基于线性回归算法的在线学习行为分析-《计算机技术与发展》

文章信息/Info

Title:: Online Learning Behavior Analysis Based on Linear Regression Algorithm

Author(s):: GUO Ling-ling; FAN Si-meng; WANG Mei; SU Dong-na; School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China

Keywords:: online learning behavior; K-means clustering algorithm; linear regression; learning behavior analysis; learner centered

摘要:: 互联网的快速发展带动了教育领域的发展,促使在线学习迅速兴起并深受教育人士认可。因此各种在线学习平台中的教学数据飞速递增,对于如何充分利用、深度分析平台存储数据的价值,引起了教育从事人员的关注。应用机器学习技术,对学习者在线学习行为与学习结果之间的相关性进行了一系列学习分析。通过收集在线平台上学生学习时的数据,对收集到的数据进行预处理。基于 K-means 聚类算法对学习者聚类建模,将学生聚类成不同的类型。教师给予不同群体的学生相应的资料,有效地提高学生的学习效率。基于线性回归算法分析学生学习行为,确定学习行为对于学生最终成绩影响程度,教师在众多在线平台学生活动中筛选出对学生最终成绩影响较大的活动,完善教学方式。

Abstract:: The rapid development of the Internet has driven the development of the education field,prompting the rapid rise of online learning and recognized by educators. Therefore,the teaching data from various online learning platforms increase rapidly. How to fully utilize and deeply analyze the value of the data stored on the platform has aroused the attention of educators. A series of learning and analysis on the correlation between learners’ online learning behavior and learning outcomes were conducted by applying machine learning technology. Firstly,the studying data of students from online platforms were collected and preprocessed. Secondly,the K-means clustering algorithm was used to cluster the learners into different types. Teachers give the students in different groups the appropriate material,improving their learning efficiency effectively. Finally, the students’ learning behavior was analyzed by the linear regression algorithm to determine the influence degree of learning behavior on students’ final scores. From the numerous online activities,teachers can screen out the activities that have a great influence on students爷 final scores and improve the teaching methods.