Design and Implementation of the Reliable Learning Style Recognition Mechanism Based on Fusion Labels and Ensemble Classification

Abstract

Learning style recognition is an indispensable part of achieving personalized learning in online learning systems. The traditional inventory method for learning style identification faces the limitations such as subject and static characteristics. Therefore, an automatic and reliable learning style recognition mechanism is designed in this paper. Firstly, a learning style labeling framework (LSDFA) based on multi-label fusion is proposed, which can obtain learning style labels by mining the potential information of two sets of inventories. Furthermore, a two-layer ensemble model (SRGSML) based on learners' online learning behaviors data to recognize learners' learning styles is proposed, which combines the resampling technology (SMOTE) to solve the unreliable prediction problem caused by class imbalance. The superiority of the proposed mechanism is verified on learning behavior data of 2,056 learners during the online teaching period of Shanghai Normal University. Experimental results show that the recognition accuracy of SRGSML achieves to 0.977, as well as prove the effectiveness of the LSDFA for labeling learning style.