research-article

Open access

Explanations as Mechanisms for Supporting Algorithmic Transparency

Authors:

Janghee ChoAuthors Info & Claims

CHI '18: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems

Paper No.: 103, Pages 1 - 13

https://doi.org/10.1145/3173574.3173677

Published: 19 April 2018 Publication History

Abstract

Transparency can empower users to make informed choices about how they use an algorithmic decision-making system and judge its potential consequences. However, transparency is often conceptualized by the outcomes it is intended to bring about, not the specifics of mechanisms to achieve those outcomes. We conducted an online experiment focusing on how different ways of explaining Facebook's News Feed algorithm might affect participants' beliefs and judgments about the News Feed. We found that all explanations caused participants to become more aware of how the system works, and helped them to determine whether the system is biased and if they can control what they see. The explanations were less effective for helping participants evaluate the correctness of the system's output, and form opinions about how sensible and consistent its behavior is. We present implications for the design of transparency mechanisms in algorithmic decision-making systems based on these results.

Supplementary Material

ZIP File (pn1694.nb.html.zip)

The supplemental file presents the experiment manipulation and survey instrument, descriptive statistics about each question, a table of correlations between all of the quantitative variables, and the full output of the regression models.The file is a HTML file and should be viewable in any web browser.

Download
788.06 KB

References

[1]

Mike Ananny and Kate Crawford. 2017. Seeing without knowing: Limitations of the transparency ideal and its application to algorithmic accountability. New Media & Society 33, 4 (2017), 1--17.

[2]

Association for Computing Machinery U.S. Public Policy Council. 2017. Statement on algorithmic transparency and accountability. (2017). https://www.acm.org/binaries/content/assets/publicpolicy/2017_usacm_statement_algorithms.pdf

[3]

Shlomo Berkovsky, Ronnie Taib, and Dan Conway. 2017. How to recommend? User trust factors in movie recommender systems. In International Conference on Intelligent User Interfaces. 287--300.

Digital Library

[4]

Anol Bhattacherjee. 2001. Understanding information systems continuance: An expectation-confirmation model. MIS Quarterly 25, 3 (2001), 351--370.

Digital Library

[5]

Mustafa Bilgic and Raymond J Mooney. 2005. Explaining recommendations: Satisfaction vs. promotion. In Beyond Personalization Workshop, IUI, Vol. 5. 153.

[6]

Engin Bozdag and Jeroen van den Hoven. 2015. Breaking the filter bubble: Democracy and design. Ethics and Information Technology 17, 4 (2015), 249--265.

Digital Library

[7]

Jenna Burrell. 2016. How the machine 'thinks': Understanding opacity in machine learning algorithms. Big Data & Society 3, 1 (2016), 1--12.

[8]

Federal Trade Commission. 2016. Big Data: A tool for inclusion or exclusion? Understanding the issues. (2016). https://www.ftc.gov/system/files/documents/reports/ big-data-tool-inclusion-or-exclusion-understandingissues/160106big-data-rpt.pdf

[9]

Kelley Cotter, Janghee Cho, and Emilee Rader. 2017. Explaining the news feed algorithm: An analysis of the News Feed FYI blog. In Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems. 1553--1560.

Digital Library

[10]

Henriette Cramer, Vanessa Evers, Satyan Ramlal, Maarten van Someren, Lloyd Rutledge, Natalia Stash, Lora Aroyo, and Bob Wielinga. 2008. The effects of transparency on trust in and acceptance of a content-based art recommender. User Modeling and User-Adapted Interaction 18, 5 (2008), 455--496.

Digital Library

[11]

Michael A. DeVito, Darren Gergle, and Jeremy Birnholtz. 2017. "Algorithms ruin everything": #RIPTwitter, Folk Theories, and Resistance to Algorithmic Change in Social Media. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. 3163--3174.

Digital Library

[12]

Nicholas Diakopoulos. 2016. Accountability in algorithmic decision making. Commun. ACM 59, 2 (2016), 56--62.

Digital Library

[13]

Nicholas Diakopoulos. 2017. Enabling Accountability of Algorithmic Media: Transparency as a Constructive and Critical Lens. In Transparent Data Mining for Big and Small Data, Tania Cerquitelli, Daniele Quercia, and Frank Pasquale (Eds.). Vol. 32. Springer International Publishing, Cham, Switzerland, 25--43.

[14]

Nicholas Diakopoulos and Michael Koliska. 2016. Algorithmic transparency in the news media. Digital Journalism 5, 7 (2016), 809--828.

[15]

Nicole B. Ellison, Charles Steinfield, and Cliff Lampe. 2007. The benefits of Facebook "friends:" Social capital and college students' use of online social network sites. Journal of Computer-Mediated Communication 12, 4 (2007), 1143--1168.

[16]

Motahhare Eslami, Aimee Rickman, Kristen Vaccaro, Amirhossein Aleyasen, Andy Vuong, Karrie Karahalios, Kevin Hamilton, and Christian Sandvig. 2015. I always assumed that I wasn't really that close to {her}": Reasoning about invisible algorithms in News Feeds. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. 153--162.

Digital Library

[17]

Motahhare Eslami, Kristen Vaccaro, Karrie Karahalios, and Kevin Hamilton. 2017. Be careful; things can be worse than they appear": Understanding biased algorithms and users' behavior around them in rating platforms. In The International AAAI Conference on Web and Social Media. 62--71.

[18]

Kenneth R. Fleischmann and William A. Wallace. 2005. A covenant with transparency: Opening the black box of models. Commun. ACM 48, 5 (2005), 93--97.

Digital Library

[19]

Mikkel Flyverbom. 2016. Transparency: Mediation and the Management of Visibilities. International Journal of Communication 10 (2016), 1--13.

[20]

Gerhard Friedrich and Markus Zanker. 2011. A taxonomy for generating explanations in recommender systems. AI Magazine 32, 3 (2011), 90--98.

Digital Library

[21]

Fatih Gedikli, Dietmar Jannach, and Mouzhi Ge. 2014. How should I explain? A comparison of different explanation types for recommender systems. International Journal of Human-Computer Studies 72, 4 (2014), 367--382.

Digital Library

[22]

Justin Scott Giboney, Susan A. Brown, Paul Benjamin Lowry, and Jay F. Nunamaker. 2015. User acceptance of knowledge-based system recommendations: Explanations, arguments, and fit. Decision Support Systems 72 (2015), 1--10.

Digital Library

[23]

Tarleton Gillespie. 2014. The relevance of algorithms. In Media Technologies: Essays on Communication, Materiality, and Society, Tarleton Gillespie, Pablo J. Boczkowski, and Kirsten A. Foot (Eds.). The MIT Press, Cambridge, Mass., 167--194.

[24]

Shirley Gregor and Izak Benbasat. 1999. Explanations from intelligent systems: Theoretical foundations and implications for practice. 23, 4 (1999), 497--530.

Digital Library

[25]

Eszter Hargittai and Yuli Patrick Hsieh. 2011. Succinct survey measures of web-use skills. Social Science Computer Review 30, 1 (2011), 95--107.

Digital Library

[26]

Bernie Hogan. 2015. From invisible algorithms to interactive affordances: Data after the ideology of machine learning. In Roles, Trust, and Reputation in Social Media Knowledge Markets: Theory and Methods, Elisa Bertino and Sorin Adam Matei (Eds.). Springer International Publishing, 103--117.

[27]

Lucas D. Introna. 2016. Algorithms, Governance, and Governmentality: On Governing Academic Writing. Science, Technology, & Human Values 41, 1 (2016), 17--49.

[28]

Dietmar Jannach, Paul Resnick, Alexander Tuzhilin, and Markus Zanker. 2016. Recommender systems: Beyond matrix completion. Commun. ACM 59, 11 (2016), 94--102.

Digital Library

[29]

Joseph A Konstan and John Riedl. 2012. Recommender systems: from algorithms to user experience. User Modeling and User-Adapted Interaction 22, 1--2 (2012), 101--123.

Digital Library

[30]

Joshua A. Kroll, Joanna Huey, Solon Barocas, Edward W. Felten, Joel R. Reidenberg, David G. Robinson, and Harlan Yu. 2016. Accountable algorithms. University of Pennsylvania Law Review 165, 3 (2016).

[31]

Todd Kulesza, Simone Stumpf, Margaret Burnett, Sherry Yang, Irwin Kwan, and Weng-Keen Wong. 2013. Too much, too little, or just right? Ways explanations impact end users' mental models. In 2013 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC). IEEE, 3--10.

[32]

Min Kyung Lee, Daniel Kusbit, Evan Metsky, and Laura Dabbish. 2015. Working with machines: The impact of algorithmic and data-driven management on human workers. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. 1603--1612.

Digital Library

[33]

Xin Li, Traci J Hess, and Joseph S Valacich. 2008. Why do we trust new technology? A study of initial trust formation with organizational information systems. The Journal of Strategic Information Systems 17, 1 (2008), 39--71.

Digital Library

[34]

Brian Y. Lim and Anind K. Dey. 2009. Assessing demand for intelligibility in context-aware applications. In Proceedings of the 11th International Conference on Ubiquitous Computing. 195--204.

Digital Library

[35]

Zachary C Lipton. 2016. The mythos of model interpretability. In 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016). 96--100.

[36]

Claudia Marino, Livio Finos, Alessio Vieno, Michela Lenzi, and Marcantonio M. Spada. 2017. Objective Facebook behaviour: Differences between problematic and non-problematic users. Computers in Human Behavior 73 (2017), 541--546.

Digital Library

[37]

Joseph E. Mercado, Michael A. Rupp, Jessie Y. C. Chen, Michael J. Barnes, Daniel Barber, and Katelyn Procci. 2016. Intelligent agent transparency in human-agent teaming for multi-UxV management. Human Factors: The Journal of the Human Factors and Ergonomics Society 58, 3 (2016), 401--415.

[38]

Brent Mittelstadt. 2016. Automation, algorithms, and politics: Auditing for transparency in content personalization systems. International Journal of Communication 10 (2016), 4991--5002.

[39]

Sayooran Nagulendra and Julita Vassileva. 2016. Providing awareness, explanation and control of personalized filtering in a social networking site. Information Systems Frontiers 18, 1 (2016), 145--158.

Digital Library

[40]

Kenya Freeman Oduor and Eric N. Wiebe. 2008. The effects of automated decision algorithm modality and transparency on reported trust and task performance. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 52, 4 (2008), 302--306.

[41]

Julian A. Oldmeadow, Sally Quinn, and Rachel Kowert. 2013. Attachment style, social skills, and Facebook use amongst adults. Computers in Human Behavior 29, 3 (2013), 1142--1149.

Digital Library

[42]

Alexis Papadimitriou, Panagiotis Symeonidis, and Yannis Manolopoulos. 2012. A generalized taxonomy of explanations styles for traditional and social recommender systems. Data Mining and Knowledge Discovery 24, 3 (2012), 555--583.

Digital Library

[43]

Frank Pasquale. 2015. The black box society: the secret algorithms that control money and information. Harvard University Press, Cambridge, MA.

[44]

John D. Podesta, Penny Pritzker, Ernest J. Moniz, John P. Holdren, and Jeffrey D. Zients. 2014. Big data: Seizing opportunities, preserving values. (2014). https://obamawhitehouse.archives.gov/sites/default/ files/docs/big_data_privacy_report_may_1_2014.pdf

[45]

Emilee Rader. 2017. Examining user surprise as a symptom of algorithmic filtering. International Journal of Human Computer Studies 98 (2017), 72--88.

Digital Library

[46]

Emilee Rader and Rebecca Gray. 2015. Understanding user beliefs about algorithmic curation in the Facebook News Feed. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 173--182.

Digital Library

[47]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. "Why should I trust you?" Explaining the Predictions of Any Classifier. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1135--1144.

Digital Library

[48]

Christian Sandvig, Kevin Hamilton, Karrie Karahalios, and Cedric Langbort. 2014. Auditing algorithms: Research methods for detecting discrimination on internet platforms. Data and discrimination: converting critical concerns into productive inquiry (2014).

[49]

Rashmi Sinha and Kirsten Swearingen. 2002. The role of transparency in recommender systems. In Proceedings of the 2002 CHI Conference Extended Abstracts on Human Factors in Computing Systems. 830--831.

Digital Library

[50]

Nava Tintarev and Judith Masthoff. 2007. A survey of explanations in recommender systems. In Proceedings of the 2007 IEEE 23rd International Conference on Data Engineering Workshop. 801--810.

Digital Library

[51]

Nava Tintarev and Judith Masthoff. 2011. Designing and Evaluating Explanations for Recommender Systems. In Recommender Systems Handbook, Francesco Ricci, Lior Rokach, Bracha Shapira, and Paul B. Kantor (Eds.). Springer-Verlag, New York, New York, 479--510.

[52]

Nava Tintarev and Judith Masthoff. 2012. Evaluating the effectiveness of explanations for recommender systems. User Modeling and User-Adapted Interaction 22, 4--5 (2012), 399--439.

Digital Library

[53]

Viswanath Venkatesh, James Y. L. Thong, Frank K. Y. Chan, Paul Jen-Hwa Hu, and Susan A. Brown. 2011. Extending the two-stage information systems continuance model: incorporating UTAUT predictors and the role of context. Information Systems Journal 21, 6 (2011), 527--555.

[54]

Weiquan Wang and Izak Benbasat. 2007. Recommendation agents for electronic commerce: Effects of explanation facilities on trusting beliefs. Journal of Management Information Systems 23, 4 (2007), 217--246.

Digital Library

[55]

Markus Zanker and Daniel Ninaus. 2010. Knowledgeable explanations for recommender systems. In Proceedings of the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Vol. 1. 657--660.

Digital Library

[56]

Tal Zarsky. 2016. The trouble with algorithmic decisions: An analytic road map to examine efficiency and fairness in automated and opaque decision making. Science, Technology, & Human Values 41, 1 (2016), 118--132.

Cited By

Panda RMishra AMohanty A(2024)Innovating RealityThe Pioneering Applications of Generative AI10.4018/979-8-3693-3278-8.ch004(85-105)Online publication date: 28-Jun-2024
https://doi.org/10.4018/979-8-3693-3278-8.ch004
Doyle CAlvarez-Garcia MTracey PGrill GWhitney CChambers L(2024)Reparations of the horse? Algorithmic reparation and overspecialized remediesBig Data & Society10.1177/2053951724127067011:3Online publication date: 24-Sep-2024
https://doi.org/10.1177/20539517241270670
Wang ROphir Y(2024)Behind the black box: The moderating role of the machine heuristic on the effect of transparency information about automated journalism on hostile media bias perceptionJournalism10.1177/14648849241284575Online publication date: 13-Sep-2024
https://doi.org/10.1177/14648849241284575
Show More Cited By

Index Terms

Explanations as Mechanisms for Supporting Algorithmic Transparency
1. Human-centered computing

Recommendations

Are explanations always important?: a study of deployed, low-cost intelligent interactive systems
IUI '12: Proceedings of the 2012 ACM international conference on Intelligent User Interfaces

Intelligent interactive systems (IIS) have great potential to improve users' experience with technology by tailoring their behaviour and appearance to users' individual needs; however, these systems, with their complex algorithms and dynamic behaviour, ...
Using Theory of Mind in Explanations for Fostering Transparency in Human-Robot Interaction
Social Robotics
Abstract
In human-robot interaction, addressing disparities in action perception is vital for fostering effective collaboration. Our study delves into the integration of explanatory mechanisms during robotic actions, focusing on aligning robot perspectives ...
Impact of Explanations on Transparency in HRI: A Study Using the HRIVST Metric
Social Robotics
Abstract
This paper presents an exploration of the role of explanations provided by robots in enhancing transparency during human-robot interaction (HRI). We conducted a study with 85 participants to investigate the impact of different types and timings of ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

CHI '18: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems

April 2018

8489 pages

ISBN:9781450356206

DOI:10.1145/3173574

General Chairs:
Regan Mandryk
University of Saskatchewan, Canada
,
Mark Hancock
University of Waterloo, Canada
,
Program Chairs:
Mark Perry
Brunel University London, UK
,
Anna Cox
University College London, UK

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part 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 components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGCHI: ACM Special Interest Group on Computer-Human Interaction

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 April 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

National Science Foundation

Conference

CHI '18

Sponsor:

SIGCHI

CHI '18: CHI Conference on Human Factors in Computing Systems

April 21 - 26, 2018

Montreal QC, Canada

Acceptance Rates

CHI '18 Paper Acceptance Rate 666 of 2,590 submissions, 26%;

Overall Acceptance Rate 6,199 of 26,314 submissions, 24%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

181
Total Citations
View Citations
6,280
Total Downloads

Downloads (Last 12 months)1,169
Downloads (Last 6 weeks)136

Reflects downloads up to 21 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Panda RMishra AMohanty A(2024)Innovating RealityThe Pioneering Applications of Generative AI10.4018/979-8-3693-3278-8.ch004(85-105)Online publication date: 28-Jun-2024
https://doi.org/10.4018/979-8-3693-3278-8.ch004
Doyle CAlvarez-Garcia MTracey PGrill GWhitney CChambers L(2024)Reparations of the horse? Algorithmic reparation and overspecialized remediesBig Data & Society10.1177/2053951724127067011:3Online publication date: 24-Sep-2024
https://doi.org/10.1177/20539517241270670
Wang ROphir Y(2024)Behind the black box: The moderating role of the machine heuristic on the effect of transparency information about automated journalism on hostile media bias perceptionJournalism10.1177/14648849241284575Online publication date: 13-Sep-2024
https://doi.org/10.1177/14648849241284575
Wang SHuang G(2024)The Impact of Machine Authorship on News Audience Perceptions: A Meta-Analysis of Experimental StudiesCommunication Research10.1177/00936502241229794Online publication date: 14-Feb-2024
https://doi.org/10.1177/00936502241229794
Zhang ZTsiakas KSchneegass C(2024)Explaining the Wait: How Justifying Chatbot Response Delays Impact User TrustProceedings of the 6th ACM Conference on Conversational User Interfaces10.1145/3640794.3665550(1-16)Online publication date: 8-Jul-2024
https://dl.acm.org/doi/10.1145/3640794.3665550
Goyal NBaumler CNguyen TDaumé III H(2024)The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy FeaturesProceedings of the 29th International Conference on Intelligent User Interfaces10.1145/3640543.3645210(155-180)Online publication date: 18-Mar-2024
https://dl.acm.org/doi/10.1145/3640543.3645210
Gunturi UKumar ADing XRho E(2024)Linguistically Differentiating Acts and Recalls of Racial Microaggressions on Social MediaProceedings of the ACM on Human-Computer Interaction10.1145/36373668:CSCW1(1-36)Online publication date: 26-Apr-2024
https://dl.acm.org/doi/10.1145/3637366
Franzen DMüller-Birn CWegwarth O(2024)Communicating the Privacy-Utility Trade-off: Supporting Informed Data Donation with Privacy Decision Interfaces for Differential PrivacyProceedings of the ACM on Human-Computer Interaction10.1145/36373098:CSCW1(1-56)Online publication date: 26-Apr-2024
https://dl.acm.org/doi/10.1145/3637309
Figueiredo MAnkrah EPowell JEpstein DChen Y(2024)Powered by AIProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36314147:4(1-24)Online publication date: 12-Jan-2024
https://dl.acm.org/doi/10.1145/3631414
Deck LSchoeffer JDe-Arteaga MKühl N(2024)A Critical Survey on Fairness Benefits of Explainable AIProceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency10.1145/3630106.3658990(1579-1595)Online publication date: 3-Jun-2024
https://dl.acm.org/doi/10.1145/3630106.3658990
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

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

Media

Figures

Other

Tables

View Table of Contents