DATA & SCRIPTS -- Data sharing in learning analytics: how context and group discussion influence the individual willingness to share

The ethical integration of the data generated by learners into educational practices is of great importance now that data-rich technologies are prevalent in education. Despite the common agreement that learners should have agency in deciding what to do with their data, existing ethical discussions focus on policies or algorithms, with limited attention to participatory learner practices. Participatory practices, particularly around informed consent, can support ethical and meaningful engagement with data sharing decisions. Using a novel experimental methodology, we explored how the decision context influences the perceived acceptability for sharing learning data. We found that participants became more cautious in sharing their data in and after a group discussion. The willingness to share was the lowest when these data are submitted to a government entity and for a collective benefit. Further network analysis of group discussions confirmed the observed attitude shifts: participants consistently discussed different aspects of sharing learning data based on the context such as sharing process vs outcome-related learning data. The results suggest that educational data consent is contextual and that mechanisms for consent in educational technology may differ from those in health contexts. The proposed method of interactive consent therefore not only contributes to theories explaining privacy and effective data collection but also represents a new way of conceptualising and realising participatory informed consent.