I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational Agent
We describe the work on infusion of emotion into a limited-task autonomous spoken conversational agent situated in the domestic environment, using a need-inspired task-independent emotion model (NEMO). In order to demonstrate the generation of affect through the use of the model, we describe the wor...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2013-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/13/8/10519 |
_version_ | 1828151552146145280 |
---|---|
author | Juan Manuel Montero Fernando Fernández-Martínez Roberto Barra-Chicote Jaime Lorenzo-Trueba Syaheerah Lebai Lutfi |
author_facet | Juan Manuel Montero Fernando Fernández-Martínez Roberto Barra-Chicote Jaime Lorenzo-Trueba Syaheerah Lebai Lutfi |
author_sort | Juan Manuel Montero |
collection | DOAJ |
description | We describe the work on infusion of emotion into a limited-task autonomous spoken conversational agent situated in the domestic environment, using a need-inspired task-independent emotion model (NEMO). In order to demonstrate the generation of affect through the use of the model, we describe the work of integrating it with a natural-language mixed-initiative HiFi-control spoken conversational agent (SCA). NEMO and the host system communicate externally, removing the need for the Dialog Manager to be modified, as is done in most existing dialog systems, in order to be adaptive. The first part of the paper concerns the integration between NEMO and the host agent. The second part summarizes the work on automatic affect prediction, namely, frustration and contentment, from dialog features, a non-conventional source, in the attempt of moving towards a more user-centric approach. The final part reports the evaluation results obtained from a user study, in which both versions of the agent (non-adaptive and emotionally-adaptive) were compared. The results provide substantial evidences with respect to the benefits of adding emotion in a spoken conversational agent, especially in mitigating users’ frustrations and, ultimately, improving their satisfaction. |
first_indexed | 2024-04-11T21:59:23Z |
format | Article |
id | doaj.art-4825c0b2ed424244ba81ffc68495f516 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T21:59:23Z |
publishDate | 2013-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-4825c0b2ed424244ba81ffc68495f5162022-12-22T04:01:00ZengMDPI AGSensors1424-82202013-08-01138105191053810.3390/s130810519I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational AgentJuan Manuel MonteroFernando Fernández-MartínezRoberto Barra-ChicoteJaime Lorenzo-TruebaSyaheerah Lebai LutfiWe describe the work on infusion of emotion into a limited-task autonomous spoken conversational agent situated in the domestic environment, using a need-inspired task-independent emotion model (NEMO). In order to demonstrate the generation of affect through the use of the model, we describe the work of integrating it with a natural-language mixed-initiative HiFi-control spoken conversational agent (SCA). NEMO and the host system communicate externally, removing the need for the Dialog Manager to be modified, as is done in most existing dialog systems, in order to be adaptive. The first part of the paper concerns the integration between NEMO and the host agent. The second part summarizes the work on automatic affect prediction, namely, frustration and contentment, from dialog features, a non-conventional source, in the attempt of moving towards a more user-centric approach. The final part reports the evaluation results obtained from a user study, in which both versions of the agent (non-adaptive and emotionally-adaptive) were compared. The results provide substantial evidences with respect to the benefits of adding emotion in a spoken conversational agent, especially in mitigating users’ frustrations and, ultimately, improving their satisfaction.http://www.mdpi.com/1424-8220/13/8/10519spoken conversational agentsaffect predictiondomotic applicationsaffective agentsfrustrationcontentmentconversational featuresuser satisfactionemotion modelemotion design and evaluation |
spellingShingle | Juan Manuel Montero Fernando Fernández-Martínez Roberto Barra-Chicote Jaime Lorenzo-Trueba Syaheerah Lebai Lutfi I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational Agent Sensors spoken conversational agents affect prediction domotic applications affective agents frustration contentment conversational features user satisfaction emotion model emotion design and evaluation |
title | I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational Agent |
title_full | I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational Agent |
title_fullStr | I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational Agent |
title_full_unstemmed | I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational Agent |
title_short | I Feel You: The Design and Evaluation of a Domotic Affect-Sensitive Spoken Conversational Agent |
title_sort | i feel you the design and evaluation of a domotic affect sensitive spoken conversational agent |
topic | spoken conversational agents affect prediction domotic applications affective agents frustration contentment conversational features user satisfaction emotion model emotion design and evaluation |
url | http://www.mdpi.com/1424-8220/13/8/10519 |
work_keys_str_mv | AT juanmanuelmontero ifeelyouthedesignandevaluationofadomoticaffectsensitivespokenconversationalagent AT fernandofernandezmartinez ifeelyouthedesignandevaluationofadomoticaffectsensitivespokenconversationalagent AT robertobarrachicote ifeelyouthedesignandevaluationofadomoticaffectsensitivespokenconversationalagent AT jaimelorenzotrueba ifeelyouthedesignandevaluationofadomoticaffectsensitivespokenconversationalagent AT syaheerahlebailutfi ifeelyouthedesignandevaluationofadomoticaffectsensitivespokenconversationalagent |