Home // ACHI 2020, The Thirteenth International Conference on Advances in Computer-Human Interactions // View article

Embodied Conversational Agent for Emotional Recognition Training

Authors:
Karl Daher
Zeno Bardelli
Jacky Casas
Elena Mugellini
Omar Abou Khaled
Denis Lalanne

Keywords: HCI, ECA, Conversational agent, Avatar, Emotions

Abstract:
Avatars were known in the world of video games, where heroes with specific characters, attributes and powers are assigned to players. However, avatars are evolving and reaching domains like companions, assistants and tutors. These avatars now use speech, facial expression, body language or text to interact with humans. When we say interaction, we say emotional expression and empathy. Avatars are still short in the emotional and empathic world; it cannot express nor share emotions. In this paper, we research the emotional avatar world, and we present the Anthropomorphic Chatbot for Emotion Recognition (ACER), an empathic friend companion designed for children. The goal of ACER is to teach children about emotions by expressing it through facial expressions and body language while texting through a chat. An experiment was held to test the avatar effect. Qualitative and quantitative results show users positive emotions tending towards having a chat with ACER with facial and body expressions instead of only ACERs chatbot.

Pages: 384 to 390

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-61208-761-0

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020