No Cover Image

Conference Paper/Proceeding/Abstract 552 views 430 downloads

Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study

Joy Egede, Maria J. Galvez Trigo, Adrian Hazzard, Martin Porcheron Orcid Logo, Edgar Bodiaj, Joel E. Fischer, Chris Greenhalgh, Michel Valstar

IVA 2021: 21st ACM International Conference on Intelligent Virtual Agents, Pages: 112 - 119

Swansea University Author: Martin Porcheron Orcid Logo

DOI (Published version): 10.1145/3472306.3478350

Abstract

Access to healthcare advice is crucial to promote healthy societies. Many factors shape how access might be constrained, such as economic status, education or, as the COVID-19 pandemic has shown, remote consultations with health practitioners. Our work focuses on providing pre/post-natal advice to m...

Full description

Published in: IVA 2021: 21st ACM International Conference on Intelligent Virtual Agents
ISBN: 978-1-4503-8619-7
Published: Association for Computing Machinery 2021
Online Access: https://doi.org/10.1145/3472306.3478350
URI: https://cronfa.swan.ac.uk/Record/cronfa57166
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-08-02T12:53:35Z
last_indexed 2021-12-02T04:14:08Z
id cronfa57166
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-12-01T10:47:51.8671918</datestamp><bib-version>v2</bib-version><id>57166</id><entry>2021-06-17</entry><title>Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study</title><swanseaauthors><author><sid>d9de398c04c0b443d547d455782d5de5</sid><ORCID>0000-0003-3814-7174</ORCID><firstname>Martin</firstname><surname>Porcheron</surname><name>Martin Porcheron</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-06-17</date><deptcode>SCS</deptcode><abstract>Access to healthcare advice is crucial to promote healthy societies. Many factors shape how access might be constrained, such as economic status, education or, as the COVID-19 pandemic has shown, remote consultations with health practitioners. Our work focuses on providing pre/post-natal advice to maternal women. A salient factor of our work concerns the design and deployment of embodied conversation agents (ECAs) which can sense the (health) literacy of users and adapt to scaffold user engagement in this setting. We present an account of a Wizard of Oz user study of `ALTCAI&#x2019;, an ECA with three modes of interaction (i.e., adaptive speech and text, adaptive ECA, and non-adaptive ECA). We compare reported engagement with these modes from 44 maternal women who have differing levels of literacy. The study shows that a combination of embodiment and adaptivity scaffolds reported engagement, but matters of health-literacy and language introduce nuanced considerations for the design of ECAs.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>IVA 2021: 21st ACM International Conference on Intelligent Virtual Agents</journal><volume/><journalNumber/><paginationStart>112</paginationStart><paginationEnd>119</paginationEnd><publisher>Association for Computing Machinery</publisher><placeOfPublication/><isbnPrint/><isbnElectronic>978-1-4503-8619-7</isbnElectronic><issnPrint/><issnElectronic/><keywords>embodied conversational agents, virtual human, design, health and well-being, literacy, user study</keywords><publishedDay>14</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-09-14</publishedDate><doi>10.1145/3472306.3478350</doi><url>https://doi.org/10.1145/3472306.3478350</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>Department for International Development and Engineering and Physical Sciences Research Council</funders><projectreference>EP/V00784X/1</projectreference><lastEdited>2021-12-01T10:47:51.8671918</lastEdited><Created>2021-06-17T14:46:39.0488959</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Joy</firstname><surname>Egede</surname><order>1</order></author><author><firstname>Maria J. Galvez</firstname><surname>Trigo</surname><order>2</order></author><author><firstname>Adrian</firstname><surname>Hazzard</surname><order>3</order></author><author><firstname>Martin</firstname><surname>Porcheron</surname><orcid>0000-0003-3814-7174</orcid><order>4</order></author><author><firstname>Edgar</firstname><surname>Bodiaj</surname><order>5</order></author><author><firstname>Joel E.</firstname><surname>Fischer</surname><order>6</order></author><author><firstname>Chris</firstname><surname>Greenhalgh</surname><order>7</order></author><author><firstname>Michel</firstname><surname>Valstar</surname><order>8</order></author></authors><documents><document><filename>57166__20511__b5c4307532cb402c9a5eed3b14afd9c7.pdf</filename><originalFilename>IVA2021 - ALTCAI.pdf</originalFilename><uploaded>2021-08-02T13:53:13.2787461</uploaded><type>Output</type><contentLength>1188550</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>false</copyrightCorrect></document></documents><OutputDurs/></rfc1807>
spelling 2021-12-01T10:47:51.8671918 v2 57166 2021-06-17 Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study d9de398c04c0b443d547d455782d5de5 0000-0003-3814-7174 Martin Porcheron Martin Porcheron true false 2021-06-17 SCS Access to healthcare advice is crucial to promote healthy societies. Many factors shape how access might be constrained, such as economic status, education or, as the COVID-19 pandemic has shown, remote consultations with health practitioners. Our work focuses on providing pre/post-natal advice to maternal women. A salient factor of our work concerns the design and deployment of embodied conversation agents (ECAs) which can sense the (health) literacy of users and adapt to scaffold user engagement in this setting. We present an account of a Wizard of Oz user study of `ALTCAI’, an ECA with three modes of interaction (i.e., adaptive speech and text, adaptive ECA, and non-adaptive ECA). We compare reported engagement with these modes from 44 maternal women who have differing levels of literacy. The study shows that a combination of embodiment and adaptivity scaffolds reported engagement, but matters of health-literacy and language introduce nuanced considerations for the design of ECAs. Conference Paper/Proceeding/Abstract IVA 2021: 21st ACM International Conference on Intelligent Virtual Agents 112 119 Association for Computing Machinery 978-1-4503-8619-7 embodied conversational agents, virtual human, design, health and well-being, literacy, user study 14 9 2021 2021-09-14 10.1145/3472306.3478350 https://doi.org/10.1145/3472306.3478350 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University Not Required Department for International Development and Engineering and Physical Sciences Research Council EP/V00784X/1 2021-12-01T10:47:51.8671918 2021-06-17T14:46:39.0488959 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Joy Egede 1 Maria J. Galvez Trigo 2 Adrian Hazzard 3 Martin Porcheron 0000-0003-3814-7174 4 Edgar Bodiaj 5 Joel E. Fischer 6 Chris Greenhalgh 7 Michel Valstar 8 57166__20511__b5c4307532cb402c9a5eed3b14afd9c7.pdf IVA2021 - ALTCAI.pdf 2021-08-02T13:53:13.2787461 Output 1188550 application/pdf Accepted Manuscript true false
title Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
spellingShingle Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
Martin Porcheron
title_short Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
title_full Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
title_fullStr Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
title_full_unstemmed Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
title_sort Designing an Adaptive Embodied Conversational Agent for Health Literacy: a User Study
author_id_str_mv d9de398c04c0b443d547d455782d5de5
author_id_fullname_str_mv d9de398c04c0b443d547d455782d5de5_***_Martin Porcheron
author Martin Porcheron
author2 Joy Egede
Maria J. Galvez Trigo
Adrian Hazzard
Martin Porcheron
Edgar Bodiaj
Joel E. Fischer
Chris Greenhalgh
Michel Valstar
format Conference Paper/Proceeding/Abstract
container_title IVA 2021: 21st ACM International Conference on Intelligent Virtual Agents
container_start_page 112
publishDate 2021
institution Swansea University
isbn 978-1-4503-8619-7
doi_str_mv 10.1145/3472306.3478350
publisher Association for Computing Machinery
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url https://doi.org/10.1145/3472306.3478350
document_store_str 1
active_str 0
description Access to healthcare advice is crucial to promote healthy societies. Many factors shape how access might be constrained, such as economic status, education or, as the COVID-19 pandemic has shown, remote consultations with health practitioners. Our work focuses on providing pre/post-natal advice to maternal women. A salient factor of our work concerns the design and deployment of embodied conversation agents (ECAs) which can sense the (health) literacy of users and adapt to scaffold user engagement in this setting. We present an account of a Wizard of Oz user study of `ALTCAI’, an ECA with three modes of interaction (i.e., adaptive speech and text, adaptive ECA, and non-adaptive ECA). We compare reported engagement with these modes from 44 maternal women who have differing levels of literacy. The study shows that a combination of embodiment and adaptivity scaffolds reported engagement, but matters of health-literacy and language introduce nuanced considerations for the design of ECAs.
published_date 2021-09-14T04:12:41Z
_version_ 1763753865370402816
score 11.012678