On demand analysis of learning experiences for adaptive content retrieval in an e-learning environment

Abstract

Understanding the learning experiences plays a vital role in identifying the suitable learning content for the learners. In this regard, the standards like the experience Application Programming Interface (xAPI) are of great help as they have the potential to record and represent the learning experiences over the e-learning environment. As the learner requirements vary with their understanding of the topics over the learning cycle, there is an inherent need for dynamic derivation of the learner’s requirement at each learning instance. However, the limitation with experience statements generated through the xAPIs is that they fail to convey the detailed information about the Learning Object (LO) or the learner who used it. This paper addresses the issues with the representation of experience statements by proposing a multidimensional view of learning experiences such that they could be analyzed effectively. The Cross Dimensional Slicing (CDS) algorithm proposed in this paper has proved that the multidimensional representation of learning experiences greatly improves the effectiveness of analyzing them and thereby improving the precision of LOs being recommended. Also, the steep increase in the accuracy of recommendation of LOs over the different batches of learners considered for the study has reduced the number of slow learners of the learning environment altogether.