Crowdsourcing stereotypes: Linguistic bias in metadata generated via GWAP

Games with a Purpose (GWAP) is a popular approach for metadata creation, enabling institutions to collect descriptions of digital artifacts on a mass scale. Creating metadata is challenging not only because one must recognize the artifact; the description must then be encoded into natural language. Language behaviors are influenced by many social factors, particularly when we are asked to describe other people. We consider labels for images of people generated via the ESP Game. While ESP has been shown to produce relevant labels, critics claim they are obvious and stereotypical. Based on theories of linguistic biases, we examine whether there are systematic differences in the ways players describe images of men versus women. Our first analysis considers images of people generally, and reveals a tendency for women to be described with subjective adjectives. A second analysis compares images depicting men and women within each of six occupational roles. Images of women receive more labels related to appearance, whereas those depicting men receive more occupation-related labels. Our work exposes the presence of gender-based stereotypes through linguistic biases, illustrates the forms in which they manifest, and raises important implications for those who design systems or train algorithms using data produced via GWAP.