络对学生知识结构状态进行建模,并融合情感特征和行为特征,通过全连接神经网络对学习成绩进行预测。实验结果表明,该方法能够显著提升学习成绩预测的准确性。同时,以此为基础,进一步提出了成绩主要影响因素的判断方法。


关键词:  , LSTM, 成绩预测, 学生情感, 学生行为

Abstract: There are general problems in the study of student performance prediction, such as simple data structure, shallow linear layer of learner, etc. Therefore, considering the temporality of students’ historical performance and the forgotten features during learning process, a LSTM network was introduced to model the state of students’ knowledge structure. The features of emotion and behavior were integrated to predict the academic performance through fully connected neural networks. Experimental results show that the method can significantly improve the accuracy of prediction of academic performance. At the same time, a method for judging the main influencing factors of performance is further proposed.


Key words: LSTM, academic performance prediction, student emotion, student behavior

中图分类号: