FairEd: A Systematic Fairness Analysis Approach Applied in a Higher Educational Context

Verdugo, Jonathan Vasquez; Gitiaux, Xavier; Ortega, Claudio Bravo; Rangwala, Huzefa

doi:10.1145/3506860.3506902

Cited by 10 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The potential of algorithms for education is high. The best adaptive learning systems and at-risk prediction systems have made large positive impacts on student outcomes (Ma et al, 2014[85]; VanLehn, 2011 [86]; Millron, Malcom and Kil, 2014 [87]). However, this potential cannot be fully reached if algorithms replicate or even magnify the biases occurring in societies around the world.…”

Section: Discussionmentioning

confidence: 99%

OECD Digital Education Outlook 2021

2021

OECD Digital Education Outlook

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

OECD Digital Education Outlook 2021

2021

OECD Digital Education Outlook

View full text Add to dashboard Cite

show abstract

“…Although fairness in educational contexts is already being examined (Anderson et al, 2019;Baker et al, 2020;Gardner et al, 2019;Riazy et al, 2020;Vasquez Verdugo et al, 2022), fairness is mainly determined concerning demographic groups such as gender, race, or migration background (Baker & Hawn, 2021). The fairness metrics that 2.2 Measuring Fairness.…”

Section: Introductionmentioning

confidence: 99%

Unbias me! Mitigating Algorithmic Bias for Less-studied Demographic Groups in the Context of Language Learning Technology

Rzepka¹,

Fernsel²,

Müller³

et al. 2023

Preprint

View full text Add to dashboard Cite

Rzepka, N., Fernsel, L., Müller, H., Simbeck, K., & Pinkwart, N., (2023) Unbias me! Mitigating Algorithmic Bias for Less-studied Demographic Groups in the Context of Language Learning Technology. Computer-Based Learning in Context, 6 (1), 1-23. 10.5281/zenodo.7996194 Algorithms and machine learning models are being used more frequently in educational settings, but there are concerns that they may discriminate against certain groups. While there is some research on algorithmic fairness, there are two main issues with the current research. Firstly, it often focuses on gender and race and ignores other groups. Secondly, studies often find algorithmic bias in educational models but don't explore ways to reduce it. This study evaluates three drop-out prediction models used in an online learning platform to teach German spelling skills. The aim is to assess the fairness of the models for (in part) less-studied demographic groups, including first spoken language, home literacy environment, parental education background, and gender. To evaluate the models, four fairness metrics are used: predictive parity, equalized odds, predictive equality, and ABROCA. The study also examines ways to reduce algorithmic bias by analyzing the models at each stage of the machine learning process. The results show that all three models had biases that affected the fairness of all four demographic groups to varying degrees. However, the study found that most biases could be mitigated during the process. The methods used to mitigate bias differed by demographic group, and some methods improved fairness for one group but worsened it for others. Therefore, the study concludes that reducing algorithmic bias for less-studied demographic groups is possible, but finding the right method for each algorithm and demographic group is crucial.

show abstract