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

As recent events have demonstrated, disinformation spread through socialnetworks can have dire political, economic and social consequences. Detectingdisinformation must inevitably rely on the structure of the network, on usersparticularities and on event occurrence patterns. We present a graph datastructure, which we denote as a meta-graph, that combines underlying users'relational event information, as well as semantic and topical modeling. Wedetail the construction of an example meta-graph using Twitter data coveringthe 2016 US election campaign and then compare the detection of disinformationat cascade level, using well-known graph neural network algorithms, to the samealgorithms applied on the meta-graph nodes. The comparison shows a consistent3%-4% improvement in accuracy when using the meta-graph, over all consideredalgorithms, compared to basic cascade classification, and a further 1% increasewhen topic modeling and sentiment analysis are considered. We carry out thesame experiment on two other datasets, HealthRelease and HealthStory, part ofthe FakeHealth dataset repository, with consistent results. Finally, we discussfurther advantages of our approach, such as the ability to augment the graphstructure using external data sources, the ease with which multiple meta-graphscan be combined as well as a comparison of our method to other graph-baseddisinformation detection frameworks.

A Unified Graph-Based Approach to Disinformation Detection using Contextual and Semantic Relations