AI in the classroom: Maximising spatial design and improving learning outcomes

Lecturer walks around room

Monash University researchers have analysed positioning patterns of teachers within a number of learning environments to develop an advanced artificial intelligence (AI) system, called Moodoo, which determines the best teaching positions for educators.

Previous research has found teachers’ positioning in the classroom and proximity to students can strongly influence critical aspects of student engagement, motivation, disruptive behaviour, and self-efficacy. But the literature does not clearly identify the optimum position educators should place themselves during a class or how classrooms should be designed to ensure maximum student engagement.

With the advancement of technology, there has been a growing interest in using advanced sensing technologies, such as wearable devices and computer vision systems, to automatically analyse classroom activity and model behaviours such as student engagement, teacher-student interactions and students’ physical activity.

In response, Monash researchers, in collaboration with international partners from Escuela Superior Politécnica del Litoral (Ecuador), Carnegie Mellon University (USA), University of Technology Sydney, and Norwegian University of Science and Technology, have built on the foundations of spatial analysis and pedagogy, to propose a set of metrics that identify and recommend optimal teaching positioning strategies in a classroom space.

Project Lead, Senior Lecturer Dr Roberto Martinez-Maldonado, from the Faculty of Information Technology (IT) at Monash University, said their research analysed data from seven teachers wearing indoor positioning trackers.

The teachers delivered three distinct types of classes to over 190 students in the context of physics education.

“Our results showed that by using Moodoo, wearable trackers revealed the kinds of learning tasks performed by students in the classroom and the appropriate positioning approaches used by teachers,” said Dr Martinez-Maldonado.

“Our results form a foundation that can help us train novice teachers to use the classroom spaces effectively or to assess the impact of the spatial design on teaching and learning outcomes.”

The data captured by Moodoo highlights certain factors that are essential to delivering successful learning outcomes – for instance, providing increased teacher-student time ratio for hands-on learning as opposed to a one-way lecture delivery method.

Further studies into classroom spatial use are underway to determine specifically where teachers should stand for effective education delivery and how classrooms should be designed or laid out.

The technology is currently being co-designed by a number of academics and stakeholders. This stage of design will ensure the technology meets authentic pedagogical needs and developed specifically with teachers, academic developers, academic decision makers and designers of learning spaces in mind.

The Moodoo research paper won the Best Paper Award at the 21st International Conference on Artificial Intelligence in Education.

To read the research paper, please visit here.