The Upstream Sources of Bias: Investigating Theory, Design, and Methods Shaping Adaptive Learning Systems

Abstract

Adaptive systems in education need to ensure population validity to meet the needs of all students for an equitable outcome. Recent research highlights how these systems encode societal biases leading to discriminatory behaviors towards specific student subpopulations. However, the focus has mostly been on investigating bias in predictive modeling, particularly its downstream stages like model development and evaluation. My dissertation work hypothesizes that the upstream sources (i.e., theory, design, training data collection method) in the development of adaptive systems also contribute to the bias in these systems, highlighting the need for a nuanced approach to conducting fairness research. By empirically analyzing student data previously collected from various virtual learning environments, I investigate demographic disparities in three cases representative of the aspects that shape technological advancements in education: 1) non-conformance of data to a widely-accepted theoretical model of emotion, 2) differing implications of technology design on student outcomes, and 3) varying effectiveness of methodological improvements in annotated data collection. In doing so, I challenge implicit assumptions of generalizability in theory, design, and methods and provide an evidence-based commentary on future research and design practices in adaptive and artificially intelligent educational systems surrounding how we consider diversity in our investigations.