The Discovery of Network Structure for E-Learning Participation Prediction: An Integrated Bayesian Networks Approach

Abstract

This research proposes an integrated Bayesian networks (BN) approach that adopts structural equation modeling (SEM) to discover the knowledge of the belief or causal relationships which are subsequently used as the BN network structure to predict the level of e-learning participation. SEM is an advanced statistical technique in the social and behavioral sciences to verify the hypothesized relationships, but it is seldom combined with other machine-learning algorithms. To overcome the difficulty of constructing a BN structure when learning from data, this study uses SEM to aid BN in discovering a suitable network architecture for prediction. 159 valid samples were collected from college students with online English learning experience. Compared with other prediction methods, the SEM-BN approach yielded better results than those of back-propagation neural networks (BPN) and classification & regression trees (CART).