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

News recommender systems play an increasingly influential role in shapinginformation access within democratic societies. However, tailoringrecommendations to users' specific interests can result in the divergence ofinformation streams. Fragmented access to information poses challenges to theintegrity of the public sphere, thereby influencing democracy and publicdiscourse. The Fragmentation metric quantifies the degree of fragmentation ofinformation streams in news recommendations. Accurate measurement of thismetric requires the application of Natural Language Processing (NLP) toidentify distinct news events, stories, or timelines. This paper presents anextensive investigation of various approaches for quantifying Fragmentation innews recommendations. These approaches are evaluated both intrinsically, bymeasuring performance on news story clustering, and extrinsically, by assessingthe Fragmentation scores of different simulated news recommender scenarios. Ourfindings demonstrate that agglomerative hierarchical clustering coupled withSentenceBERT text representation is substantially better at detectingFragmentation than earlier implementations. Additionally, the analysis ofsimulated scenarios yields valuable insights and recommendations forstakeholders concerning the measurement and interpretation of Fragmentation.

Improving and Evaluating the Detection of Fragmentation in News Recommendations with the Clustering of News Story Chains