4 papers
Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models
Tanvi Dinkar, Aiqi Jiang, Gavin Abercrombie +1
Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Incre…
Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech
Tanvi Dinkar, Aiqi Jiang, Simona Frenda +4
Counterspeech, i.e. the practice of responding to online hate speech, has gained traction in NLP as a promising intervention. While early work emphasised collaboration with non-gov…
Re-examining Sexism and Misogyny Classification with Annotator Attitudes
Aiqi Jiang, Nikolas Vitsakis, Tanvi Dinkar +2
Gender-Based Violence (GBV) is an increasing problem online, but existing datasets fail to capture the plurality of possible annotator perspectives or ensure the representation of…
Voices in a Crowd: Searching for Clusters of Unique Perspectives
Nikolas Vitsakis, Amit Parekh, Ioannis Konstas
Language models have been shown to reproduce underlying biases existing in their training data, which is the majority perspective by default. Proposed solutions aim to capture mino…