Prediction of middle school students' programming talent using artificial neural networks

Abstract

Nowadays, the softwarization and virtualization of resources and services rapidly continue, and along with reading and writing, programming is going to be one of the basic human ability. Thus, the detection of skilled programmers at an early age has become important for economies to strengthen their workforce and compete globally. The current technological momentum shows that when the middle school students of today reach the 2030s, the demand for advanced programming skills will be rapidly increased, expanding as high as 90% between 2016 and 2030. Thus, the identification of these skilled people at an early age is important. Accordingly, this study focused on predicting middle school students’ programming aptitude using artificial neural network (ANN) algorithms. A participant survey was developed and applied to middle school students consisting of fifth, sixth, and seventh graders from Konya Science Center, Turkey. After the completion of the survey, the participants then took the 20-level Classic Maze course (CMC) on Code.org. The participants’ final scores in the CMC were calculated based on the level they completed and the lines of codes they wrote. The best results were obtained using the Bayesian regularization algorithm: Training-R = 9.72284e−1; Test-R = 9.12687e−1, and All-R = 9.597e−1. The results show that ANN is an appropriate machine learning method that can forecast participants’ skills, such as analytical thinking, problem-solving, and programming aptitude.