Evaluating Interaction Content in Online Learning Using Deep Learning for Quality Classification

Online learning is an important bridge between students and teachers for communication and learning. Online learning interaction content (OLIC) is created during information exchange. The evaluation of OLIC in the literature has been mainly focused on the perspective of quantitative instead of qualitative. The purpose of this study is to explore a new method for the qualitative evaluation of OLIC in online learning setting. A novel deep learning model is proposed for evaluating the quality of OLIC in the education domain. A multichannel of a framework based on bidirectional long short-term memory and attention mechanism (MFLBA) is used to achieve automatic evaluation. The results show that MFLBA takes the advantage of Word2Vector for evaluating the quality of OLIC. This study provides new horizon to analyze the nature of online interaction and monitors students' online learning process.