Classification and prediction‐based machine learning algorithms to predict students’ low and high programming performance

Abstract

The current study aims to determine the programming performance (low and high) of the students between the ages of 12–24 who receive programming education, by descriptive analysis, to determine the current situation according to various variables and to redict them with machine learning algorithms. Thus, the change in programming performance, computational identity, computational thinking perspective, programming empowerment, and programming anxiety according to various variables was examined. The performances of different algorithms were compared in estimating the low and high programming performance of these variables. The research involved 763 students who were between the ages of 12 and 24 and had received programming education. Different scales were used to collect the opinions of students who received programming education. Descriptive analyses, one‐way analysis of variance (ANOVA), and machine learning algorithms were used in the analysis of the data set. Analyzes were made in Statistical Package for the Social Sciences (SPSS) and Knime software. Decision trees, k‐nearest neighbors, support vector machines, random forest, Naive Bayes classifiers, and logistic regression were used in the study. Students’ programming performance, computational identity, computational thinking perspective, and programming empowerment mean scores differ in terms of gender and educational level variables. Research variables do not differ statistically in terms of academic success level variables. According to the programming performance level, students’ computational identity, computational thinking perspective, and programming empowerment scores differ. No significant difference was found between programming anxiety scores. Decision trees of the algorithm with the highest accuracy result according to low and high programming performance conditions are [(0.966), (0.966)], respectively. The fact that these obtained scores are above 90% can be interpreted as sufficient estimation performance.