A multimodal corpus for the study of non-verbal behavior expressing interpersonal stances

Mathieu Chollet (1) , Magalie Ochs (1) , Catherine Pelachaud (1)

1 LTCI - Laboratoire Traitement et Communication de l'Information

In order to give the capability to a virtual recruiter to convey interpersonal stances through its non-verbal behavior, we propose to use a multimodal corpus approach using videos of job recruitment enactments. The corpus has been annotated at different levels to consider both the participants' non-verbal behavior and the expressed stances. In this article, we present this corpus and our annotations, and discuss issues related to the specificity of the acquired data.

Domaines: Interface homme-machine [cs.HC]

Mathieu Chollet, Magalie Ochs, Catherine Pelachaud. A multimodal corpus for the study of non-verbal behavior expressing interpersonal stances. IVA 2013 Workshop Multimodal Corpora: Beyond Audio and Video, Sep 2013, Edinburgh, United Kingdom. ⟨hal-01074865⟩