Learner Agency in Personalised Content Recommendation: Investigating Its Impact in Kenyan Pre-primary Education

There is a lack of understanding regarding how pre-primary learners exercise their agency in their learning processes when interactingwith AI-powered digital personalised learning (DPL) tools. This study aims to address the gap by investigating the interaction between pre-primary learners' agency and a DPL tool in a Kenyan classroom setting. A total of 76,479 pre-primary learners participated in a two-month experiment, where each learner was randomly assigned to two partitions. Learners in the control partition followed the learning content designated by an algorithm within an adaptive DPL tool. In the experimental partition, learners received two additional learning units to choose from as well as the default content unit. Learning outcomes were assessed through six summative test units measuring literacy and numeracy skills. The results revealed that learners who were provided with a choice scored significantly higher in four out of the six test units. This study highlights the potential that pre-primary learners can exercise some degree of agency and direct their own learning within a structured set of choices provided by a DPL tool. Future research is needed for a comprehensive understanding of pre-primary learner agency.