Sentic avatar: Multimodal affective conversational agent with common sense

Cambria, Erik; Hupont, Isabelle; Hussain, Amir; Cerezo, Eva; Baldassarri, Sandra

Abstract

The capability of perceiving and expressing emotions through different modalities is a key issue for the enhancement of human-computer interaction. In this paper we present a novel architecture for the development of intelligent multimodal affective interfaces. It is based on the integration of Sentic Computing, a new opinion mining and sentiment analysis paradigm based on AI and Semantic Web techniques, with a facial emotional classifier and Maxine, a powerful multimodal animation engine for managing virtual agents and 3D scenarios. One of the main distinguishing features of the system is that it does not simply perform emotional classification in terms of a set of discrete emotional labels but it operates in a continuous 2D emotional space, enabling the integration of the different affective extraction modules in a simple and scalable way.

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: Third COST 2102 International Training School
• Start Date: Mar 15, 2010
• End Date: Mar 19, 2010
• Publication Date: 2011
• Deposit Date: Oct 15, 2019
• Publisher: Springer
• Pages: 81-95
• Series Title: Lecture Notes in Computer Science
• Series Number: 6456
• Series ISSN: 0302-9743
• Book Title: Toward Autonomous, Adaptive, and Context-Aware Multimodal Interfaces. Theoretical and Practical Issues Third COST 2102 International Training School, Caserta, Italy, March 15-19, 2010, Revised Selected Papers
• ISBN: 978-3-642-18183-2
• DOI: https://doi.org/10.1007/978-3-642-18184-9_8
• Keywords: AI; Sentic Computing; NLP; Facial Expression Analysis; Sentiment Analysis; Multimodal Affective HCI; Conversational Agents
• Public URL: http://researchrepository.napier.ac.uk/Output/1793382