摘要
提出一种结合概率推理与决策理论来有效构建C++智能教学系统ITS(Intelligent tutoring System)中学生学习模型的方法,以帮助ITS达到自适应教学的目的。首先,利用概率推理来识别学生的知识状态。其次,采用学习风格问卷调查(ILS)和机器学习的方法来分类预测学生的学习风格,并且实验数据也验证了这种方法的可靠性和有效性。通过将模块植入现有的ITS并投入实际的教学应用中,学生的反馈表明了本系统对提高学生的学习兴趣和学习效果具有积极作用。
This paper proposes a new approach which is based on probabilistic inference and learning style theory to efficiently build student learning model of C ＋＋ intelligent tutoring system （ ITS ） for the purpose of providing this ITS with adaptive teaching strategies. Firstly,probabilistic inference based on Bayesian Network is applied to identify the knowledge states of students. Secondly, learning style survey （ILS） and machine learning tools are integrated to predict and classify the learning styles of students, and also the reliability and validity of this method was proved by real experimental data. The prototype system was transplanted into existing ITS and then put into our real teaching environment for trial. From students＇ feedback ,the result shows that system has positive influence on helping students enhance their interests and effectiveness in learning C ＋＋ programming language.
出处
《计算机应用与软件》
CSCD
2009年第12期170-173,共4页
Computer Applications and Software
关键词
智能教学系统
学习风格
贝叶斯网
学生学习模型
Intelligent tutoring system Learning style Bayesian network Student leaning model
作者简介
杨诚一，硕士生，主研领域：中文信息处理，人机交互。
