Preprocessing and analyzing educational data set using X-API for improving student's performance

Educational data mining concerns of developing methods to discover hidden patterns from educational data. The quality of data mining techniques depends on the collected data and features. In this paper, we proposed a new student performance model with a new category of features, which called behavioral features. This type of features is related to the learner interactivity with e-learning system. We collect the data from an e-Learning system called Kalboard 360 using Experience API Web service (XAPI). After that, we use some data mining techniques such as Artificial Neural Network, Naïve Bayesian, and Decision Tree classifiers to evaluate the impact of such features on student's academic performance. The results reveal that there is a strong relationship between learner behaviors and its academic achievement. Results with different classification methods using behavioral features achieved up to 29% improvement in the classification accuracy compared to the same data set when removing such features.