Exploration of student behavior patterns through digital footprints

Journal of Mathematics Mechanics and Computer Science, 2019

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.26577/jmmcs-2019-3-25
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

In this experimental work, a set of Data Mining methods were used to reveal student behavior patterns by analyzing their digital footprints in social Web.Data were gathered from open social profiles of students learning at one of the universities in Kazakhstan.For this case study, 25 publications appeared in the students' social feeds were selected, and students' digital footprints (namely, information about their likes on these publications) were fixed.Patterns extracted via analysis of these footprints were compared with the results of psychological tests that were carried out before; and finally, the degree to which both these findings corroborated and complemented each other was assessed.Therefore, conducted experiments provided by R ecosystem demonstrated the potential of proposed methods to analyze digital footprints for the sake of educational analytics.Despite the fact that a very small set of data was used, the case study results are quite illustrative.