Abstract
International large-scale assessments, such as PISA, provide structured and static data. However, due to its extensive databases, several researchers place it as a reference in Big Data in Education. With the goal of exploring which factors at country, school and student level have a higher relevance in predicting student performance, this paper proposes an Educational Data Mining approach to detect and analyze factors linked to academic performance. To this end, we conducted a secondary data analysis and built decision trees (C4.5 algorithm) to obtain a predictive model of school performance. Specifically, we selected as predictor variables a set of socioeconomic, process and outcome variables from PISA 2018 and other sources (World Bank, 2020). Since the unit of analysis were schools from all the countries included in PISA 2018 (n = 21,903), student and teacher predictor variables were imputed to the school database. Based on the available student performance scores in Reading, Math, and Science, we applied k-means clustering to obtain a categorized (three categories) target variable of global school performance. Results show the existence of two main branches in the decision tree, split according to the schools’ mean socioeconomic status (SES). While performance in high-SES schools is influenced by educational factors such as metacognitive strategies or achievement motivation, performance in low-SES schools is affected in greater measure by country-level socioeconomic indicators such as GDP, and individual educational indicators are relegated to a secondary level. Since these evidences are in line and delve into previous research, this work concludes by analyzing its potential contribution to support the decision making processes regarding educational policies.
Highlights
The emergence of international large-scale assessments (ILSA) in the past two decades, together with their cyclic nature, have consistently provided educational researchers with large databases containing diverse types of variables. Assessment schemes such as the Programme for International Student Assessment (PISA) from the Organisation for Cooperation and Economic Development (OECD), or the Trends in International Mathematics and Science Study (TIMSS) and the Progress in International Reading Literacy Study (PIRLS), both conducted by the International Association for the Evaluation of
It has been observed that educational policies are usually influenced by the reports and analyses elaborated directly by the OECD, because these are the first ones presented to the public after a given PISA wave (Wiseman, 2013) and since these analyses can be somewhat limited considering the vast array of variables that PISA offers (Jornet, 2016), there is a certain responsibility for educational researchers to delve deeper into the databases and find relationships among variables and conclusions that might not be offered by the OECD reports in order to enrich the political debate around the topic
From a purely quantitative approach (Johnson et al, 2007), the main objective of this study is to analyze factors linked to academic performance in large-scale assessments mainly using data mining techniques (Witten et al, 2016), decision trees
Summary
The emergence of international large-scale assessments (ILSA) in the past two decades, together with their cyclic nature, have consistently provided educational researchers with large databases containing diverse types of variables (student performance and background, school practices and processes, etc.). Assessment schemes such as the Programme for International Student Assessment (PISA) from the Organisation for Cooperation and Economic Development (OECD), or the Trends in International Mathematics and Science Study (TIMSS) and the Progress in International Reading Literacy Study (PIRLS), both conducted by the International Association for the Evaluation of. Data mining has appeared in the past few years as one of the emerging techniques to analyse PISA data (Liu and Whitford, 2011; Tourón et al, 2018; Martínez-Abad, 2019; She et al, 2019), it is a less-explored analysis method
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
