Affect as Information about Users' Attitudes to Conversational Agents

Abstract

This paper presents a novel method for automatic evaluation of conversational agents. In the method, information about users’ attitudes and sentiments to conversational agents and their performance are achieved by analyzing their general emotional engagement in the conversation and specific affective states, and interpreting them using psychological reasoning of Affect-as-Information. In the evaluation experiment the users’ attitudes to two Japanese-speaking conversational agents were checked simultaneously in a survey and using a system constructed on the proposed method. The results returned by the system revealed similar tendencies as the survey. Therefore the method is applicable as a mean of evaluation for Japanese-speaking conversational agents.

DOI: 10.1109/WIIAT.2008.192

Extracted Key Phrases

8 Figures and Tables

Cite this paper

@article{Ptaszynski2008AffectAI, title={Affect as Information about Users' Attitudes to Conversational Agents}, author={Michal Ptaszynski and Pawel Dybala and Shinsuke Higuchi and Rafal Rzepka and Kenji Araki}, journal={2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology}, year={2008}, volume={3}, pages={495-500} }