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

Automatic identification of hateful and abusive content is vital in combatingthe spread of harmful online content and its damaging effects. Most existingworks evaluate models by examining the generalization error on train-testsplits on hate speech datasets. These datasets often differ in theirdefinitions and labeling criteria, leading to poor model performance whenpredicting across new domains and datasets. In this work, we propose a newMulti-task Learning (MTL) pipeline that utilizes MTL to train simultaneouslyacross multiple hate speech datasets to construct a more encompassingclassification model. We simulate evaluation on new previously unseen datasetsby adopting a leave-one-out scheme in which we omit a target dataset fromtraining and jointly train on the other datasets. Our results consistentlyoutperform a large sample of existing work. We show strong results whenexamining generalization error in train-test splits and substantialimprovements when predicting on previously unseen datasets. Furthermore, weassemble a novel dataset, dubbed PubFigs, focusing on the problematic speech ofAmerican Public Political Figures. We automatically detect problematic speechin the $305,235$ tweets in PubFigs, and we uncover insights into the postingbehaviors of public figures.

Detect Hate Speech in Unseen Domains using Multi-Task Learning: A Case Study of Political Public Figures