Run Like a Girl! Sports-Related Gender Bias in Language and Vision
This work addresses gender bias in AI datasets and models, which can perpetuate stereotypes and discrimination against women, but it is incremental as it builds on prior findings of underrepresentation.
The study analyzed gender bias in Language and Vision datasets, finding that women are underrepresented and that human naming choices for sports participants show bias, with 46% of men vs. 35% of women receiving sports-related names, and a computational model trained on this data reproduced the bias.
Gender bias in Language and Vision datasets and models has the potential to perpetuate harmful stereotypes and discrimination. We analyze gender bias in two Language and Vision datasets. Consistent with prior work, we find that both datasets underrepresent women, which promotes their invisibilization. Moreover, we hypothesize and find that a bias affects human naming choices for people playing sports: speakers produce names indicating the sport (e.g. 'tennis player' or 'surfer') more often when it is a man or a boy participating in the sport than when it is a woman or a girl, with an average of 46% vs. 35% of sports-related names for each gender. A computational model trained on these naming data reproduces the bias. We argue that both the data and the model result in representational harm against women.