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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

News recommendation is important for online news services. Existing newsrecommendation models are usually learned from users' news click behaviors.Usually the behaviors of users with the same sensitive attributes (e.g.,genders) have similar patterns and news recommendation models can easilycapture these patterns. It may lead to some biases related to sensitive userattributes in the recommendation results, e.g., always recommending sports newsto male users, which is unfair since users may not receive diverse newsinformation. In this paper, we propose a fairness-aware news recommendationapproach with decomposed adversarial learning and orthogonality regularization,which can alleviate unfairness in news recommendation brought by the biases ofsensitive user attributes. In our approach, we propose to decompose the userinterest model into two components. One component aims to learn a bias-awareuser embedding that captures the bias information on sensitive user attributes,and the other aims to learn a bias-free user embedding that only encodesattribute-independent user interest information for fairness-aware newsrecommendation. In addition, we propose to apply an attribute prediction taskto the bias-aware user embedding to enhance its ability on bias modeling, andwe apply adversarial learning to the bias-free user embedding to remove thebias information from it. Moreover, we propose an orthogonality regularizationmethod to encourage the bias-free user embeddings to be orthogonal to thebias-aware one to better distinguish the bias-free user embedding from thebias-aware one. For fairness-aware news ranking, we only use the bias-free userembedding. Extensive experiments on benchmark dataset show that our approachcan effectively improve fairness in news recommendation with minor performanceloss.

FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learning