Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency
This work addresses fairness and representational harm in social media algorithms for users affected by biased cropping, though it is incremental as it critiques existing methods without proposing a new technical solution.
The study analyzed Twitter's automated image cropping system, which was found to systematically favor light-skinned individuals and crop women's bodies over heads, identifying factors like argmax bias. It concluded that formal fairness metrics alone are insufficient to address representational harm and recommended removing saliency-based cropping in favor of human-centered solutions.
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.