Feature extraction and Classification of Learners using Multi-Context Recurrent Neural Networks

This study presents about a new procedure for extraction and classification of learners in a class using the neural networks. It is necessary to provide learning support corresponding to the understanding degree of each learner to improve learning process efficiency. For this purpose, this study develops a procedure to predict the achievement level of learners at the end of the class and classify them. A Multi-Context Recurrent Neural Network (MCRNN) is used for predicting achievement level and classifying learners. By providing additional education for the learners who are classified as a low degree by the proposed method, it is expected to be able to take countermeasures for not becoming dropout in early stage. In this study, numerical experiments are executed to verify the usefulness of the proposed method. To gather enough number of learners' data, this study generates the learners' growth process data that used as training and test data of MCRNN. The experimental result indicates that the proposed method succeeded in classifying learners into three groups based on the understanding degree at the end of a class.