Authors:
Eric Gondran
1
;
Giancarlo Lucca
1
;
Rafael Berri
1
;
Helida Santos
1
;
2
and
Eduardo N. Borges
1
Affiliations:
1
C3, Universidade Federal do Rio Grande, Av. Itália km 08, Rio Grande, Brazil
;
2
ISC, Universidad Publica de Navarra, Campus Arrosadia, Pamplona, Spain
Keyword(s):
ENADE, Feature Selection, Educational Data Mining, Data Science.
Abstract:
The National Student Performance Exam (ENADE) annually evaluates different Brazilian higher education courses. This exam considers both face-to-face and distance learning courses. Distance learning is growing increasingly, especially during the coronavirus (COVID-19) pandemic. This study applies different techniques for selecting ENADE 2018 database characteristics, like information gain, gain rate, symmetric uncertainty, Pearson correlation, and relief F. The objective of the work is to discover which personal and socioeconomic characteristics are decisive for the student’s performance at ENADE, whether the student is in the context of Distance Education or face-to-face. It can be concluded, among other results, that: the father’s level of education directly influences performance; the higher the income, the better the performance; and white students have better performance than black and brown-skinned ones. Thus, the results obtained in this study may initiate analyzes of public po
licies towards improving performance at ENADE.
(More)