Automatic Grading Tool for Jupyter Notebooks in Artificial Intelligence Courses

Cristian D. González-Carrillo, Felipe Restrepo-Calle, Jhon J. Ramírez-Echeverry and Fabio A. González
Additional contact information
Cristian D. González-Carrillo: Department of Systems and Industrial Engineering, Universidad Nacional de Colombia, Bogotá 111321, Colombia
Felipe Restrepo-Calle: Department of Systems and Industrial Engineering, Universidad Nacional de Colombia, Bogotá 111321, Colombia
Jhon J. Ramírez-Echeverry: Department of Electrical and Electronics Engineering, Universidad Nacional de Colombia, Bogotá 111321, Colombia
Fabio A. González: Department of Systems and Industrial Engineering, Universidad Nacional de Colombia, Bogotá 111321, Colombia

Sustainability, 2021, vol. 13, issue 21, 1-26

Abstract: Jupyter notebooks provide an interactive programming environment that allows writing code, text, equations, and multimedia resources. They are widely used as a teaching support tool in computer science and engineering courses. However, manual grading programming assignments in Jupyter notebooks is a challenging task, thus using an automatic grader becomes a must. This paper presents UNCode notebook auto-grader, that offers summative and formative feedback instantaneously. It provides instructors with an easy-to-use grader generator within the platform, without having to deploy a new server. Additionally, we report the experience of employing this tool in two artificial intelligence courses: Introduction to Intelligent Systems and Machine Learning . Several programming activities were carried out using the proposed tool. Analysis of students’ interactions with the tool and the students’ perceptions are presented. Results showed that the tool was widely used to evaluate their tasks, as a large number of submissions were performed. Students expressed positive opinions mostly, giving feedback about the auto-grader, highlighting the usefulness of the immediate feedback and the grading code, among other aspects that helped them to solve the activities. Results remarked on the importance of providing clear grading code and formative feedback to help the students to identify errors and correct them.

Keywords: auto-grading systems; jupyter notebooks; artificial intelligence; computer programming; formative feedback; summative feedback; assessment; sustainable development (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2071-1050/13/21/12050/pdf (application/pdf)
https://www.mdpi.com/2071-1050/13/21/12050/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:13:y:2021:i:21:p:12050-:d:669631

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().