MLDG - Machine Learning Dataset Generator (Pilot Findings): For Final Year Open-Book Machine Learning Summative Assessment

Authors

Keith Quille, Technological University DublinFollow
Keith Nolan, TU DublinFollow
Lidia Vidal-Meliá, ,UniversitatJaumeI Castelló,SpainFollow
Brett A. Becker, UCDFollow

Document Type

Conference Paper

Disciplines

Computer Sciences

Publication Details

Human-Centred AI Education & Practice Conference (HCAI-ep '23), Dublin, Ireland, Dec 14 and 15 2023. (Short Paper Track)

https://hcai-ep.sigcseire.acm.org/publications/

Abstract

Following the COVID-19 pandemic, many institutions are considering the continuation of open-book assessments. Students cite many reasons for preferences for open-book assessments, both held in proctored environments and assessments that can be held remotely. Despite the numerous benefits, open-book assessments impose a number of challenges for educators, which is compounded if the assessment has the option to be taken in class (proctored) and remotely simultaneously. The challenges not only exist around academic integrity but also exist from a student-centred viewpoint of fairness and the equality of the assessment.

This paper first presents the development of a tool for generating student-centred datasets (using the MLDG - Machine Learning Dataset Generator) which are unique but fair to allow for both in-class and remote summative assessment for a final-year Machine Learning course, simultaneously. Second, a study was conducted over a two-year period to trail the tool and assessment environment, where it reported positive findings from a student’s viewpoint, academic integrity viewpoint and the workload from course instructors (as the tool also generates an information file to reduce grading time). The results are encouraging and provide evidence that MLDG and the assessment approach used to promote a fair assessment with academic integrity for Machine Learning students. This tool and assessment approach could also be applied in other subjects such as databases thus having value outside of Machine Learning courses for the Computing Education Research community

DOI

https://doi.org/10.21427/AZEE-BZ43

Recommended Citation

Quille, K., Nolan, K., Vidal-Meliá, L., & Becker, B. A. (2023). MLDG - Machine Learning Dataset Generator (Pilot Findings) - For Final Year Open-Book Machine Learning Summative Assessment. HCAI Education and Practice Conference. DOI: 10.21427/AZEE-BZ43

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.