Supporting Acceptable Dialogue Start Based on User Uninterruptibility Estimation for Avatar-Mediated Multi-tasking Online Communication

Authors:
Takahiro Tanaka;Kyouhei Matsumura;Kinya Fujita
Affiliations:
Tokyo University of Agriculture and Technology, Tokyo, Japan 184-8588;Tokyo University of Agriculture and Technology, Tokyo, Japan 184-8588;Tokyo University of Agriculture and Technology, Tokyo, Japan 184-8588
Venue:
OCSC '09 Proceedings of the 3d International Conference on Online Communities and Social Computing: Held as Part of HCI International 2009
Year:
2009

Citing 5
Cited 0

The GAZE groupware system: mediating joint attention in multiparty communication and collaboration

Proceedings of the SIGCHI conference on Human Factors in Computing Systems
Predicting human interruptibility with sensors: a Wizard of Oz feasibility study

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Emotionally Expressive Head and Body Movement During Gaze Shifts

IVA '07 Proceedings of the 7th international conference on Intelligent Virtual Agents
A hybrid discriminative/generative approach for modeling human activities

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Nonverbal behavior generator for embodied conversational agents

IVA'06 Proceedings of the 6th international conference on Intelligent Virtual Agents

Quantified Score

Hi-index	0.00

Visualization

Abstract

Current users of real-time online communication tools have difficulty recognizing the status of interaction partners. Therefore, initiation dialogue has a risk of unintended interruption of the partner. To overcome the problem, we focused on application-switching (AS) as a potential intelligent activity discontinuity marker for uninterruptibility estimation. Preliminary experiments revealed an uninterruptibility reduction effect of AS. Therefore, we prototyped an acceptable dialogue start supporting agent system that allows users to recognize the uninterruptibility of interaction partners naturally. The system estimates uninterruptibility using AS, keystrokes, and mouse clicks, and presenting the results by avatar posture and motion using overlapping expressions to control the impression of uninterruptibility.