No Cover Image

Conference Paper/Proceeding/Abstract 237 views 124 downloads

What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents

Leigh Clark Orcid Logo, Cosmin Munteanu, Vincent Wade, Benjamin R. Cowan, Nadia Pantidi, Orla Cooney, Philip Doyle, Diego Garaialde, Justin Edwards, Brendan Spillane, Emer Gilmartin, Christine Murad

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19, Pages: 1 - 12

Swansea University Author: Leigh Clark Orcid Logo

DOI (Published version): 10.1145/3290605.3300705

Abstract

Conversational agents promise conversational interaction but fail to deliver. Efforts often emulate functional rules from human speech, without considering key characteristics that conversation must encapsulate. Given its potential in supporting long-term human-agent relationships, it is paramount t...

Full description

Published in: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19
ISBN: 9781450359702 978-1-4503-5970-2
Published: New York, New York, USA ACM Press 2019
URI: https://cronfa.swan.ac.uk/Record/cronfa52477
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-10-16T20:25:39Z
last_indexed 2020-09-26T03:12:44Z
id cronfa52477
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-09-25T15:07:26.7778477</datestamp><bib-version>v2</bib-version><id>52477</id><entry>2019-10-16</entry><title>What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents</title><swanseaauthors><author><sid>004ef41b90854a57a498549a462f13a0</sid><ORCID>0000-0002-9237-1057</ORCID><firstname>Leigh</firstname><surname>Clark</surname><name>Leigh Clark</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2019-10-16</date><deptcode>SCS</deptcode><abstract>Conversational agents promise conversational interaction but fail to deliver. Efforts often emulate functional rules from human speech, without considering key characteristics that conversation must encapsulate. Given its potential in supporting long-term human-agent relationships, it is paramount that HCI focuses efforts on delivering this promise. We aim to understand what people value in conversation and how this should manifest in agents. Findings from a series of semi-structured interviews show people make a clear dichotomy between social and functional roles of conversation, emphasising the long-term dynamics of bond and trust along with the importance of context and relationship stage in the types of conversations they have. People fundamentally questioned the need for bond and common ground in agent communication, shifting to more utilitarian definitions of conversational qualities. Drawing on these findings we discuss key challenges for conversational agent design, most notably the need to redefine the design parameters for conversational agent interaction.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19</journal><paginationStart>1</paginationStart><paginationEnd>12</paginationEnd><publisher>ACM Press</publisher><placeOfPublication>New York, New York, USA</placeOfPublication><isbnPrint>9781450359702</isbnPrint><isbnElectronic>978-1-4503-5970-2</isbnElectronic><keywords>Conversational Agents, Speech HCI, Spoken Dialogue Sys- tems, Voice User Interface Design, Interviews</keywords><publishedDay>2</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-05-02</publishedDate><doi>10.1145/3290605.3300705</doi><url/><notes>Received CHI 2019 Honourable Mention award.</notes><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-09-25T15:07:26.7778477</lastEdited><Created>2019-10-16T17:04:23.6649431</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Leigh</firstname><surname>Clark</surname><orcid>0000-0002-9237-1057</orcid><order>1</order></author><author><firstname>Cosmin</firstname><surname>Munteanu</surname><order>2</order></author><author><firstname>Vincent</firstname><surname>Wade</surname><order>3</order></author><author><firstname>Benjamin R.</firstname><surname>Cowan</surname><order>4</order></author><author><firstname>Nadia</firstname><surname>Pantidi</surname><order>5</order></author><author><firstname>Orla</firstname><surname>Cooney</surname><order>6</order></author><author><firstname>Philip</firstname><surname>Doyle</surname><order>7</order></author><author><firstname>Diego</firstname><surname>Garaialde</surname><order>8</order></author><author><firstname>Justin</firstname><surname>Edwards</surname><order>9</order></author><author><firstname>Brendan</firstname><surname>Spillane</surname><order>10</order></author><author><firstname>Emer</firstname><surname>Gilmartin</surname><order>11</order></author><author><firstname>Christine</firstname><surname>Murad</surname><order>12</order></author></authors><documents><document><filename>52477__15656__308f49bce101464eba5b5df526c5c631.pdf</filename><originalFilename>1901.06525.pdf</originalFilename><uploaded>2019-10-17T13:50:58.0670000</uploaded><type>Output</type><contentLength>484639</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-10-17T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2020-09-25T15:07:26.7778477 v2 52477 2019-10-16 What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents 004ef41b90854a57a498549a462f13a0 0000-0002-9237-1057 Leigh Clark Leigh Clark true false 2019-10-16 SCS Conversational agents promise conversational interaction but fail to deliver. Efforts often emulate functional rules from human speech, without considering key characteristics that conversation must encapsulate. Given its potential in supporting long-term human-agent relationships, it is paramount that HCI focuses efforts on delivering this promise. We aim to understand what people value in conversation and how this should manifest in agents. Findings from a series of semi-structured interviews show people make a clear dichotomy between social and functional roles of conversation, emphasising the long-term dynamics of bond and trust along with the importance of context and relationship stage in the types of conversations they have. People fundamentally questioned the need for bond and common ground in agent communication, shifting to more utilitarian definitions of conversational qualities. Drawing on these findings we discuss key challenges for conversational agent design, most notably the need to redefine the design parameters for conversational agent interaction. Conference Paper/Proceeding/Abstract Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19 1 12 ACM Press New York, New York, USA 9781450359702 978-1-4503-5970-2 Conversational Agents, Speech HCI, Spoken Dialogue Sys- tems, Voice User Interface Design, Interviews 2 5 2019 2019-05-02 10.1145/3290605.3300705 Received CHI 2019 Honourable Mention award. COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2020-09-25T15:07:26.7778477 2019-10-16T17:04:23.6649431 College of Science Computer Science Leigh Clark 0000-0002-9237-1057 1 Cosmin Munteanu 2 Vincent Wade 3 Benjamin R. Cowan 4 Nadia Pantidi 5 Orla Cooney 6 Philip Doyle 7 Diego Garaialde 8 Justin Edwards 9 Brendan Spillane 10 Emer Gilmartin 11 Christine Murad 12 52477__15656__308f49bce101464eba5b5df526c5c631.pdf 1901.06525.pdf 2019-10-17T13:50:58.0670000 Output 484639 application/pdf Accepted Manuscript true 2019-10-17T00:00:00.0000000 true eng
title What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
spellingShingle What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
Leigh, Clark
title_short What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
title_full What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
title_fullStr What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
title_full_unstemmed What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
title_sort What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
author_id_str_mv 004ef41b90854a57a498549a462f13a0
author_id_fullname_str_mv 004ef41b90854a57a498549a462f13a0_***_Leigh, Clark_***_0000-0002-9237-1057
author Leigh, Clark
author2 Leigh Clark
Cosmin Munteanu
Vincent Wade
Benjamin R. Cowan
Nadia Pantidi
Orla Cooney
Philip Doyle
Diego Garaialde
Justin Edwards
Brendan Spillane
Emer Gilmartin
Christine Murad
format Conference Paper/Proceeding/Abstract
container_title Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems - CHI '19
container_start_page 1
publishDate 2019
institution Swansea University
isbn 9781450359702
978-1-4503-5970-2
doi_str_mv 10.1145/3290605.3300705
publisher ACM Press
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
document_store_str 1
active_str 0
description Conversational agents promise conversational interaction but fail to deliver. Efforts often emulate functional rules from human speech, without considering key characteristics that conversation must encapsulate. Given its potential in supporting long-term human-agent relationships, it is paramount that HCI focuses efforts on delivering this promise. We aim to understand what people value in conversation and how this should manifest in agents. Findings from a series of semi-structured interviews show people make a clear dichotomy between social and functional roles of conversation, emphasising the long-term dynamics of bond and trust along with the importance of context and relationship stage in the types of conversations they have. People fundamentally questioned the need for bond and common ground in agent communication, shifting to more utilitarian definitions of conversational qualities. Drawing on these findings we discuss key challenges for conversational agent design, most notably the need to redefine the design parameters for conversational agent interaction.
published_date 2019-05-02T04:16:51Z
_version_ 1722626878886379520
score 10.852379