Potential Abstract:
Recent advancements in educational data mining have provided valuable insights into student learning patterns and educational outcomes. However, the field has largely overlooked the intersectional dimensions of student identities and experiences. This study aims to fill this gap by examining how various social identities intersect in shaping students’ learning trajectories and educational achievement. Drawing on critical race theory and feminist theory, we propose a political paradigm shift in educational data mining that centers on understanding the complex interplay of race, gender, socio-economic status, and other intersecting identities in educational contexts.
Our research will utilize a mixed-methods approach, combining quantitative analysis of large-scale educational datasets with qualitative interviews and surveys to capture the nuanced experiences of students from marginalized backgrounds. By applying an intersectional lens to educational data mining, we seek to challenge dominant narratives and uncover hidden biases in educational systems that perpetuate inequality. This study has the potential to inform more equitable educational policies and practices that better serve diverse student populations.
Potential References:
- Fluidity of social identities: implications for applying intersectionality
- A novel application of a data mining technique to study intersections in the social determinants of mental health among young Canadians
- Implementing equitable and intersectionalityâaware ML in education: A practical guide
- A new educational normal an intersectionality-led exploration of education, learning technologies, and diversity during COVID-19
- Using knowledgeable agents of the digital and data feminism to uncover social identities in the# blackgirlmagic twitter community
