Classification of Students’ Mathematical Literacy Score Using Educational Data Mining: PISA 2015 Turkey Application
Abstract
PISA 2015 mathematical literacy score of Turkey is 420 while the average score of all countries is 461. It is understood that; Turkish students’ PISA 2015 mathematical literacy score was lower than the average. The basic reasons for the below average score need to be truly examined and developmental activities should be revealed. The aim of this study is to classify students according to the factors affecting their mathematical literacy score and to reveal the effects of these factors in classification.The data of the study is obtained from 5895 students who participated in PISA 2015. In this study, we used Random Forest, Naïve Bayes Classifier, Logistic Regression, Decision Tree Algorithm and Discriminant Analysis as classifiers. According to the results, Random Forest method produced more accurate scores than other methods with 76.32% accuracy. We also calculated the correct classification rate and determined the factors that positively and negatively affect the classification with discriminant analysis. According to the discriminant analysis home possessions, information and computer technology resources at home and students' expected occupational status were the most positive effective variables on mathematical literacy score. On the other hand, family wealth possessions, student-related factors affecting school climate and anxiety have negative effect on mathematical literacy score.
Keywords
Classification, Educational data mining, PISA 2015, Mathematics education, Discriminant analysis.
References
- [1] Taş U.E., Arici Ö., Ozarkan H.B., Özgürlük B., PISA 2015 ulusal raporu, Ankara: Milli Eğitim Bakanlığı, (2016).
- [2] Witten I.H., Frank E., Data mining: practical machine learning tools and techniques with Java implementations, Acm Sigmod Record, 31(1) (2002) 76-77.
- [3] Romero C., Ventura S., Educational Data Mining: A Review of the State of the Art, IEEE Trans. Syst., Man, Cybern. C, 40(6) (2010) 601–618.
- [4] Aksu G., Doğan N., Veri madenciliğinde kullanılan öğrenme yöntemlerinin farklı koşullar altında karşılaştırılması, Ankara University Journal of Faculty of Educational Sciences (JFES), 51(3) (2018) 71-100.
- [5] Aksu G., Güzeller C.O., Classification of PISA 2012 mathematical literacy scores using Decision-Tree Method: Turkey sampling. Egitim ve Bilim, 41(185) (2016) 101–122.
- [6] Dos Santos R.A., Paulista C.R., da Hora, H.R.M., Education Data Mining on PISA 2015 Best Ranked Countries: What Makes the Students go Well, Technology, Knowledge and Learning, (2021) 1-32.
- [7] Martínez Abad F., Chaparro Caso López A.A., Data-mining techniques in detecting factors linked to academic achievement, School Effectiveness and School Improvement, 28(1) (2017) 39–55.
- [8] Toprak E., Gelbal S., Comparison of Classification Performances of Mathematics Achievement at PISA 2012 with the Artificial Neural Network, Decision Trees and Discriminant Analysis, International Journal of Assessment Tools in Education, 7(4) (2020) 773-799.
- [9] Shahiri A.M., Husain W., Rashid N.A., A Review on Predicting Student’s Performance Using Data Mining Techniques, Procedia Computer Science, 72 (2015) 414–422.
- [10] Aksu G., Keceoglu C.R., Comparison of Results Obtained from Logistic Regression, CHAID Analysis and Decision Tree Methods, EJER, 19 (84) (2019) 1–20.