Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Adapting to multiple affective states in spoken dialogue

UNSPECIFIED (2012) Adapting to multiple affective states in spoken dialogue. In: UNSPECIFIED.

[img] Plain Text (licence)
Available under License : See the attached license file.

Download (1kB)

Abstract

©2012 Association for Computational Linguistics. We evaluate a wizard-of-oz spoken dialoguesystem that adapts to multiple user affectivestates in real-time: user disengagement anduncertainty. We compare this version with theprior version of our system, which only adaptsto user uncertainty. Our analysis investigateshow iteratively adding new affect adaptationto an existing affect-adaptive system impactsglobal and local performance. We find a significantincrease in motivation for users whomost frequently received the disengagementadaptation. Moreover, responding to disengagementbreaks its negative correlations withtask success and user satisfaction, reduces uncertaintylevels, and reduces the likelihood ofcontinued disengagement.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (UNSPECIFIED)
Status: Published
Centers: University Centers > Learning Research and Development Center (LRDC)
Date: 1 January 2012
Date Type: Publication
Journal or Publication Title: SIGDIAL 2012 - 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
Page Range: 217 - 226
Event Type: Conference
Schools and Programs: Dietrich School of Arts and Sciences > Computer Science
Dietrich School of Arts and Sciences > Intelligent Systems
Refereed: Yes
ISBN: 9781937284442
Date Deposited: 22 Sep 2014 19:52
Last Modified: 05 Jan 2019 14:56
URI: http://d-scholarship.pitt.edu/id/eprint/22882

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item