English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Public figures receive a disproportionate amount of abuse on social media,impacting their active participation in public life. Automated systems canidentify abuse at scale but labelling training data is expensive, complex andpotentially harmful. So, it is desirable that systems are efficient andgeneralisable, handling both shared and specific aspects of online abuse. Weexplore the dynamics of cross-group text classification in order to understandhow well classifiers trained on one domain or demographic can transfer toothers, with a view to building more generalisable abuse classifiers. Wefine-tune language models to classify tweets targeted at public figures acrossDOmains (sport and politics) and DemOgraphics (women and men) using our novelDODO dataset, containing 28,000 labelled entries, split equally across fourdomain-demographic pairs. We find that (i) small amounts of diverse data arehugely beneficial to generalisation and model adaptation; (ii) models transfermore easily across demographics but models trained on cross-domain data aremore generalisable; (iii) some groups contribute more to generalisability thanothers; and (iv) dataset similarity is a signal of transferability.

DoDo Learning: DOmain-DemOgraphic Transfer in Language Models for Detecting Abuse Targeted at Public Figures