摘要
随着教育越来越走向信息化,大量的教育数据会被保存,在海量教育数据中挖掘出学生的潜在信息是智能教育中非常值得研究的问题之一。针对目前大多数得分预测都是预测一个总分,无法具体到每一题得分预测的问题,对考试中存在的主要题型进行了研究,结合现有试题得分预测方法,指出其优势与不足,提出基于认知诊断和神经网络分别预测客观题和主观题得分的方法。该方法结合认知诊断理论计算出学生的知识状态,通过矩阵算法来预测学生在每道客观题上的得分,再将学生的知识状态作为特征,学生得分作为训练标签,使用卷积神经网络来训练并且预测学生在每道主观题上的得分。将两种方法分别与传统方法进行比较,结果表明两种方法分别在客观题和主观题上的效果比传统方法提高了很多。
As education becomes more and more informatized, a large amount of education data will be preserved. Mining the potential information of students from the massive amount of education data is one of the issues worthy of research in intelligent education. In view of most of the current score predictions that predict a total score, which cannot be specific to the score prediction of each question, the main question types existing in the test are analyzed. Combined with the existing test question score prediction methods, we point out their advantages and disadvantages and put forward a method to predict the scores of objective and subjective questions respectively based on cognitive diagnosis and neural network. This method combines the cognitive diagnosis theory to calculate the student’s knowledge state, predicts the student’s score on each objective question through a matrix algorithm, trains and predicts student’s scores on each subjective question by convolutional neural network, with the student’s knowledge state as a feature and the student’s score as a training label. Comparing the two methods with the traditional methods, the results show that the effects of the two methods on objective and subjective questions are much higher than the traditional methods.
作者
史浩杰
李幸
贾俊铖
匡健
那幸仪
SHI Hao-jie;LI Xing;JIA Jun-cheng;KUANG Jian;NA Xing-yi(School of Computer Science and Technology,Soochow University,Suzhou 215006,China;Momenta(Suzhou)Technology Company Limited,Suzhou 215100,China)
出处
《计算机技术与发展》
2022年第2期39-44,共6页
Computer Technology and Development
基金
中国博士后科学基金资助及项目(2017M611905)
江苏高校优势学科建设工程资助项目(PAPD)。
关键词
得分预测
客观题
主观题
认知诊断
神经网络
score prediction
objective questions
subjective questions
cognitive diagnosis
neural network
