From Non-verbal Signals Sequence Mining to Bayesian Networks for Interpersonal Attitudes Expression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

From Non-verbal Signals Sequence Mining to Bayesian Networks for Interpersonal Attitudes Expression

Résumé

In this paper, we present a model and its evaluation for ex-pressing attitudes through sequences of non-verbal signals for Embodied Conversational Agents. To build our model, a corpus of interpersonal job interview interactions has been annotated at two levels: the non-verbal behavior of the recruiters as well as their expressed attitudes was anno-tated. Using a sequence mining method, sequences of non-verbal signals characterizing dierent interpersonal attitudes were automatically ex-tracted from the corpus. From this data, a probabilistic graphical model was built. The probabilistic model is used to select the most appropriate sequences of non-verbal signals that an ECA should display to convey a particular attitude. The results of a perceptive evaluation of sequences generated by the model show that such a model can be used to express some interpersonal attitudes.
Fichier principal
Vignette du fichier
iva2014camreadyv3nocolor.pdf (820.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01074880 , version 1 (15-10-2014)

Identifiants

Citer

Mathieu Chollet, Magalie Ochs, Catherine Pelachaud. From Non-verbal Signals Sequence Mining to Bayesian Networks for Interpersonal Attitudes Expression. Intelligent Virtual Agents, Aug 2014, Boston, United States. pp.120 - 133, ⟨10.1007/978-3-319-09767-1_15⟩. ⟨hal-01074880⟩
204 Consultations
434 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More