Development and Evaluation of Across-Unit Diagnostic Feedback Mechanism for Online Learning

Solving well-structured problems often requires using considerable related concepts which are usually scattered and introduced throughout different learning units of a subject. In addition, poor learning of related concepts of preceding units may block the learning of subsequent units, and eventually leads to the inability to solve wellstructured problems of a subject. Thus, this work proposes using across-unit diagnostic feedback, which can identify weak concepts not only within a unit but also in different units. Furthermore, the provided feedback can be used to recommend remedial learning paths for students, and inform the students the priority of the paths to understand which weak unit should be remedied first and which weak concepts within a unit should be remedied first. Students can refer to the instructions and use the provided corresponding remedial materials to conduct remedial learning in a systematic way. To discriminate the learning effect among various feedback types, this project will compare the proposed system, the Across-Unit Diagnostic Feedback System (AUDFS), with two other systems, the Single-Unit Diagnostic Feedback System (SUDFS) and the Traditional Feedback System (TFS). Experiment results show that the proposed system significantly enhanced learning achievement and the ability to solve well-structured problems for students. The mean student retention time of the proposed system is significantly higher than that of other systems, indicating that the proposed system enables sustained connection between students and the system. Additionally, positive correlations exist between student retention time of the proposed system and student post-test scores. Through a questionnaire and interviews, most students expressed positive attitudes to the proposed system.