Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation

Jichen Zhu; Antonios Liapis; Sebastian Risi; Rafael Bidarra; G. Michael Youngblood

doi:10.1109/CIG.2018.8490433

Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation

Jichen Zhu, Antonios Liapis, Sebastian Risi, Rafael Bidarra, G. Michael Youngblood

Computer Graphics and Visualisation

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

133 Citations (Scopus)

47 Downloads (Pure)

Abstract

Growing interest in eXplainable Artificial Intelligence (XAI) aims to make AI and machine learning more understandable to human users. However, most existing work focuses on new algorithms, and not on usability, practical interpretability and efficacy on real users. In this vision paper, we propose a new research area of eXplainable AI for Designers (XAID), specifically for game designers. By focusing on a specific user group, their needs and tasks, we propose a human-centered approach for facilitating game designers to co-create with AI/ML techniques through XAID. We illustrate our initial XAID framework through three use cases, which require an understanding both of the innate properties of the AI techniques and users' needs, and we identify key open challenges.

Original language	English
Title of host publication	2018 IEEE Conference on Computational Intelligence and Games ( CIG)
Subtitle of host publication	Proceedings
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	1-8
Number of pages	8
ISBN (Electronic)	978-1-5386-4359-4
ISBN (Print)	978-1-5386-4360-0
DOIs	https://doi.org/10.1109/CIG.2018.8490433
Publication status	Published - 2018
Event	14th IEEE Conference on Computational Intelligence and Games, CIG 2018 - Maastricht, Netherlands Duration: 14 Aug 2018 → 17 Aug 2018

Conference

Conference	14th IEEE Conference on Computational Intelligence and Games, CIG 2018
Country/Territory	Netherlands
City	Maastricht
Period	14/08/18 → 17/08/18

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public

Keywords

Explainable artificial intelligence
Game design
Human-computer interaction
Machine learning
Mixed-initiative co-creation

Access to Document

10.1109/CIG.2018.8490433

08490433Final published version, 710 KB

Cite this

@inproceedings{9277f8c9a07146c791ca4c5849080f91,

title = "Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation",

abstract = "Growing interest in eXplainable Artificial Intelligence (XAI) aims to make AI and machine learning more understandable to human users. However, most existing work focuses on new algorithms, and not on usability, practical interpretability and efficacy on real users. In this vision paper, we propose a new research area of eXplainable AI for Designers (XAID), specifically for game designers. By focusing on a specific user group, their needs and tasks, we propose a human-centered approach for facilitating game designers to co-create with AI/ML techniques through XAID. We illustrate our initial XAID framework through three use cases, which require an understanding both of the innate properties of the AI techniques and users' needs, and we identify key open challenges.",

keywords = "Explainable artificial intelligence, Game design, Human-computer interaction, Machine learning, Mixed-initiative co-creation",

author = "Jichen Zhu and Antonios Liapis and Sebastian Risi and Rafael Bidarra and {Michael Youngblood}, G.",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public; 14th IEEE Conference on Computational Intelligence and Games, CIG 2018 ; Conference date: 14-08-2018 Through 17-08-2018",

year = "2018",

doi = "10.1109/CIG.2018.8490433",

language = "English",

isbn = "978-1-5386-4360-0 ",

pages = "1--8",

booktitle = "2018 IEEE Conference on Computational Intelligence and Games ( CIG)",

publisher = "IEEE",

address = "United States",

}

Zhu, J, Liapis, A, Risi, S, Bidarra, R & Michael Youngblood, G 2018, Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation. in 2018 IEEE Conference on Computational Intelligence and Games ( CIG): Proceedings. IEEE, Piscataway, NJ, pp. 1-8, 14th IEEE Conference on Computational Intelligence and Games, CIG 2018, Maastricht, Netherlands, 14/08/18. https://doi.org/10.1109/CIG.2018.8490433

Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation. / Zhu, Jichen; Liapis, Antonios; Risi, Sebastian et al.
2018 IEEE Conference on Computational Intelligence and Games ( CIG): Proceedings. Piscataway, NJ: IEEE, 2018. p. 1-8.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Explainable AI for Designers

T2 - 14th IEEE Conference on Computational Intelligence and Games, CIG 2018

AU - Zhu, Jichen

AU - Liapis, Antonios

AU - Risi, Sebastian

AU - Bidarra, Rafael

AU - Michael Youngblood, G.

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public

PY - 2018

Y1 - 2018

N2 - Growing interest in eXplainable Artificial Intelligence (XAI) aims to make AI and machine learning more understandable to human users. However, most existing work focuses on new algorithms, and not on usability, practical interpretability and efficacy on real users. In this vision paper, we propose a new research area of eXplainable AI for Designers (XAID), specifically for game designers. By focusing on a specific user group, their needs and tasks, we propose a human-centered approach for facilitating game designers to co-create with AI/ML techniques through XAID. We illustrate our initial XAID framework through three use cases, which require an understanding both of the innate properties of the AI techniques and users' needs, and we identify key open challenges.

AB - Growing interest in eXplainable Artificial Intelligence (XAI) aims to make AI and machine learning more understandable to human users. However, most existing work focuses on new algorithms, and not on usability, practical interpretability and efficacy on real users. In this vision paper, we propose a new research area of eXplainable AI for Designers (XAID), specifically for game designers. By focusing on a specific user group, their needs and tasks, we propose a human-centered approach for facilitating game designers to co-create with AI/ML techniques through XAID. We illustrate our initial XAID framework through three use cases, which require an understanding both of the innate properties of the AI techniques and users' needs, and we identify key open challenges.

KW - Explainable artificial intelligence

KW - Game design

KW - Human-computer interaction

KW - Machine learning

KW - Mixed-initiative co-creation

UR - http://www.scopus.com/inward/record.url?scp=85054998782&partnerID=8YFLogxK

U2 - 10.1109/CIG.2018.8490433

DO - 10.1109/CIG.2018.8490433

M3 - Conference contribution

AN - SCOPUS:85054998782

SN - 978-1-5386-4360-0

SP - 1

EP - 8

BT - 2018 IEEE Conference on Computational Intelligence and Games ( CIG)

PB - IEEE

CY - Piscataway, NJ

Y2 - 14 August 2018 through 17 August 2018

ER -

Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this