Protected Attributes Tell Us Who, Behavior Tells Us How: A Comparison of Demographic and Behavioral Oversampling for Fair Student Success Modeling
Open Access
- 13 March 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 488-498
Abstract
Algorithms deployed in education can shape the learning experience and success of a student. It is therefore important to understand whether and how such algorithms might create inequalities or amplify existing biases. In this paper, we analyze the fairness of models which use behavioral data to identify at-risk students and suggest two novel pre-processing approaches for bias mitigation. Based on the concept of intersectionality, the first approach involves intelligent oversampling on combinations of demographic attributes. The second approach does not require any knowledge of demographic attributes and is based on the assumption that such attributes are a (noisy) proxy for student behavior. We hence propose to directly oversample different types of behaviors identified in a cluster analysis. We evaluate our approaches on data from (i) an open-ended learning environment and (ii) a flipped classroom course. Our results show that both approaches can mitigate model bias. Directly oversampling on behavior is a valuable alternative, when demographic metadata is not available. Source code and extended results are provided in https://github.com/epfl-ml4ed/behavioral-oversampling.Keywords
All Related Versions
Funding Information
- SERI
This publication has 20 references indexed in Scilit:
- Inherent Trade-Offs in Algorithmic Fairness2018
- Demarginalizing the Intersection of Race and Sex: A Black Feminist Critique of Antidiscrimination Doctrine, Feminist Theory, and Antiracist Politics [1989]2018
- Modeling exploration strategies to predict student performance within a learning environment and beyond2017
- Self-regulated learning strategies & academic achievement in online higher education learning environments: A systematic reviewThe Internet and Higher Education, 2015
- Gender Bias in STEM FieldsPsychology of Women Quarterly, 2015
- Self-regulation in online learningDistance Education, 2013
- Socioeconomic determinants of academic achievementEducational Assessment, Evaluation and Accountability, 2012
- Applying Latent Dirichlet Allocation to Automatic Essay Grading2006
- Effect of School Population Socioeconomic Status on Individual Academic AchievementThe Journal of Educational Research, 1997
- Gender-group differences in the learning behaviour of entering first-year university studentsHigher Education, 1995