Monitoring the understanding of explanations (Project A02)

When something is being explained to someone, the explainee signals their understanding – or lack thereof – to the explainer with verbal expressions and other non-verbal means of communication, such as gestures and facial expressions. By nodding, the explainee can signal that they have understood. Nodding, however, can also be meant as a request to continue with the explanation. This has to be determined from the context of the conversation. In Project A02, linguists and computational linguists are investigating how people (and later, artificial agents) recognize that the person they’re explaining something to is understanding – or not.  For this, the research team will be looking at 80 dialogues in which one person explains a social game to another, examining these for communicative feedback signals that indicate varying degrees of comprehension in the process of understanding. The findings from these analyses will be incorporated into an intelligent system that will be able to detect feedback signals such as head nods and interpret them in terms of signaled level of understanding.

Axelsson, A., Buschmeier, H. and Skantze, G. (2022) Modeling Feedback in Interaction With Conversational Agents - A Review. Front. Comput. Sci. 4:744574. doi: 10.3389/fcomp.2022.744574

Lazarov, S., Grimminger, A. (2023) The Relation Between Multimodal Behaviour And Elaborations In Explanations. Poster for the "1st International Multimodal Communication Symposium". View poster

Wang, Y., Buschmeier, H. (2023) An Unsupervised Method for Head Movement Detection. View poster