Modelling Group Dynamics with SYMLOG and Snowdrift for Intelligent Classroom Environment

The aim of this thesis is to provide assistance to human teachers focusing on supporting group work within a classroom environment. This is achieved by incorporating theories from Psychology and Game Theory in order to provide a better method of modelling and predicting group interactions. This research proposes a framework that extends the pre-existing Intelligent Tutorial System (ITS) beyond the individual and into one that encompasses one or more groups of learners within a learning space. This framework transforms a traditional school classroom into a group interface as part of the communication module of an ITS and enhances the role of a human teacher. This is achieved by automating class management tasks and providing an immersive learning experience. Moreover, the proposed framework monitors emotional well-being and feeds back, to the teacher, emotional profiles of individuals and groups. This new ITS system is named Intelligent Classroom Tutoring System (ICTS). 6 experiments were conducted to support the ICTS. 2 experiments were set up to compare experimental frameworks for SYMLOG allowing the researchers to test a new mod-SYMLOG which was found to be an effective tool for modelling groups interactions. 1 experiment was centred around a longitudinal study of group work, and the final 3 composing of both AI and human studies, examining applying a new mod-Snowdift game to produce a predictive mechanism for group interaction.