abstract

Getting Playful with Explainable AI: Games with a Purpose to Improve Human Understanding of AI

Authors:

Laura Beth Fulton,

Jessica Hammer,

Adam PererAuthors Info & Claims

CHI EA '20: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

Pages 1 - 8

https://doi.org/10.1145/3334480.3382831

Published: 25 April 2020 Publication History

Abstract

Explainable Artificial Intelligence (XAI) is an emerging topic in Machine Learning (ML) that aims to give humans visibility into how AI systems make decisions. XAI is increasingly important in bringing transparency to fields such as medicine and criminal justice where AI informs high consequence decisions. While many XAI techniques have been proposed, few have been evaluated beyond anecdotal evidence. Our research offers a novel approach to assess how humans interpret AI explanations; we explore this by integrating XAI with Games with a Purpose (GWAP). XAI requires human evaluation at scale, and GWAP can be used for XAI tasks which are presented through rounds of play. This paper outlines the benefits of GWAP for XAI, and demonstrates application through our creation of a multi-player GWAP that focuses on explaining deep learning models trained for image recognition. Through our game, we seek to understand how humans select and interpret explanations used in image recognition systems, and bring empirical evidence on the validity of GWAP designs for XAI.

References

[1]

Abdul and et al. 2018. Trends and trajectories for explainable, accountable and intelligible systems. Proceedings of the CHI Conference on Human Factors in Computing Systems (2018), 582.

[2]

Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, and et. al. 2018. Sanity checks for saliency maps. (2018).

[3]

Luis Von Ahn and Laura Dabbish. 2008. Designing games with a purpose. Commun. ACM 51, 8 (2008), 58--67.

Digital Library

[4]

Greg Costikyan. 2013. Uncertainty in Games. MIT Press, Cambridge, MA.

Digital Library

[5]

Vickie Curtis. 2015. Motivation to participate in an online citizen science game: A study of foldit. Science Communications 37, 6 (2015), 723--746.

[6]

Doshi-Velez and Kim. 2017. Towards A Rigorous Science of Interpretable Machine Learning. (2017).

[7]

Marta Sabou et al. 2014. Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines. (2014).

[8]

David Gundry and et al. 2018. Intrinsic elicitation: A model and design approach for games collecting human subject data. "International Conference on the Foundations of Digital Games" (2018), 38.

[9]

Fred Hohman, Minsuk Kahng, Robert Pienta, and Duen Horng Chau. 2018. Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers. (2018).

[10]

Andreas Holzinger, Chris Biemann, Constantinos S. Pattichis, and Douglas B. Kell. 2017. What do we need to build explainable AI systems for the medical domain? (2017).

[11]

Matthew Kay and et al. 2016. When (Ish) is My Bus?: User-centered Visualizations of Uncertainty in Everyday, Mobile Predictive Systems. In CHI Conference on Human Factors in Computing Systems.

[12]

Josua Krause, Adam Perer, and Kenney Ng. 2016. Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models. In 2016 CHI Conference on Human Factors in Computing Systems.

Digital Library

[13]

Edith L. M. Law, Luis Von Ahn, Roger B. Dannenberg, and Mike Crawford. 2007. Tagatune: A game for music and sound annotation. (2007).

[14]

Tania Lombrozo. 2006. The structure and function of explanations. Trends in Cognitive Science (2006).

[15]

Tania Lombrozo. 2009. Explanation and categorization: How "why?" informs "what?". Cognition (2009).

[16]

Chris Madge and et al. 2017. Experiment-Driven Development of a GWAP for Marking Segments in Text.

[17]

Tim Miller. 2017. Explanation in Artificial Intelligence: Insights from the Social Sciences. (2017).

[18]

Chris Olah, Alexander Mordvintsev, and Ludwig Schubert. 2017. Feature Visualization. Distill (2017).

[19]

Ei Pa Pa Pe-Than, Dion Hoe-Lian Goh, and Chei Sian Lee. 2015. A typology of human computation games: An analysis and a review of current games. Behaviour Information Technology 34 (2015), 809--824.

Digital Library

[20]

Ei Pa Pa Pe-Than, Dion Hoe-Lian Goh, and Chei Sian Lee. 2017. Does It Matter How You Play? The Effects of Collaboration and Competition Among Players of Human Computation Games. (2017).

[21]

Mark A Runco. 2010. Divergent thinking, creativity, and ideation. The Cambridge handbook of creativity 413 (2010). Issue 446.

[22]

Michael Saler, Jan Ulrich, Hense, Sarah Katharina Mayr, and et. al. 2017. How gamification motivates: An experimental study of the effects of specific game design elements on psychological need satisfaction. Computers in Human Behavior 69 (2017), 371--380.

Digital Library

[23]

Nitin Seemakurty, Jonathan Chu, Luis von Ahn, and Anthony Tomasic. 2010. Word Sense Disambiguation via Human Computation. In ACM SIGKDD Workshop on Human Computation (HCOMP '10).

Digital Library

[24]

Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2013. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. (2013).

[25]

Kristin Siu and Mark O. Riedl. 2016. Reward Systems in Human Computation Games. In Proceedings of the 2016 Annual Symposium on Computer-Human Interaction in Play (CHI PLAY '16).

[26]

Kristin Siu, Alexander Zook, and Mark O. Riedl. 2017. A Framework for Exploring and Evaluating Mechanics in Human Computation Games. In International Conference on the Foundations of Digital Games.

[27]

Simone Stumpf and et al. 2009. Interacting meaningfully with machine learning systems: Three experiments. Int. J. Hum.-Comput. Stud. 67 (2009), 639--662.

Digital Library

[28]

Alexandra To, Jarrek Holmes, Elaine Fath, Eda Zhang, Geoff Kaufman, and Jessica Hammer. 2017. Modeling and Designing for Key Elements of Curiosity: Risking Failure, Valuing Questions. Digital Games Research Association (2017).

[29]

Miaomiao Wen and et al. 2016. Transactivity as a predictor of future collaborative knowledge integration in team-based learning in online courses. International Educational Data Mining Society (2016).

[30]

Miaomiao Wen, Keith Maki, Xu Wang, Steven P Dow, James Herbsleb, and et. al. 2019. Exploring Neural Networks with Activation Atlases. (2019).

[31]

J. Wexler, M. Pushkarna, T. Bolukbasi, M. Wattenberg, F. Viégas, and J. Wilson. 2020. The What-If Tool: Interactive Probing of Machine Learning Models. IEEE Transactions on Visualization and Computer Graphics 26, 1 (2020), 56--65.

[32]

Jichen Zhu, Antonios Liapis, Sebastian Risi, Rafael Bidarra, and G Michael Youngblood. 2018. Explainable AI for designers: A human-centered perspective on mixed-initiative co-creation. IEEE, 1--8.

Cited By

Wani AJoshi ISingh P(2024)Navigating the Job-Seeking Journey: Challenges and Opportunities for Digital Employment Support in KashmirProceedings of the ACM on Human-Computer Interaction10.1145/36373758:CSCW1(1-28)Online publication date: 26-Apr-2024
https://dl.acm.org/doi/10.1145/3637375
Singh AShrivastava RSrivastava A(2024) Efficient and Compressed Deep Learning Model for Brain Tumour Classification With Explainable AI for Smart Healthcare and Information Communication Systems Expert Systems10.1111/exsy.1377042:2Online publication date: 27-Oct-2024
https://doi.org/10.1111/exsy.13770
Khalifa FAbdelkader HElsaid A(2024)An analysis of ensemble pruning methods under the explanation of Random ForestInformation Systems10.1016/j.is.2023.102310120:COnline publication date: 4-Mar-2024
https://dl.acm.org/doi/10.1016/j.is.2023.102310
Show More Cited By

Index Terms

Getting Playful with Explainable AI: Games with a Purpose to Improve Human Understanding of AI
1. Applied computing
  1. Computers in other domains
    1. Personal computers and PC applications
      1. Computer games
2. Human-centered computing

Recommendations

Introduction to Explainable AI
CHI EA '21: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems

As Artificial Intelligence technologies are increasingly used to make important decisions and perform autonomous tasks, providing explanations to allow users and stakeholders to understand the AI has become a ubiquitous concern. Recently, a number of ...
Eye into AI: Evaluating the Interpretability of Explainable AI Techniques through a Game with a Purpose
CSCW

Recent developments in explainable AI (XAI) aim to improve the transparency of black-box models. However, empirically evaluating the interpretability of these XAI techniques is still an open challenge. The most common evaluation method is algorithmic ...
Explainable AI and Interpretable Machine Learning: A Case Study in Perspective
Abstract
Explainable AI, as the word implies is a type of artificial intelligence which enables the explanation of learning models and focuses on why the system arrived at a particular decision, exploring its logical paradigms, contrary to the inherent ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

CHI EA '20: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

April 2020

4474 pages

ISBN:9781450368193

DOI:10.1145/3334480

General Chairs:
Regina Bernhaupt
Eindhoven University of Technology, Netherlands
,
Florian 'Floyd' Mueller
Monash University, Australia
,
David Verweij
Newcastle University, UK
,
Josh Andres
RMIT, Australia
,
Program Chairs:
Joanna McGrenere
University of British Columbia, Canada
,
Andy Cockburn
University of Canterbury, New Zealand
,
Ignacio Avellino
University of Maryland Baltimore County, USA
,
Alix Goguey
Grenoble Alpes University, France
,
Pernille Bjørn
University of Copenhagen, Denmark
,
Shengdong (Shen) Zhao
National University of Singapore, Singapore
,
Briane Paul Samson
Future University Hakodate, Japan & De La Salle University, Philippines
,
Rafal Kocielnik
University of Washington, USA

Copyright © 2020 Owner/Author.

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Sponsors

SIGCHI: ACM Special Interest Group on Computer-Human Interaction

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 April 2020

Check for updates

Author Tags

Qualifiers

Abstract

Conference

CHI '20

Sponsor:

SIGCHI

CHI '20: CHI Conference on Human Factors in Computing Systems

April 25 - 30, 2020

HI, Honolulu, USA

Acceptance Rates

Overall Acceptance Rate 6,164 of 23,696 submissions, 26%

Upcoming Conference

CHI 2025

Sponsor:
sigchi

ACM CHI Conference on Human Factors in Computing Systems

April 26 - May 1, 2025

Yokohama , Japan

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
1,030
Total Downloads

Downloads (Last 12 months)143
Downloads (Last 6 weeks)16

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wani AJoshi ISingh P(2024)Navigating the Job-Seeking Journey: Challenges and Opportunities for Digital Employment Support in KashmirProceedings of the ACM on Human-Computer Interaction10.1145/36373758:CSCW1(1-28)Online publication date: 26-Apr-2024
https://dl.acm.org/doi/10.1145/3637375
Singh AShrivastava RSrivastava A(2024) Efficient and Compressed Deep Learning Model for Brain Tumour Classification With Explainable AI for Smart Healthcare and Information Communication Systems Expert Systems10.1111/exsy.1377042:2Online publication date: 27-Oct-2024
https://doi.org/10.1111/exsy.13770
Khalifa FAbdelkader HElsaid A(2024)An analysis of ensemble pruning methods under the explanation of Random ForestInformation Systems10.1016/j.is.2023.102310120:COnline publication date: 4-Mar-2024
https://dl.acm.org/doi/10.1016/j.is.2023.102310
Bijlani V(2023)Sustainable Cities With GamificationIntersecting Health, Livability, and Human Behavior in Urban Environments10.4018/978-1-6684-6924-8.ch010(205-226)Online publication date: 3-May-2023
https://doi.org/10.4018/978-1-6684-6924-8.ch010
Morrison KJain MHammer JPerer A(2023)Eye into AI: Evaluating the Interpretability of Explainable AI Techniques through a Game with a PurposeProceedings of the ACM on Human-Computer Interaction10.1145/36100647:CSCW2(1-22)Online publication date: 4-Oct-2023
https://dl.acm.org/doi/10.1145/3610064
Atf ZLewis P(2023)Human Centricity in the Relationship Between Explainability and Trust in AIIEEE Technology and Society Magazine10.1109/MTS.2023.334023842:4(66-76)Online publication date: Dec-2023
https://doi.org/10.1109/MTS.2023.3340238
Viswan VShaffi NMahmud MSubramanian KHajamohideen F(2023)Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic ReviewCognitive Computation10.1007/s12559-023-10192-x16:1(1-44)Online publication date: 13-Nov-2023
https://doi.org/10.1007/s12559-023-10192-x
Tocchetti ABrambilla M(2022)The Role of Human Knowledge in Explainable AIData10.3390/data70700937:7(93)Online publication date: 6-Jul-2022
https://doi.org/10.3390/data7070093
Mohanrajan SLoganathan A(2022)Novel Vision Transformer–Based Bi-LSTM Model for LU/LC Prediction—Javadi Hills, IndiaApplied Sciences10.3390/app1213638712:13(6387)Online publication date: 23-Jun-2022
https://doi.org/10.3390/app12136387
Druga SChristoph FKo A(2022)Family as a Third Space for AI Literacies: How do children and parents learn about AI together?Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems10.1145/3491102.3502031(1-17)Online publication date: 29-Apr-2022
https://dl.acm.org/doi/10.1145/3491102.3502031
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten