Evaluating humans' implicit attitudes towards an embodied conversational agent

Authors:
Andrey Kiselev;Niyaz Abdikeev;Toyoaki Nishida
Affiliations:
Dept. of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan;Plekhanov Russian Academy of Economics, Moscow, Russia;Dept. of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan
Venue:
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part I
Year:
2011

Citing 2
Cited 0

Computers are social actors

CHI '94 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
The design of a generic framework for integrating ECA components

Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the problem of evaluating embodied conversational agents in terms of their communicative performance. We show our attempt to evaluate humans' implicit attitudes towards different kinds of information presenting by embodied conversational agents using the Implicit Association Test (IAT) rather than gathering explicit data using interviewing methods. We conducted an experiment in which we use the method of indirect measurements with the IAT. The conventional procedure and scoring algorithm of the IAT were used in order to discover possible issues and solutions for future experiments. We discuss key differences between the conventional usage of the IAT and using the IAT in our experiment for evaluating embodied conversational agents using unfamiliar information as test data.