Evaluation of students’ academic results through the analysis of their use of Version Control Systems)

Abstract

Version Control Systems are commonly used by Information and Communication Technology professionals. These systems allow for monitoring programmers’ activity working in a project. Thus, the usage of such systems should be encouraged by educational institutions. The aim of this work is to evaluate if students’ academic success can be predicted by monitoring their interaction with a Version Control System. In order to do so, we have built a model that predicts students’ results in a specific practical assignment of the Operating Systems Extension subject. A second-year subject in the degree in Computer Science at the University of León. In order to obtain a prediction, the model analyzes students’ interaction with a Git repository. To build the model, several classifiers and predictors have been evaluated by using the MoEv tool. The tool allows for evaluating several classification and prediction models in order to get the most suitable one for a specific problem. Prior to the model development, Moev performs a feature selection from input data to select the most significant ones. The resulting model has been trained using results from the 2016 – 2017 course year. Later, in order to ensure an optimal generalization, the model has been validated by using results from the 2017 – 2018 course. Results conclude that the model predicts students’ outcomes? with a success high percentage.