no code implementations • 3 Mar 2022 • Klara Krieg, Emilia Parada-Cabaleiro, Markus Schedl, Navid Rekabsaz
This work investigates the effect of gender-stereotypical biases in the content of retrieved results on the relevance judgement of users/annotators.
1 code implementation • 19 Jan 2022 • Klara Krieg, Emilia Parada-Cabaleiro, Gertraud Medicus, Oleg Lesota, Markus Schedl, Navid Rekabsaz
To facilitate the studies of gender bias in the retrieval results of IR systems, we introduce Gender Representation-Bias for Information Retrieval (Grep-BiasIR), a novel thoroughly-audited dataset consisting of 118 bias-sensitive neutral search queries.