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

The large language based-model chatbot ChatGPT gained a lot of popularitysince its launch and has been used in a wide range of situations. This researchcenters around a particular situation, when the ChatGPT is used to produce newsthat will be consumed by the population, causing the facilitation in theproduction of fake news, spread of misinformation and lack of trust in newssources. Aware of these problems, this research aims to build an artificialintelligence model capable of performing authorship attribution on newsarticles, identifying the ones written by the ChatGPT. To achieve this goal, adataset containing equal amounts of human and ChatGPT written news wasassembled and different natural processing language techniques were used toextract features from it that were used to train, validate and test threemodels built with different techniques. The best performance was produced bythe Bidirectional Long Short Term Memory (LSTM) Neural Network model, achiving91.57\% accuracy when tested against the data from the testing set.

Detection of news written by the ChatGPT through authorship attribution performed by a Bidirectional LSTM model