We are working on studying methods to detect social biases. This includes detecting gendered language automatically using unsupervised learning methods, such as variational auto-encoders. The findings of our first paper on this (Hoyle et al., 2019) have been reported by 75+ international news outlets, including Forbes.
We have also studied gender biases in cross-lingual settings, as well as the relationship between gender bias and attitudes towards entities on social media as part of a project funded by DFF.
Moreover, in a Carlsberg-funded project which started in autumn 2023, we are investigating biases which influence the employer images that organisations project in job ads.
