Microsoft Word 18067-51689-1-ce (1). doc

Data mining techniques applied in educational environments: Literature review 
A. Villanueva, L.G. Moreno & M.J. Salinas 
Digital Education Review - Number 33, June 2018- http://greav.ub.edu/der/ 
 
249
In total 127 papers have been revised, where 305 authors have participated and 12 data mining 
techniques were identified.
The following sections classify the analyzed studies into three groups. 
1.
Classification of works by educational domains. 
2.
Papers classified by data mining techniques 
3.
Data mining techniques used by educational domains. 
b. Classification of works by educational domains 
There are multiple case studies in which data mining techniques are applied for education, each 
one of them seeking an answer to a particular situation that contributes to the objective sought by 
the EDM. In this review they were taken into account published papers between 1993 and 2015 in 
data mining techniques have been used in any of the following domains widely linked to education: 
•
Dropping out or Retention Analysis: 
papers in which factors related to dropout are analyze or 
studies seeking to promote student retention.
 
•
VLO or VLE Analysis: 
those papers in which VLO virtual learning objects or Virtual Learning 
Environment (VLE) have been analyzed. 
 
•
Performance and students evaluation Analysis: 
studies in which the use of data mining 
techniques was guide to analyze the performance of students or their assessment made 
during face-to-face or virtual courses.
 
•
Generation of Educational Recommendations: 
domain in which papers that generate 
recommendations during the educational process are associated.
 
•
Learning pattern Identification:
in this group is the work that analyzes the way in which 
virtual students develop in the learning environment and tries to establish the way in which 
they learn. Generally, these employers seek to group students according to similar 
characteristics.
 
•
Students patterns Identification: 
data analysis of educational environments which identified 
patterns among students.
 
•
Students related Prediction:
in this domain we find studies that allowed to do predictions 
relating to students, predictions in final grades, performance, behavior in specific courses 
etc.