Connecting AI, Embodied Learning and Student Engagement: A Didactic–Pedagogical Perspective for Secondary Schools
Giovanni Tafuri, Gianluca Gravino, Lucia Ariemma, Davide Di Palma
Abstract
Among the most powerful predictors of learning effectiveness in secondary schools is student engagement. This paper explores the synergistic value of artificial intelligence (AI) and embodiment to increase such engagement. We conducted an experimental study that involved the use of the Nao robot for the development of digital and logical skills, integrated with motor activities oriented to promote embodied processes in Physical Science lessons. Data collection included the administration of the Student Engagement Scale (SES) and a qualitative analysis of student responses. The evidence shows a significant increase in engagement in both cases, with distinct profiles: AI mainly favours the emotional and cognitive components; embodiment predominantly affects the behavioural one. These results suggest that a combination of AI and embodiment could be an innovative strategy to foster more dynamic and engaging learning.
Keywords
References
Journal of Education- al Technology, 14(1), 22-35.
Belpaeme, T., Kennedy, J., Bianchi, E., & Dautenhahn, K. (2018). Social robots for education:
A review. Interna- tional Journal of Social Robotics, 10(3), 493–511.
Fredricks, J. A., Blumenfeld, P. C., & Paris, A. H. (2004). School engagement: Potential of the
concept, state of the evidence. Review of Educational Research, 74(1), 59–109.
Gallese, V. (2011). Embodied simulation: From neurons to phenomenal experience. In
Embodied Cognition and the Arts (pp. 145–161). Routledge.
Dautenhahn, K., & Billard, A. (2002). Towards social robots for the elderly. Robotics and
Autonomous Systems, 43(2–3), 143–148.
Klein, J. T. (2014). Beyond interdisciplinary: A new agenda for higher education. Change: The
Magazine of Higher Learning, 46(4), 36–43.
Papert, S. (1980). Mindstorms: Children, computers, and powerful ideas. Basic Books.
Baker, R. S. J. D., & Inventado, P. S. (2014). Educational data mining and learning analytics.
In Learning, Design, and Technology (pp. 1–24). Springer.
Lund, A., & Lindqvist, U. (2019). The role of robot-assisted therapy in the treatment of children
with autism spectrum disorder: A review. Journal of Autism and Developmental
Disorders, 49(10), 4190–4201.
Feng, Y., & Jansen, D. (2018). Robots in education: A comprehensive review of the literature.
International Journal of Social Robotics, 10(4), 517–534.
Miller, T., & Sweeney, K. (2017). The role of physical activity in promoting academic
achievement in youth: A systematic review. American Journal of Health Promotion,
31(6), 448–456.
Santos, A. F., & Mota, M. A. (2016). The impact of embodied learning on engagement in the
classroom. Journal of Educational Psychology, 108(1), 152–164.
Cobo, C., & Moravec, J. W. (2011). The future of learning: A shift from education to learning.
International Jour- nal of Emerging Technologies in Learning, 6(3), 4–10.
Kirk, D., & Macdonald, D. (2001). Physical education futures. Routledge.
Chiu, T. K. F., & Chang, Y. J. (2019). Embodied learning and its impact on student engagement
in physical edu- cation. Physical Education and Sport Pedagogy, 24(5), 450–464.
Gonzalez, C., & Watanabe, T. (2020). Learning by doing: The impact of embodied learning
activities on cogni- tive and motor skills. Journal of Educational Psychology, 112(3),
540–553.
Rossi, L., & De Luca, A. (2023). Embodied Learning in Physical Education: The Role of Body
in Enhancing Engagement and Cognitive Skills. International Journal of Physical
Education and Pedagogy, 30(2), 100-115.
