Tangible Explainable AI - an Initial Conceptual Framework

Ashley Colley; Kaisa Väänänen; Jonna Häkkilä

doi:10.1145/3568444.3568456

Tangible Explainable AI - an Initial Conceptual Framework

Ashley Colley, Kaisa Väänänen, Jonna Häkkilä

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

10 Citations (Scopus)

329 Downloads (Pure)

Abstract

Artificial Intelligence (AI) solutions are becoming prevalent in almost all aspects of human life. However, their acceptance may be limited by a lack of transparency of how the AI works. Explainable AI (XAI) aims to provide the users of AI systems with an understanding of why decisions are made, increasing trust in the system. To date, research into XAI has focused on the use of graphical user interfaces, presenting numerical, textual or graphical explanations. However, AI is increasingly being used in systems that include physical devices, and hence the need for explainability in physical or tangible user interfaces (TUI) is also increasing. We present an initial conceptual framework for tangible explainable AI (TangXAI), which identifies the potential approaches of communicating XAI through physical artifacts, using the concepts of data physicalization and tangible interaction. The framework provides a basis into which ongoing research of tangible explainable AI can be mapped and related research gaps identified.

Original language	English
Title of host publication	Proceedings of MUM 2022
Subtitle of host publication	the 21st International Conference on Mobile and Ubiquitous Multimedia
Editors	Tanja Döring, Susanne Boll, Ashley Colley, Augusto Esteves, João Guerreiro
Place of Publication	New York, NY, USA
Publisher	ACM
Pages	22-27
ISBN (Electronic)	978-1-4503-9821-3
DOIs	https://doi.org/10.1145/3568444.3568456
Publication status	Published - 2022
MoEC publication type	A4 Article in a conference publication
Event	MUM 2022: 21th International Conference on Mobile and Ubiquitous Multimedia - Lisbon , Portugal Duration: 27 Nov 2022 → 30 Nov 2022

Publication series

Series	MUM '22

Conference

Conference	MUM 2022: 21th International Conference on Mobile and Ubiquitous Multimedia
Abbreviated title	MUM 2022
Country/Territory	Portugal
City	Lisbon
Period	27.11.2022 → 30.11.2022

Keywords

TangXAI
XAI
human centered AI
human in the loop
HCI
Explainable AI
tangible interaction
TUI

Field of science

Computer and information sciences

Access to research output

10.1145/3568444.3568456Licence: CC BY

3568444.3568456Final published version, 1.51 MBLicence: CC BY

Citation for this output

@inproceedings{edb4203fdd614002bc7a7350a83155b5,

title = "Tangible Explainable AI - an Initial Conceptual Framework",

abstract = "Artificial Intelligence (AI) solutions are becoming prevalent in almost all aspects of human life. However, their acceptance may be limited by a lack of transparency of how the AI works. Explainable AI (XAI) aims to provide the users of AI systems with an understanding of why decisions are made, increasing trust in the system. To date, research into XAI has focused on the use of graphical user interfaces, presenting numerical, textual or graphical explanations. However, AI is increasingly being used in systems that include physical devices, and hence the need for explainability in physical or tangible user interfaces (TUI) is also increasing. We present an initial conceptual framework for tangible explainable AI (TangXAI), which identifies the potential approaches of communicating XAI through physical artifacts, using the concepts of data physicalization and tangible interaction. The framework provides a basis into which ongoing research of tangible explainable AI can be mapped and related research gaps identified.",

keywords = "TangXAI, XAI, human centered AI, human in the loop, HCI, Explainable AI, tangible interaction, TUI",

author = "Ashley Colley and Kaisa V{\"a}{\"a}n{\"a}nen and Jonna H{\"a}kkil{\"a}",

year = "2022",

doi = "10.1145/3568444.3568456",

language = "English",

series = "MUM '22",

pages = "22--27",

editor = "Tanja D{\"o}ring and Susanne Boll and Ashley Colley and Augusto Esteves and {Guerreiro }, Jo{\~a}o",

booktitle = "Proceedings of MUM 2022",

publisher = "ACM ",

address = "Australia",

note = "MUM 2022: 21th International Conference on Mobile and Ubiquitous Multimedia, MUM 2022 ; Conference date: 27-11-2022 Through 30-11-2022",

}

Colley, A, Väänänen, K & Häkkilä, J 2022, Tangible Explainable AI - an Initial Conceptual Framework. in T Döring, S Boll, A Colley, A Esteves & J Guerreiro (eds), Proceedings of MUM 2022: the 21st International Conference on Mobile and Ubiquitous Multimedia. ACM , New York, NY, USA, MUM '22, pp. 22-27, MUM 2022: 21th International Conference on Mobile and Ubiquitous Multimedia, Lisbon , Portugal, 27.11.2022. https://doi.org/10.1145/3568444.3568456

Tangible Explainable AI - an Initial Conceptual Framework. / Colley, Ashley; Väänänen, Kaisa; Häkkilä, Jonna.
Proceedings of MUM 2022: the 21st International Conference on Mobile and Ubiquitous Multimedia. ed. / Tanja Döring; Susanne Boll; Ashley Colley; Augusto Esteves; João Guerreiro . New York, NY, USA: ACM , 2022. p. 22-27 (MUM '22).

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

TY - GEN

T1 - Tangible Explainable AI - an Initial Conceptual Framework

AU - Colley, Ashley

AU - Väänänen, Kaisa

AU - Häkkilä, Jonna

PY - 2022

Y1 - 2022

N2 - Artificial Intelligence (AI) solutions are becoming prevalent in almost all aspects of human life. However, their acceptance may be limited by a lack of transparency of how the AI works. Explainable AI (XAI) aims to provide the users of AI systems with an understanding of why decisions are made, increasing trust in the system. To date, research into XAI has focused on the use of graphical user interfaces, presenting numerical, textual or graphical explanations. However, AI is increasingly being used in systems that include physical devices, and hence the need for explainability in physical or tangible user interfaces (TUI) is also increasing. We present an initial conceptual framework for tangible explainable AI (TangXAI), which identifies the potential approaches of communicating XAI through physical artifacts, using the concepts of data physicalization and tangible interaction. The framework provides a basis into which ongoing research of tangible explainable AI can be mapped and related research gaps identified.

AB - Artificial Intelligence (AI) solutions are becoming prevalent in almost all aspects of human life. However, their acceptance may be limited by a lack of transparency of how the AI works. Explainable AI (XAI) aims to provide the users of AI systems with an understanding of why decisions are made, increasing trust in the system. To date, research into XAI has focused on the use of graphical user interfaces, presenting numerical, textual or graphical explanations. However, AI is increasingly being used in systems that include physical devices, and hence the need for explainability in physical or tangible user interfaces (TUI) is also increasing. We present an initial conceptual framework for tangible explainable AI (TangXAI), which identifies the potential approaches of communicating XAI through physical artifacts, using the concepts of data physicalization and tangible interaction. The framework provides a basis into which ongoing research of tangible explainable AI can be mapped and related research gaps identified.

KW - TangXAI

KW - XAI

KW - human centered AI

KW - human in the loop

KW - HCI

KW - Explainable AI

KW - tangible interaction

KW - TUI

UR - http://www.scopus.com/inward/record.url?scp=85145877834&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85145877834&partnerID=8YFLogxK

U2 - 10.1145/3568444.3568456

DO - 10.1145/3568444.3568456

M3 - Conference contribution

T3 - MUM '22

SP - 22

EP - 27

BT - Proceedings of MUM 2022

A2 - Döring, Tanja

A2 - Boll, Susanne

A2 - Colley, Ashley

A2 - Esteves, Augusto

A2 - Guerreiro , João

PB - ACM

CY - New York, NY, USA

T2 - MUM 2022: 21th International Conference on Mobile and Ubiquitous Multimedia

Y2 - 27 November 2022 through 30 November 2022

ER -

Tangible Explainable AI - an Initial Conceptual Framework

Abstract

Publication series

Conference

Keywords

Field of science

Access to research output

Other files and links

Fingerprint

Lapland Robotics

Citation for this output

Tangible Explainable AI - an Initial Conceptual Framework

Abstract

Publication series

Conference

Keywords

Field of science

Access to research output

Other files and links

Fingerprint

Projects

Lapland Robotics

Citation for this output