Can we predict success from log data in VLEs? Classification of interactions for learning analytics and their relation with performance in VLE-supported F2F and online learning

作者：

Highlights：

• Three system-independent classifications of interaction data for LA are proposed.

• They are based on agent type, frequency of use of activities and participation mode.

• Indicators and performance are related in online courses, but not in F2F courses.

• Interactions with peers and teachers predict students’ outcomes in online courses.

• The same is true for evaluating students and active interactions.

摘要

•Three system-independent classifications of interaction data for LA are proposed.•They are based on agent type, frequency of use of activities and participation mode.•Indicators and performance are related in online courses, but not in F2F courses.•Interactions with peers and teachers predict students’ outcomes in online courses.•The same is true for evaluating students and active interactions.

论文关键词：Interactions,Educational data,e-Learning,Learning analytics,Academic performance,Virtual learning environments

论文评审过程：Available online 2 July 2013.

论文官网地址：https://doi.org/10.1016/j.chb.2013.05.031