You are here

Prof. dr. ir. Dirk Heylen

Projectleader of the COMMIT project IUALL (Interaction for Universal Access)

Dirk Heylen is Professor Socially Intelligent Computing at the University of Twente, working in the Human Media Interaction group. His research interests cover both the machine analysis of human (conversational) behaviour and the generation of human-like (conversational) behaviour by virtual agents and robots. He is especially interested in the nonverbal and paraverbal aspects of dialogue and what these signals reveal about the mental state (cognitive, affective, social). These topics are explored both from a computational perspective and as basic research in the humanities, reflecting his training as a computational linguist.

After his studies of Linguistics, Computer Science and Computational Linguistics at the University of Antwerp he moved to the Institute of Dutch Lexicology in Leyden, to develop tools for enriching natural language databases. After a couple of years he went on to the Utrecht University and got involved in the big European project Eurotra on Machine Translation. After coordinating a follow-up EU project, he started his PhD on a logical approach to natural language analysis and parsing (Type Logical Grammar).

At the University of Twente he started working on embodied dialogue systems (aka virtual agents or embodied conversational agents). This made his interests shift from pure linguistic analysis to body language, from text analysis to real-time human-machine interaction, and from the logical analysis to a much broader concern with emotion and social relations in interaction.

He has been involved in several European projects such as Humaine, AMI and AMIDA, COST 2102, Semaine, SSPNET, and SERA. Dialogue management, human behaviour modeling, cognitive modeling, human-robot interaction, methodological issues in corpus studies and annotation, are some of the topics dealt with in these projects. Current Dutch national projects he is involved in include BrainGain in which neural correlates of a user’s experience are explored for Human Computer Interaction using Brain Computing Interfaces and GATE dealing with cognitive models of virtual agents in training applications.

Works with