Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency

24Citations
Citations of this article
52Readers
Mendeley users who have this article in their library.

Abstract

Twitter uses machine learning to crop images, where crops are centered around the part predicted to be the most salient. In fall 2020, Twitter users raised concerns that the automated image cropping system on Twitter favored light-skinned over dark-skinned individuals, as well as concerns that the system favored cropping woman's bodies instead of their heads. In order to address these concerns, we conduct an extensive analysis using formalized group fairness metrics. We find systematic disparities in cropping and identify contributing factors, including the fact that the cropping based on the single most salient point can amplify the disparities because of an effect we term argmax bias. However, we demonstrate that formalized fairness metrics and quantitative analysis on their own are insufficient for capturing the risk of representational harm in automatic cropping. We suggest the removal of saliency-based cropping in favor of a solution that better preserves user agency. For developing a new solution that sufficiently address concerns related to representational harm, our critique motivates a combination of quantitative and qualitative methods that include human-centered design.

References Powered by Scopus

Toward understanding women's lived experiences and mental health risks

3697Citations
N/AReaders
Get full text

Learning to predict where humans look

1761Citations
N/AReaders
Get full text

The Chicago face database: A free stimulus set of faces and norming data

1215Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem

71Citations
N/AReaders
Get full text

Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction

60Citations
N/AReaders
Get full text

Can Generative AI improve social science?

36Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Yee, K., Tantipongpipat, U., & Mishra, S. (2021). Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency. Proceedings of the ACM on Human-Computer Interaction, 5(CSCW2). https://doi.org/10.1145/3479594

Readers over time

‘21‘22‘23‘24‘2508162432

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 17

89%

Lecturer / Post doc 1

5%

Researcher 1

5%

Readers' Discipline

Tooltip

Computer Science 9

50%

Social Sciences 5

28%

Business, Management and Accounting 3

17%

Philosophy 1

6%

Article Metrics

Tooltip
Mentions
News Mentions: 1

Save time finding and organizing research with Mendeley

Sign up for free
0