Towards Culturally Relevant Personalization at Scale: Experiments with Data Science Learners

Publication Information


  • Christopher Brooks, University of Michigan
  • Rebecca M. Quintana, University of Michigan
  • Heeryung Choi, University of Michigan
  • Chris Quintana, University of Michigan
  • Timothy NeCamp, University of Michigan
  • Joshua Gardner, University of Michigan


  • 516-537


  • Culturally relevant pedagogy, Data science education, Personalization, Learning at scale


  • In this article we describe our experiences building a large-scale data science program aimed at supporting diversity in online data science learning. This program was built to support a set of introductory skills-based, higher education courses. We are motivated by work done in project-based learning contexts and culturally responsive pedagogies and are particularly keen to understand how we can scale such kinds of approaches to large and diverse global classrooms. Specifically, we consider the country from which a learner is accessing the course as the key context for our work and discuss two interrelated investigations we have undertaken to understand how this feature interacts with learners’ motivation and learning. Our findings provide insights on how learners respond to location-specific problem-based personalizations in data science education and provides an initial exploration as to how this form of personalization differs depending on the geo-political context of the learners.