Functional and architectural solution of a software package for the analysis of educational data

2021

Closed access Metadata (CSL-JSON)
DOI 10.1109/icoten52080.2021.9493505
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 development of e-learning systems and the introduction of digital technologies in the traditional educational process leads to the emergence of large information arrays, which are studied by the analysis of educational data (EDM) - a scientific discipline associated with the application of data mining methods to information produced by educational institutions. The article discusses EDM methods and their features in comparison with data mining methods. The directions of the EDM application and the advantages that its use gives to all participants in the educational process are analyzed. The problems and challenges facing the EDM are analyzed, as well as promising areas of research.