Toward Personalised Learning Experiences
Beyond Prompt Engineering
Joost Kruis (Cito Institute for Educational Measurement )
Maria Soledad Pera (TU Delft - Web Information Systems)
Zoë ten Napel (Cito Institute for Educational Measurement )
Monica Landoni (University of Lugano)
Emiliana Murgia (Università degli Studi di Genova)
Theo Huibers (University of Twente)
Remco Feskens (Cito Institute for Educational Measurement , University of Twente)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
We discuss the foundation of a collaborative effort to explore AI's role in supporting (teachers and) children in their learning experiences. We integrate principles of educational psychology, AI, and HCI, and align with best practices in education while undertaking a human-centered focus on design and development that puts the student at the centre and keeps the expert-in-the-loop. Initially, we study assessment items - questions or tasks tied to a learning target. These items vary in complexity, serve as indicators of students' grasp of specific concepts and spotlight areas where support may be needed. This preliminary analysis will help us outline a framework to guide the design and evaluation of AI technology for K-12 education. Such a framework would ensure that assessment item generation technology goes beyond the current one-dimensional approach by incorporating multifaceted, adaptable perspectives that consider the variegated landscape of learners' needs, subject matter complexities, and pedagogical goals.