AI-Induced guidance: Preserving the optimal Zone of Proximal Development

Abstract

Holding the promise of higher learning outcomes, discovery learning utilizes intrinsic motivation to provide an enjoyable self-directed learning experience. Unfortunately, this approach can also lead to a sub-optimal cognitive load, which hinders learning. To avoid this, players must be in the optimal Zone of Proximal Development (ZPD). A way of accomplishing this is to make use of Artificial Intelligence in a narrative-centered discovery game using adaptive guidance. Textual instructions were automatically adapted in real-time to ensure a personalized challenge for one group of learners, where a control group received static instructions. Compared to the control group, the learners with personalized instructions showed higher story and spatial learning, while having decreased cognitive load and a similar learning experience. So, instructions given to self-directed learners can be personalized in real-time, which not only reduces learners’ cognitive load but also leads to enhanced learning outcomes without affecting the learning experience.

Keywords

• Artificial intelligence in education (AIEd)
• Discovery learning
• Textual specificity
• Zone of proximal development (ZPD)
• Personalization
• Experience