Educational data mining and data analysis for optimal learning content management: Applied in moodle for undergraduate engineering studies

Charitopoulos, A. and Rangoussi, M. and Koulouriotis, D. (2017) Educational data mining and data analysis for optimal learning content management: Applied in moodle for undergraduate engineering studies. In: 2017 IEEE Global Engineering Education Conference (EDUCON).

Abstract

Educational data mining applies data mining methods and tools to education-related data, typically collected through the use of an e-learning platform. Data stored in an e-learning platform database include user-platform interaction events (counts of scrolls, mouse clicks or page loads), platform access times per session or in total, times between events and various assessment scores such as grades per quiz or per session test, final grades, etc. In the present paper we focus on the time between actions (TBA) taken by the learner while he/she interacts with the platform. TBA values relay information on the mode of interaction of an individual learner with the platform. The two major questions addressed are (i) whether TBA values follow any probability density function (PDF) and if so, which is the PDF that optimally fits the data, and (ii) whether the parameters of such optimally fitted PDFs might serve as features for the clustering of the learning content modules or sessions into clusters of similar characteristics or functionalities. Results verify that skewed (asymmetric) PDFs can be fitted on the TBA value histograms with adequate accuracy. Furthermore, the parameters of few optimally fitted PDFs, used as a feature vector, result in a meaningful clustering of learning content parts into clusters of similar “character”. Clustering results may then be used as a recommendation to the course designer / instructor, to improve content structure or to optimally distribute/sequence parts of the course material.

Actions (login required)

View Item