Educational Data and Learning Analytics in KazNU MOOCs Platform

Ye. S. Alimzhanov, Мадина Мансурова

2018

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The initial hype around massive open online courses (MOOCs) already subsided, but the number of new learners in MOOCs platforms is still growing. Due to low completion rates in the MOOCs compared to enrolled students it is important to establish and validate quality standards for these courses. Employing of educational data and learning analytics to improve lesson plans and course delivery become an innovative approach for teachers, curriculum developers and policy makers in education. Learning analytics of online courses can be also used for enhancement of classroom teaching by blending online and face-to-face learning models. This work presents some observations about the behavior of students, obtained by analyzing the data generated during delivery of 13 MOOCs. Besides classiﬁcation of learners by analysis their activity data, other interesting characteristics about platform learners like demographic, gender and level of education are described. The results indicate that the quality of interpersonal interaction within a course relates positively and signiﬁcantly to student scores.