A large-scale crowdsourced analysis of abuse against women journalists and politicians on Twitter
This work addresses online abuse against women in public roles, with incremental technical contributions to dataset curation and baseline establishment.
The study tackled the problem of online abuse against women journalists and politicians on Twitter by curating a dataset and establishing baselines, resulting in a technical backbone for a media campaign to raise awareness and influence social media standards.
We report the first, to the best of our knowledge, hand-in-hand collaboration between human rights activists and machine learners, leveraging crowd-sourcing to study online abuse against women on Twitter. On a technical front, we carefully curate an unbiased yet low-variance dataset of labeled tweets, analyze it to account for the variability of abuse perception, and establish baselines, preparing it for release to community research efforts. On a social impact front, this study provides the technical backbone for a media campaign aimed at raising public and deciders' awareness and elevating the standards expected from social media companies.