Adaptive Starting Points in Video Learning Environments for New Learners Based on Video and Topic Tree Relations

Abstract

AbstractTeaching and learning complex fields of knowledge, including engineering, is rarely easy, particularly because of rapid changes and high interdependences among different topics. In addition, learners are increasingly heterogeneous in terms of different experiences and levels of knowledge. Not dealing with increasingly heterogeneous learners appropriately may result in high dropout rates and poor training quality. A possible way out is addressing learners more individually. Hopefully, digital learning offers, such as video platforms, will help to convey knowledge better and more individually through a broader learning offer. But learners with different levels of knowledge need different starting points into a course based on their level of knowledge. Thus, a crucial problem is finding the most appropriate starting point for learners in such environments. This paper presents a novel approach to identify individual starting points in online video courses for learners with different levels of knowledge. The underlying algorithm identifies topics that are most useful for the concrete learner at the beginning of the course in order to introduce a new field of knowledge appropriately.KeywordsAdaptive learningVideo learningHeterogeneous learners