Evaluating Temporal Predictive Features for Virtual Patients Feedbacks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Evaluating Temporal Predictive Features for Virtual Patients Feedbacks

Résumé

A key challenge when studying human-agent interaction is the evaluation of user's experience. In virtual reality, this question is addressed by studying the sense of "presence" and"co-presence", generally assessed thanks to well-grounded subjective post-experience questionnaires. In this article, we aim at exploring behavioral measures of presence and co-presence by analyzing multimodal cues produced during an interaction both by the user and the virtual agent. In our study, we started from a corpus of human-agent interaction collected in a task-oriented context: a virtual environment aiming at training doctors to break bad news to a patient (played by a virtual agent). Based on this corpus, we have used machine learning algorithms to explore the possibility of predicting user's sense of presence and co-presence. In particular, we have applied and compared two techniques, Random forest and SVM, both showing very good results in predicting the level of presence and co-presence.
Fichier principal
Vignette du fichier
ivaea315-penteadoA.pdf (362.33 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02355386 , version 1 (08-11-2019)

Identifiants

Citer

Bruno Elias Penteado, Magalie Ochs, Roxane Bertrand, Philippe Blache. Evaluating Temporal Predictive Features for Virtual Patients Feedbacks. ACM International Conference on Intelligent Virtual Agent (IVA), Jul 2019, Paris, France. ⟨10.1145/3308532.3329438⟩. ⟨hal-02355386⟩
41 Consultations
117 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More