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

Abusive language is a massive problem in online social platforms. Existingabusive language detection techniques are particularly ill-suited to commentscontaining heterogeneous abusive language patterns, i.e., both abusive andnon-abusive parts. This is due in part to the lack of datasets that explicitlyannotate heterogeneity in abusive language. We tackle this challenge byproviding an annotated dataset of abusive language in over 11,000 comments fromYouTube. We account for heterogeneity in this dataset by separately annotatingboth the comment as a whole and the individual sentences that comprise eachcomment. We then propose an algorithm that uses a supervised attentionmechanism to detect and categorize abusive content using multi-task learning.We empirically demonstrate the challenges of using traditional techniques onheterogeneous content and the comparative gains in performance of the proposedapproach over state-of-the-art methods.

Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention