Effects of learner interaction with learning dashboards on academic performance in an e-learning environment

This study aims to investigate learners' interaction with the learning dashboards as a predictor outcome of an online learning experience and, to what extent this interaction data could be used to predict and/or provide guidance through their academic performance. For this purpose, a prescriptive learning dashboard integrated into an e-learning environment was developed as a learning analytics tool. The participants consisted of 126 higher education students enrolled in the 12-week Computer Networks and Communication course. Data gathered through logs and academic performances of learners were analysed with data mining techniques. The result of cluster analysis, based on interaction with the prescriptive learning dashboard, showed that learners were separated into four groups according to their behavioural patterns. A similar pattern appears when the related clusters are profiled based on the academic performances. At predictive analysis, the study indicates that the interaction with prescriptive learning dashboard had certain effects on academic performance of learners significantly and artificial neural networks algorithm yielded the best performance for predicting academic performance. The results support that the usage prescriptive learning dashboards can be applied in online courses as an instructional aid to improve performance of learners and learning design in e-learning environments.