A proposed learner activity taxonomy and a framework for analysing learner engagement versus performance using big educational data

Konstantinidis, Stathis; Fecowycz, Aaron; Coolin, Kirstie; Wharrad, Heather; Konstantinidis, George; Bamidis, Panagiotis

Abstract

The inclusion of information and communication technologies in Healthcare and Medical Education is a fact nowadays. Furthermore numerous virtual learning environments have been established in order to host both educational material and learner’s online activities. Online modules in a VLE can be designed in very different ways being part of different types of courses, while different models can be used to design the course based on what the creator aims to achieve. Thus, the types and the importance of the different elements of the online course may vary a lot. At the same time the need of a global approach to gather big educational data in order to provide valid meaning to the data through learning analytics and educational data mining is urgent. In order this to be achievable we propose a Learner Activity Taxonomy in which the different elements of the learners activity data can be categorised and a Learner Engagement Framework in which the importance of the different elements is vital in order for an analysis of the big educational data to provide a meaningful result. The initial application to practice of the Taxonomy and the Framework are presented based on data from 3 modules at 2 Universities, while the impact of them along with its limitations are discussed.

Citation

Konstantinidis, S., Fecowycz, A., Coolin, K., Wharrad, H., Konstantinidis, G., & Bamidis, P. (in press). A proposed learner activity taxonomy and a framework for analysing learner engagement versus performance using big educational data. Proceedings / IEEE International Symposium on Computer-Based Medical Systems. IEEE International Symposium on Computer-Based Medical Systems,

• Journal Article Type: Article
• Conference Name: 30th IEEE International Symposium on Computer-Based Medical Systems (IEEE CBMS 2017)
• End Date: Jun 24, 2017
• Acceptance Date: Jun 1, 2017
• Online Publication Date: Nov 13, 2017
• Deposit Date: Sep 11, 2017
• Publicly Available Date: Nov 13, 2017
• Journal: Proceedings of the IEEE International Symposium on Computer-Based Medical Systems
• Electronic ISSN: 2372-9198
• Peer Reviewed: Peer Reviewed
• Keywords: Learning Analytics; Big Data; learner engagement; online learning analysis, activity data; paradata
• Public URL: https://nottingham-repository.worktribe.com/output/894924
• Publisher URL: http://ieeexplore.ieee.org/document/8104232/
• Related Public URLs: http://www.cbms2017.org; http://www.cbms2017.org/slot/proposed-learner-activity-taxonomy-and-framework-analysing-learner-engagement-versus
• Additional Information: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
• Contract Date: Sep 11, 2017