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

Regulatory bodies worldwide are intensifying their efforts to ensuretransparency in influencer marketing on social media through instruments likethe Unfair Commercial Practices Directive (UCPD) in the European Union, orSection 5 of the Federal Trade Commission Act. Yet enforcing these obligationshas proven to be highly problematic due to the sheer scale of the influencermarket. The task of automatically detecting sponsored content aims to enablethe monitoring and enforcement of such regulations at scale. Current researchin this field primarily frames this problem as a machine learning task,focusing on developing models that achieve high classification performance indetecting ads. These machine learning tasks rely on human data annotation toprovide ground truth information. However, agreement between annotators isoften low, leading to inconsistent labels that hinder the reliability ofmodels. To improve annotation accuracy and, thus, the detection of sponsoredcontent, we propose using chatGPT to augment the annotation process withphrases identified as relevant features and brief explanations. Our experimentsshow that this approach consistently improves inter-annotator agreement andannotation accuracy. Additionally, our survey of user experience in theannotation task indicates that the explanations improve the annotators'confidence and streamline the process. Our proposed methods can ultimately leadto more transparency and alignment with regulatory requirements in sponsoredcontent detection.

Closing the Loop: Testing ChatGPT to Generate Model Explanations to Improve Human Labelling of Sponsored Content on Social Media