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

On June 24, 2018, Turkey conducted a highly consequential election in whichthe Turkish people elected their president and parliament in the first electionunder a new presidential system. During the election period, the Turkish peopleextensively shared their political opinions on Twitter. One aspect ofpolarization among the electorate was support for or opposition to thereelection of Recep Tayyip Erdo\u{g}an. In this paper, we present anunsupervised method for target-specific stance detection in a polarizedsetting, specifically Turkish politics, achieving 90% precision in identifyinguser stances, while maintaining more than 80% recall. The method involvesrepresenting users in an embedding space using Google's Convolutional NeuralNetwork (CNN) based multilingual universal sentence encoder. Therepresentations are then projected onto a lower dimensional space in a mannerthat reflects similarities and are consequently clustered. We show theeffectiveness of our method in properly clustering users of divergent groupsacross multiple targets that include political figures, different groups, andparties. We perform our analysis on a large dataset of 108M Turkishelection-related tweets along with the timeline tweets of 168k Turkish users,who authored 213M tweets. Given the resultant user stances, we are able toobserve correlations between topics and compute topic polarization.

Embeddings-Based Clustering for Target Specific Stances: The Case of a Polarized Turkey