Pattern-based explanation for automated decisions

Ingrid Nunes; Simon Miles; Michael Luck; Simone Barbosa; Carlos Lucena

doi:10.3233/978-1-61499-419-0-669

Pattern-based explanation for automated decisions

Ingrid Nunes, Simon Miles, Michael Luck, Simone Barbosa, Carlos Lucena

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

15 Citations (Scopus)

83 Downloads (Pure)

Abstract

Explanations play an essential role in decision support and recommender systems as they are directly associated with the acceptance of those systems and the choices they make. Although approaches have been proposed to explain automated decisions based on multi-attribute decision models, there is a lack of evidence that they produce the explanations users need. In response, in this paper we propose an explanation generation technique, which follows user-derived explanation patterns. It receives as input a multi-attribute decision model, which is used together with user-centric principles to make a decision to which an explanation is generated. The technique includes algorithms that select relevant attributes and produce an explanation that justifies an automated choice. An evaluation with a user study demonstrates the effectiveness of our approach.

Original language	English
Title of host publication	Frontiers in Artificial Intelligence and Applications
Publisher	IOS Press
Pages	669-674
Number of pages	6
Volume	263
ISBN (Print)	9781614994183
DOIs	https://doi.org/10.3233/978-1-61499-419-0-669
Publication status	Published - 2014
Event	21st European Conference on Artificial Intelligence, ECAI 2014 - Prague, Czech Republic Duration: 18 Aug 2014 → 22 Aug 2014

Publication series

Name	Frontiers in Artificial Intelligence and Applications
Volume	263
ISSN (Print)	09226389

Conference

Conference	21st European Conference on Artificial Intelligence, ECAI 2014
Country/Territory	Czech Republic
City	Prague
Period	18/08/2014 → 22/08/2014

Access to Document

10.3233/978-1-61499-419-0-669

FAIA263_0669Final published version, 267 KBLicence: CC BY-NC

Cite this

@inbook{bce55023292d4448a6ae440de31875a8,

title = "Pattern-based explanation for automated decisions",

abstract = "Explanations play an essential role in decision support and recommender systems as they are directly associated with the acceptance of those systems and the choices they make. Although approaches have been proposed to explain automated decisions based on multi-attribute decision models, there is a lack of evidence that they produce the explanations users need. In response, in this paper we propose an explanation generation technique, which follows user-derived explanation patterns. It receives as input a multi-attribute decision model, which is used together with user-centric principles to make a decision to which an explanation is generated. The technique includes algorithms that select relevant attributes and produce an explanation that justifies an automated choice. An evaluation with a user study demonstrates the effectiveness of our approach.",

author = "Ingrid Nunes and Simon Miles and Michael Luck and Simone Barbosa and Carlos Lucena",

year = "2014",

doi = "10.3233/978-1-61499-419-0-669",

language = "English",

isbn = "9781614994183",

volume = "263",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOS Press",

pages = "669--674",

booktitle = "Frontiers in Artificial Intelligence and Applications",

note = "21st European Conference on Artificial Intelligence, ECAI 2014 ; Conference date: 18-08-2014 Through 22-08-2014",

}

Nunes, I, Miles, S , Luck, M, Barbosa, S & Lucena, C 2014, Pattern-based explanation for automated decisions. in Frontiers in Artificial Intelligence and Applications. vol. 263, Frontiers in Artificial Intelligence and Applications, vol. 263, IOS Press, pp. 669-674, 21st European Conference on Artificial Intelligence, ECAI 2014, Prague, Czech Republic, 18/08/2014. https://doi.org/10.3233/978-1-61499-419-0-669

TY - CHAP

T1 - Pattern-based explanation for automated decisions

AU - Nunes, Ingrid

AU - Miles, Simon

AU - Luck, Michael

AU - Barbosa, Simone

AU - Lucena, Carlos

PY - 2014

Y1 - 2014

N2 - Explanations play an essential role in decision support and recommender systems as they are directly associated with the acceptance of those systems and the choices they make. Although approaches have been proposed to explain automated decisions based on multi-attribute decision models, there is a lack of evidence that they produce the explanations users need. In response, in this paper we propose an explanation generation technique, which follows user-derived explanation patterns. It receives as input a multi-attribute decision model, which is used together with user-centric principles to make a decision to which an explanation is generated. The technique includes algorithms that select relevant attributes and produce an explanation that justifies an automated choice. An evaluation with a user study demonstrates the effectiveness of our approach.

AB - Explanations play an essential role in decision support and recommender systems as they are directly associated with the acceptance of those systems and the choices they make. Although approaches have been proposed to explain automated decisions based on multi-attribute decision models, there is a lack of evidence that they produce the explanations users need. In response, in this paper we propose an explanation generation technique, which follows user-derived explanation patterns. It receives as input a multi-attribute decision model, which is used together with user-centric principles to make a decision to which an explanation is generated. The technique includes algorithms that select relevant attributes and produce an explanation that justifies an automated choice. An evaluation with a user study demonstrates the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84923163044&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-419-0-669

DO - 10.3233/978-1-61499-419-0-669

M3 - Conference paper

AN - SCOPUS:84923163044

SN - 9781614994183

VL - 263

T3 - Frontiers in Artificial Intelligence and Applications

SP - 669

EP - 674

BT - Frontiers in Artificial Intelligence and Applications

PB - IOS Press

T2 - 21st European Conference on Artificial Intelligence, ECAI 2014

Y2 - 18 August 2014 through 22 August 2014

ER -

Pattern-based explanation for automated decisions

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this