面向智慧学习环境的学习者情感预测方法

发布时间：2018-05-31 23:30

本文选题：智慧学习环境 + 远程教育　；参考：《计算机辅助设计与图形学学报》2017年02期

【摘要】：为了解决传统远程教育中的"情感缺失"问题,提出采用模糊认知图(FCM)构建一种面向智慧学习环境的学习者情感预测模型,对远程学习过程中的学习者情感进行实时预测,以便教学系统根据预测情感及时有效地调整教学策略,从而促进学习者的认知.首先,选择容易引起学习者情感变化的情感影响因子作为FCM的输入信号;然后通过活动Hebbian学习法推理计算,得到能代表情感重要属性的2个参数——效价和激活度;最后将这2个参数映射于一个在二维笛卡儿直角坐标系中构建的学习者情感空间中,便可以定性定量地预测出学习者当前的情感状态.实验结果表明,FCM模型的预测结果与大多数学生的实际情绪反应相符;与其他贝叶斯网络模型相比,FCM模型具有更高的情感预测准确率.
[Abstract]:In order to solve the problem of "affective deficiency" in traditional distance education, a model of learners' affective prediction based on fuzzy cognitive map (FCM) is proposed to predict learners' affective in the process of distance learning in real time. So that the teaching system can adjust teaching strategies timely and effectively according to predictive emotion, so as to promote learners' cognition. Firstly, the affective influence factors which are easy to cause the learners' affective changes are selected as the input signals of FCM, and then two parameters-titer and activation degree, which can represent the important attributes of emotion, are obtained by using the active Hebbian learning method. Finally, by mapping these two parameters into a learner's affective space constructed in a two-dimensional Cartesian coordinate system, the present emotional state of learners can be predicted qualitatively and quantitatively. The experimental results show that the prediction results of the FCM model are consistent with the actual emotional responses of most students, and that the FCM model has a higher prediction accuracy than other Bayesian network models.
【作者单位】：中南大学信息科学与工程学院;湖南文理学院电气与信息工程学院;中国地质大学自动化学院;
【基金】：国家自然科学基金(61403422)
【分类号】：G434

【相似文献】