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 recommendation is one of the most challenging tasks in recommendersystems, mainly due to the ephemeral relevance of news to users. As socialmedia, and particularly microblogging applications like Twitter or Weibo, gainspopularity as platforms for news dissemination, personalized newsrecommendation in this context becomes a significant challenge. We revisit newsrecommendation in the microblogging scenario, by taking into considerationsocial interactions and observations tracing how the information that is up forrecommendation spreads in an underlying network. We propose a deep-learningbased approach that is diffusion and influence-aware, called Influence-GraphNews Recommender (IGNiteR). It is a content-based deep recommendation modelthat jointly exploits all the data facets that may impact adoption decisions,namely semantics, diffusion-related features pertaining to local and globalinfluence among users, temporal attractiveness, and timeliness, as well asdynamic user preferences. To represent the news, a multi-level attention-basedencoder is used to reveal the different interests of users. This news encoderrelies on a CNN for the news content and on an attentive LSTM for the diffusiontraces. For the latter, by exploiting previously observed news diffusions(cascades) in the microblogging medium, users are mapped to a latent space thatcaptures potential influence on others or susceptibility of being influencedfor news adoptions. Similarly, a time-sensitive user encoder enables us tocapture the dynamic preferences of users with an attention-based bidirectionalLSTM. We perform extensive experiments on two real-world datasets, showing thatIGNiteR outperforms the state-of-the-art deep-learning based newsrecommendation methods.

IGNiteR: News Recommendation in Microblogging Applications (Extended Version)