Prediction of academic success through interaction with version control systems

Guerrero‐Higueras, Ángel Manuel; Sánchez-González, Lídia; Fernández‐Llamas, Camino; Conde, Miguel Á.; Lera, Francisco Javier Rodríguez; Sedano, Francisco Jesús Rodríguez; Costales, Gonzalo Esteban; Olivera, Vicente Matellán

doi:10.1145/3362789.3362875

Cited by 4 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allowed us to assert that the contents of a repository may be quite useful to predict academic success. Including more additional features such as the ones proposed in [15] in addition to the number of files and lines may result in higher accuracy. However, it is important to point out that this requires a static analysis of the source code.…”

Section: Discussionmentioning

confidence: 99%

“…An identifier to make students anonymous (id): it provided differentiation among the samples. In [15], the authors proposed to collect some additional variables extracted from the source code: the total number of source code lines, the number of subroutines, the number of variables or objects, the number of classes, the number of loops, the cyclomatic complexity, the number of files, some object-oriented programming related features (i.e., inheritance and polymorphism usage), the number of README files, dependencies, etc. They also considered variables computed by the measure of the interaction with VCS.…”

Section: Input Datamentioning

confidence: 99%

“…In this work, the authors built new prediction models by using the dataset presented in [15]. The new models presented a higher accuracy than the ones described in [5] and a similar accuracy to the models in [4].…”

Section: Introductionmentioning

confidence: 99%

“…To ensure an optimal generalization of prediction models, the use of a much bigger dataset was proposed in [15]. A new dataset was built not only gathering data from the Operating Systems Extension subject, but also from Computer Programming I and Computer Organization subjects.…”

Section: Introductionmentioning

confidence: 99%

“…Besides the data related to the interaction with VCSs, the work in [15] proposed including some additional variables in the dataset extracted from the source code. These were the total number of source code lines of the software solution, the number of used subroutines, or the number of variables or objects, among others.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Academic Success Assessment through Version Control Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Version control systems’ usage is a highly demanded skill in information and communication technology professionals. Thus, their usage should be encouraged by educational institutions. This work demonstrates that it is possible to assess if a student can pass a computer science-related subject by monitoring its interaction with a version control system. This paper proposes a methodology that compares the performance of several machine learning models so as to select the appropriate predicting model for the assessment of the students’ achievements. To fit predicting models, three subjects of the Degree in Computer Science at the University of León are considered to obtain the dataset: computer organization, computer programming, and operating systems extension. The common aspect of these subjects is their assignments, which are based on developing one or several programs with programming languages such as C or Java. To monitor the practical assignments and individual performance, a Git repository is employed allowing students to store source code, documentation, and supporting control versions. According to the presented experience, there is a huge correlation between the level of interaction for each student and the achieved grades.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Input Datamentioning

confidence: 99%