Using AI and Cognitive Taxonomies to map Learning Processes in Board Games

Abstract

Board Game-Based Learning (bGBL) has gained increasing attention as an innovative approach to foster active engagement and holistic cognitive development. However, integrating board games into effective practice is challenging, partly because of the lack of an established instructional framework. The implementation of bGBL often relies on teachers' personal initiative and familiarity with games, rather than on shared design practices. One of the main obstacles to implementing GBL lies in properly aligning learning goals with the actions that take place during gameplay, and the related learning processes. In this study, we develop a theoretical framework for aligning learning goals and the cognitive processes elicited by game mechanisms. We use this framework to train a GenAI assistant (GADbot) to assist bGBL instructional design, assessing its performance through human expert evaluation. Given the ever-increasing number of available board games and the constant innovation in game mechanics, this approach can revolutionize the field of bGBL, leveraging AI as an assistant to lower the entry barrier for teachers to choose the right game for their educational needs, thus providing the foundation to design meaningful learning experiences and advance active pedagogical practices.