Journal article 913 views 259 downloads
An explainable multi-attribute decision model based on argumentation
Qiaoting Zhong,
Xiuyi Fan,
Xudong Luo,
Francesca Toni
Expert Systems with Applications, Volume: 117, Pages: 42 - 61
Swansea University Author: Xiuyi Fan
-
PDF | Accepted Manuscript
Released under the terms of a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND).
Download (830.65KB)
DOI (Published version): 10.1016/j.eswa.2018.09.038
Abstract
An explainable multi-attribute decision model based on argumentation
Published in: | Expert Systems with Applications |
---|---|
ISSN: | 09574174 |
Published: |
2019
|
Online Access: |
Check full text
|
URI: | https://cronfa.swan.ac.uk/Record/cronfa44264 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
first_indexed |
2018-09-18T04:02:48Z |
---|---|
last_indexed |
2020-08-07T03:10:29Z |
id |
cronfa44264 |
recordtype |
SURis |
fullrecord |
<?xml version="1.0"?><rfc1807><datestamp>2020-08-06T16:53:29.9547046</datestamp><bib-version>v2</bib-version><id>44264</id><entry>2018-09-17</entry><title>An explainable multi-attribute decision model based on argumentation</title><swanseaauthors><author><sid>a88a07c43b3e80f27cb96897d1bc2534</sid><firstname>Xiuyi</firstname><surname>Fan</surname><name>Xiuyi Fan</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-09-17</date><abstract/><type>Journal Article</type><journal>Expert Systems with Applications</journal><volume>117</volume><paginationStart>42</paginationStart><paginationEnd>61</paginationEnd><publisher/><issnPrint>09574174</issnPrint><keywords>argumentation, decision making, explanation</keywords><publishedDay>1</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-03-01</publishedDate><doi>10.1016/j.eswa.2018.09.038</doi><url/><notes>Originality:In this paper, we present a multi-attribute decision model and a method for explaining the decisions it recommends based on an argumentative reformulation of the model. Specifically, (i) we define a notion of best decisions amounting to achieving as many goals as possible and exhibiting as few redundant attributes as possible, and (ii) we generate explanations for why a decision is best or better than or as good as another.Significance:Explainability is important to automatic decision-making systems as without a clear understanding of how a recommended decision is generated, it is hard to ensure human trust, debug and improve these systems. By connecting decision making with argumentation, this work provides a mechanism for realizing explainable decision making. Rigor:All results are shown with full proofs. We also conduct an empirical evaluation of our method with legal practitioners, confirming that our method is helpful to understand automatically generated recommendations.</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-08-06T16:53:29.9547046</lastEdited><Created>2018-09-17T20:50:54.9427909</Created><authors><author><firstname>Qiaoting</firstname><surname>Zhong</surname><order>1</order></author><author><firstname>Xiuyi</firstname><surname>Fan</surname><order>2</order></author><author><firstname>Xudong</firstname><surname>Luo</surname><order>3</order></author><author><firstname>Francesca</firstname><surname>Toni</surname><order>4</order></author></authors><documents><document><filename>0044264-17092018205126.pdf</filename><originalFilename>SourceFileFTchanges.pdf</originalFilename><uploaded>2018-09-17T20:51:26.7530000</uploaded><type>Output</type><contentLength>814986</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-09-21T00:00:00.0000000</embargoDate><documentNotes>Released under the terms of a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807> |
spelling |
2020-08-06T16:53:29.9547046 v2 44264 2018-09-17 An explainable multi-attribute decision model based on argumentation a88a07c43b3e80f27cb96897d1bc2534 Xiuyi Fan Xiuyi Fan true false 2018-09-17 Journal Article Expert Systems with Applications 117 42 61 09574174 argumentation, decision making, explanation 1 3 2019 2019-03-01 10.1016/j.eswa.2018.09.038 Originality:In this paper, we present a multi-attribute decision model and a method for explaining the decisions it recommends based on an argumentative reformulation of the model. Specifically, (i) we define a notion of best decisions amounting to achieving as many goals as possible and exhibiting as few redundant attributes as possible, and (ii) we generate explanations for why a decision is best or better than or as good as another.Significance:Explainability is important to automatic decision-making systems as without a clear understanding of how a recommended decision is generated, it is hard to ensure human trust, debug and improve these systems. By connecting decision making with argumentation, this work provides a mechanism for realizing explainable decision making. Rigor:All results are shown with full proofs. We also conduct an empirical evaluation of our method with legal practitioners, confirming that our method is helpful to understand automatically generated recommendations. COLLEGE NANME COLLEGE CODE Swansea University 2020-08-06T16:53:29.9547046 2018-09-17T20:50:54.9427909 Qiaoting Zhong 1 Xiuyi Fan 2 Xudong Luo 3 Francesca Toni 4 0044264-17092018205126.pdf SourceFileFTchanges.pdf 2018-09-17T20:51:26.7530000 Output 814986 application/pdf Accepted Manuscript true 2019-09-21T00:00:00.0000000 Released under the terms of a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND). true eng |
title |
An explainable multi-attribute decision model based on argumentation |
spellingShingle |
An explainable multi-attribute decision model based on argumentation Xiuyi Fan |
title_short |
An explainable multi-attribute decision model based on argumentation |
title_full |
An explainable multi-attribute decision model based on argumentation |
title_fullStr |
An explainable multi-attribute decision model based on argumentation |
title_full_unstemmed |
An explainable multi-attribute decision model based on argumentation |
title_sort |
An explainable multi-attribute decision model based on argumentation |
author_id_str_mv |
a88a07c43b3e80f27cb96897d1bc2534 |
author_id_fullname_str_mv |
a88a07c43b3e80f27cb96897d1bc2534_***_Xiuyi Fan |
author |
Xiuyi Fan |
author2 |
Qiaoting Zhong Xiuyi Fan Xudong Luo Francesca Toni |
format |
Journal article |
container_title |
Expert Systems with Applications |
container_volume |
117 |
container_start_page |
42 |
publishDate |
2019 |
institution |
Swansea University |
issn |
09574174 |
doi_str_mv |
10.1016/j.eswa.2018.09.038 |
document_store_str |
1 |
active_str |
0 |
published_date |
2019-03-01T03:55:29Z |
_version_ |
1763752783310225408 |
score |
11.021648 |