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

With the spreading of hate speech on social media in recent years, automaticdetection of hate speech is becoming a crucial task and has attracted attentionfrom various communities. This task aims to recognize online posts (e.g.,tweets) that contain hateful information. The peculiarities of languages insocial media, such as short and poorly written content, lead to the difficultyof learning semantics and capturing discriminative features of hate speech.Previous studies have utilized additional useful resources, such as sentimenthashtags, to improve the performance of hate speech detection. Hashtags areadded as input features serving either as sentiment-lexicons or extra contextinformation. However, our close investigation shows that directly leveragingthese features without considering their context may introduce noise toclassifiers. In this paper, we propose a novel approach to leverage sentimenthashtags to enhance hate speech detection in a natural language inferenceframework. We design a novel framework SRIC that simultaneously performs twotasks: (1) semantic relation inference between online posts and sentimenthashtags, and (2) sentiment classification on these posts. The semanticrelation inference aims to encourage the model to encode sentiment-indicativeinformation into representations of online posts. We conduct extensiveexperiments on two real-world datasets and demonstrate the effectiveness of ourproposed framework compared with state-of-the-art representation learningmodels.

Anti-Asian Hate Speech Detection via Data Augmented Semantic Relation Inference