摘要
针对超星学习通课程学习过程中学生出现的被动学习、消极学习现象,提出分析学生学习态度的方法,构建学习态度跟踪模型。首先针对超星学习通平台收集的学生网络学习行为数据,选取与学习态度相关性较高的指标,形成训练数据集;然后,通过调查法对学生学习态度进行调查,以此获得学习态度标签;最后,基于分类算法构建学习态度跟踪模型,采用五折交叉验证方式进行实验。实验对比了不同分类算法的预测准确率,当采用AdaBoost(Adaptive Boosting)算法作为学生态度积极性分类算法时,可较为精准地预测学生的学习态度。实验结果表明,构建的学习态度跟踪模型具备一定的学习态度分析能力。
Aiming at the passive learning and negative learning phenomenon of students in the learning process of courses of superstar learning pass,a method to analyze students’learning attitude is proposed and a learning attitude tracking model is constructed.First,based on the students’online learning behavior data collected by the superstar learning pass platform,select indicators that are more relevant to learning attitudes to form a training data set.Then,investigate students’learning attitudes through investigation methods to obtain learning attitude labels.Finally,construct a learning attitude tracking model based on a classification algorithm,and use a five-fold cross-validation method for experiments.The experiment compares the prediction accuracy of different classification algorithms.When the AdaBoost(Adaptive Boosting)algorithm is used as the students’attitude positivity classification algorithm,the learning attitude can be predicted more accurately.Experimental results show that the constructed learning attitude tracking model has certain learning attitude analysis capabilities.
作者
郭长东
尹永学
GUO Changdong;YIN Yongxue(School of Science, Yanbian University, Yanji 133000, China)
出处
《河南教育学院学报（自然科学版）》
2021年第2期63-65,共3页
Journal of Henan Institute of Education(Natural Science Edition)
基金
延边大学教育教学改革研究课题。
关键词
超星学习通
网络学习行为
学习态度
分类算法
交叉验证
Superstar Learning Pass
online learning behavior
learning attitude
classification algorithm
cross-validation
