Skip to content →

Our Mission

The Affective Computing Group (ACG) is an interdisciplinary team researching Social Human-Computer Interaction in various projects. The ACG is part of the Cognitive Assistants (COS) department of the German Research Center for Artificial Intelligence (DFKI). We believe that satisfying social interaction with technical devices should follow the principles of Human-Human interaction. Within that context, we focus on modeling human emotions, communication of emotions, behavioral patterns, as well as social norms and values.


News 2021

July: ACG goes the next step in the area of sign language interpretation by investigating body movements with state of the art technology with the special focus on bodily and facial emotional expression. This is relevant for the projects AVASAG, EASIER, and SocialWear.

March 15th: We organize the Func-E: Functions of Emotions für Socially Interactive Agents Workshop at the ACII 2021 conference.

March 10th: Please consider to contribute to the ACM Multimedia Grand Challenge MultiMediate: Multi-modal Group Behaviour Analysis for Artificial Mediation, which we co-organize.

February 15th: We are very happy to welcome Ann-Kristin Thurner to the Affective Computing Group. Ann-Kristin is an experienced Psychotherapist coming back to DFKI to support ACG with modelling the behaviour of empathic Agents and expert evaluations.

February 3rd: We are happy to announce that we will have another round of the seminar “How to Build a Social Computer?” in summer 2021. There will be place for 9 computer science students and 9 psychology students. The kick-off meeting will be on April 13th 2021. Psychology students have the usual process for getting into seminars by registering in LSF. Computer science students that want to participate please register on the sic seminar page.  

January 1st: We are excited to start the new year with great partners in the project “easier”. It is funded under the EU Horizon 2020 programme (Grant Agreement number 101016982). Check out the project website here