Gaze Awareness in Agent-Based Early-Childhood Learning Application - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Gaze Awareness in Agent-Based Early-Childhood Learning Application

Deepak Akkil
  • Fonction : Auteur
  • PersonId : 1026161
Prasenjit Dey
  • Fonction : Auteur
  • PersonId : 1026162
Deepshika Salian
  • Fonction : Auteur
  • PersonId : 1026163
Nitendra Rajput
  • Fonction : Auteur
  • PersonId : 1026164

Résumé

Use of technological devices for early childhood learning is increasing. Now, kindergarten and primary school children use interactive applications on mobile phones and tablet computers to support and complement classroom learning. With increase in cognitive technologies, there is further potential to make such applications more engaging by understanding the user context. In this paper, we present the Little Bear, a gaze aware pedagogical agent, that tailors its verbal and non-verbal behavior based on the visual attention of the child and employs means to reorient the attention of the child, when distracted from the learning activity. We used the Little Bear agent in a learning application to enable teaching the vocabulary of everyday fruits and vegetables. Our user-study (n = 12) with preschoolers shows that children interacted longer and showed improved short-term retention of the vocabulary using the gaze aware agent compared to a baseline touch-based application. Our results demonstrate the potential of gaze aware application design for early childhood learning.
Fichier principal
Vignette du fichier
421760_1_En_28_Chapter.pdf (880.07 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01678416 , version 1 (09-01-2018)

Licence

Paternité

Identifiants

Citer

Deepak Akkil, Prasenjit Dey, Deepshika Salian, Nitendra Rajput. Gaze Awareness in Agent-Based Early-Childhood Learning Application. 16th IFIP Conference on Human-Computer Interaction (INTERACT), Sep 2017, Bombay, India. pp.447-466, ⟨10.1007/978-3-319-67684-5_28⟩. ⟨hal-01678416⟩
97 Consultations
92 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More