International audienceDans l'optique de concevoir un agent conversationnel animé narratif et affectif, cet article montre l'importance de l'interaction dans le processus de narration à des enfants. Deux méthodes d'extraction de régularités ont été appliquées à des dialogues de narration parent-enfant afin de les modéliser. Les modèles extraits ont été évalués au cours d'une session de narration interactive de type Magicien d'Oz durant laquelle les enfants ont communiqué avec un personnage virtuel et un adulte en visio-conférence. L'expérience montre que les enfants s'engagent bien dans l'interaction avec le personnage virtuel mais que les modalités pour interagir diffèrent légèrement de celles utilisés avec l'adulte. ------------ To develop a narrative affective virtual agent, this article shows the importance of interaction modalities in storytelling environments. Building a narrative dialogue model requires a state transition that is computed automatically using various pattern extraction methods. These models are tested in a "Wizard-of-Oz" context, in a storytelling environment where the children are challenged to interact with a virtual character, by modelling several key points of interaction. We compare the level of engagement in two different narration contexts: virtual character or adult in video conference mode. Our experiments showed that the engagement exists, but the modality of the interaction feedback varies in the two contexts
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.