Toward a multi-culture adaptive virtual tour guide agent with a modular approach

Embodied conversational agents (ECAs) are computer-generated, human-like characters that interact with human users in face-to-face conversations. ECA is a powerful tool for representing cultural differences and is suitable for interactive training or edutainment systems. This article presents prelim...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:AI & society 2009-10, Vol.24 (3), p.225-235
Hauptverfasser: Huang, Hung-Hsuan, Cerekovic, Aleksandra, Pandzic, Igor S., Nakano, Yukiko, Nishida, Toyoaki
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Embodied conversational agents (ECAs) are computer-generated, human-like characters that interact with human users in face-to-face conversations. ECA is a powerful tool for representing cultural differences and is suitable for interactive training or edutainment systems. This article presents preliminary results from the development of a culture-adaptive virtual tour guide agent for serving Japanese, Croatian, and general Western users by displaying appropriate verbal and non-verbal behaviors. It is being implemented in Generic ECA Framework, a modular framework for developing ECAs. Dividing the ECA functions into reusable and loosely coupled modules minimizes the effort required to implement additional behavior and facilitates incremental scale up of the system.
ISSN:0951-5666
1435-5655
DOI:10.1007/s00146-009-0213-6