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

Ideological divisions in the United States have become increasingly prominentin daily communication. Accordingly, there has been much research on politicalpolarization, including many recent efforts that take a computationalperspective. By detecting political biases in a corpus of text, one can attemptto describe and discern the polarity of that text. Intuitively, the namedentities (i.e., the nouns and the phrases that act as nouns) and hashtags intext often carry information about political views. For example, people who usethe term "pro-choice" are likely to be liberal, whereas people who use the term"pro-life" are likely to be conservative. In this paper, we seek to revealpolitical polarities in social-media text data and to quantify these polaritiesby explicitly assigning a polarity score to entities and hashtags. Althoughthis idea is straightforward, it is difficult to perform such inference in atrustworthy quantitative way. Key challenges include the small number of knownlabels, the continuous spectrum of political views, and the preservation ofboth a polarity score and a polarity-neutral semantic meaning in an embeddingvector of words. To attempt to overcome these challenges, we propose thePolarity-aware Embedding Multi-task learning (PEM) model. This model consistsof (1) a self-supervised context-preservation task, (2) an attention-basedtweet-level polarity-inference task, and (3) an adversarial learning task thatpromotes independence between an embedding's polarity dimension and itssemantic dimensions. Our experimental results demonstrate that our PEM modelcan successfully learn polarity-aware embeddings that perform wellclassification tasks. We examine a variety of applications and we therebydemonstrate the effectiveness of our PEM model. We also discuss importantlimitations of our work and encourage caution when applying the it toreal-world scenarios.

Detecting Political Biases of Named Entities and Hashtags on Twitter