Education Data Mining on PISA 2015 Best Ranked Countries: What Makes the Students go Well

The demand for in-depth studies on educational data presupposes the application of technologies that allow data analysis of vast quantities, and subsequently, drawing relevant information and knowledge. The research objective herein is to employ data mining techniques on PISA databases to identify p...

Full description

Saved in:
Bibliographic Details
Published in:Technology, knowledge and learning Vol. 28; no. 1; pp. 47 - 78
Main Authors: dos Santos, Roberta Alvarenga, Paulista, Cássio Rangel, da Hora, Henrique Rego Monteiro
Format: Journal Article
Language:English
Published: Dordrecht Springer Netherlands 01-03-2023
Springer
Springer Nature B.V
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The demand for in-depth studies on educational data presupposes the application of technologies that allow data analysis of vast quantities, and subsequently, drawing relevant information and knowledge. The research objective herein is to employ data mining techniques on PISA databases to identify potential patterns that may explain the top-performing countries’ success. Accounting for the methodology, data acquisition, bank creation, and countries’ data extraction, we ran preprocessing and data cleaning and mining stages, respectively; in the last phase, we used the J48 method for classification purposes. From the decision trees, the study identified the relevant attributes which relate to student educational level aspiration; failure; motivation and anxiety; socioeconomic factors; scientific approaches; the use of information and communication technologies; interactions with friends; physical activity practice; paid work; home assignments; learning time for each discipline; cooperation and teamwork; the student’s study program; the teacher’s fairness; and the school year in which the student is enrolled. In this regard, results were considered satisfactory for allowing the analyses of these aforementioned relevant attributes associated with PISA best-ranked countries.
ISSN:2211-1662
2211-1670
DOI:10.1007/s10758-021-09572-9