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

Recent developments in generative AI have shone a spotlight onhigh-performance synthetic text generation technologies. The now wideavailability and ease of use of such models highlights the urgent need toprovide equally powerful technologies capable of identifying synthetic text.With this in mind, we draw inspiration from psychological studies which suggestthat people can be driven by emotion and encode emotion in the text theycompose. We hypothesize that pretrained language models (PLMs) have anaffective deficit because they lack such an emotional driver when generatingtext and consequently may generate synthetic text which has affectiveincoherence i.e. lacking the kind of emotional coherence present inhuman-authored text. We subsequently develop an emotionally aware detector byfine-tuning a PLM on emotion. Experiment results indicate that ouremotionally-aware detector achieves improvements across a range of synthetictext generators, various sized models, datasets, and domains. Finally, wecompare our emotionally-aware synthetic text detector to ChatGPT in the task ofidentification of its own output and show substantial gains, reinforcing thepotential of emotion as a signal to identify synthetic text. Code, models, anddatasets are available at https: //github.com/alanagiasi/emoPLMsynth

Do Stochastic Parrots have Feelings Too? Improving Neural Detection of Synthetic Text via Emotion Recognition