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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recommender Systems (RS) have became a popular research topic and, since2016, Deep Learning methods and techniques have been increasingly explored inthis area. News RS are aimed to personalize users experiences and help themdiscover relevant articles from a large and dynamic search space. The maincontribution of this research was named CHAMELEON, a Deep Learningmeta-architecture designed to tackle the specific challenges of newsrecommendation. It consists of a modular reference architecture which can beinstantiated using different neural building blocks. As information aboutusers' past interactions is scarce in the news domain, the user context can beleveraged to deal with the user cold-start problem. Articles' content is alsoimportant to tackle the item cold-start problem. Additionally, the temporaldecay of items (articles) relevance is very accelerated in the news domain.Furthermore, external breaking events may temporally attract global readershipattention, a phenomenon generally known as concept drift in machine learning.All those characteristics are explicitly modeled on this research by acontextual hybrid session-based recommendation approach using Recurrent NeuralNetworks. The task addressed by this research is session-based newsrecommendation, i.e., next-click prediction using only information available inthe current user session. A method is proposed for a realistic temporal offlineevaluation of such task, replaying the stream of user clicks and fresh articlesbeing continuously published in a news portal. Experiments performed with twolarge datasets have shown the effectiveness of the CHAMELEON for newsrecommendation on many quality factors such as accuracy, item coverage,novelty, and reduced item cold-start problem, when compared to othertraditional and state-of-the-art session-based recommendation algorithms.

CHAMELEON: A Deep Learning Meta-Architecture for News Recommender Systems [Phd. Thesis]