Skip to main content

The impact of affect-aware support on learning tasks of differing cognitive demands

Venue: Birkbeck Main Building

In this talk I will describe the design and ecologically valid evaluation of a learner model that lies at the heart of an intelligent learning environment called iTalk2Learn. A core objective of the learner model is to adapt formative feedback based on students' affective states. Types of adaptation include what type of formative feedback should be provided and how it should be presented. Two Bayesian networks trained with data gathered in a series of Wizard-of-Oz studies are used to drive the adaptation process. The talk will present results of a user study that investigates the effect of the affect-aware support on learning tasks that differ in their cognitive demands. The results show that when the cognitive demands of the tasks are high, students in the group where affect-aware support was provided were significantly more in flow and less confused than in the group where students were given support based on their performance only. 


Beate Grawemeyer is a Lecturer in Computer Science at Coventry University. Before that she was a Postdoctoral Researcher at Birkbeck, University of London. She has an M.Sc. in Knowledge-Based Systems and a Ph.D. in Computer Science and Artificial Intelligence, both from the University of Sussex. She has worked in several areas of Artificial Intelligence and Human–Computer Interaction. Her primary research interest lies in the development of user/learner models that offer novel adaptation techniques (such as adaptations to affective states) to enhance user experience and performance when conducting specific learning tasks.

Contact name: