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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Zipf's law defines an inverse proportion between a word's ranking in a givencorpus and its frequency in it, roughly dividing the vocabulary into frequentwords and infrequent ones. Here, we stipulate that within a domain an author'ssignature can be derived from, in loose terms, the author's missing popularwords and frequently used infrequent-words. We devise a method, termed LatentPersonal Analysis (LPA), for finding domain-based attributes for entities in adomain: their distance from the domain and their signature, which determineshow they most differ from a domain. We identify the most suitable distancemetric for the method among several and construct the distances and personalsignatures for authors, the domain's entities. The signature consists of bothover-used terms (compared to the average), and missing popular terms. Wevalidate the correctness and power of the signatures in identifying users andset existence conditions. We then show uses for the method in explainableauthorship attribution: we define algorithms that utilize LPA to identify twotypes of impersonation in social media: (1) authors with sockpuppets (multiple)accounts; (2) front users accounts, operated by several authors. We validatethe algorithms and employ them over a large scale dataset obtained from asocial media site with over 4000 users. We corroborate these results usingtemporal rate analysis. LPA can further be used to devise personal attributesin a wide range of scientific domains in which the constituents have along-tail distribution of elements.

Domain-based Latent Personal Analysis and its use for impersonation detection in social media