Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128655363> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3128655363 endingPage "55" @default.
- W3128655363 startingPage "37" @default.
- W3128655363 abstract "When developing an algorithm that uses news diversity as a key driver for personalized news recommendation it is crucial to focus on means to cluster news articles in a fine-grained manner, ideally by leveraging the content of the text. In this paper we investigate semantic classification of news articles in an unfiltered news stream. We first present an analysis of the EventDNA corpus: a collection of Dutch-language news articles annotated with event data according to apredefined typology. We found that the types assigned as features of events do not allow for such a semantic classification and investigate the IPTC News Media Topics standard as an alternative. By mapping event types with manually-assigned IPTC topics, we observe that a more diversified picture emerges, which leads us to conclude that the IPTC classification is a useful proxy. Based on a historical data sample of Dutch news articles covering the year 2018, we then perform a series of machine learning experiments in order to automatically predict the top two levels of the IPTC taxonomy. Various multi-label classification models are built with BERTje using a bottom-up and top-down approach. The results reveal that the top-down approach yields the best results, with an overall macro F-1 score of 86.4% and a Jaccard accuracy of 89.2% for the level-one topics and one of 83.7% and 87.5% for the level-two predictions." @default.
- W3128655363 created "2021-02-15" @default.
- W3128655363 creator A5019867041 @default.
- W3128655363 creator A5022634644 @default.
- W3128655363 creator A5081335221 @default.
- W3128655363 date "2020-12-12" @default.
- W3128655363 modified "2023-09-23" @default.
- W3128655363 title "News topic classification as a first step towards diverse news recommendation" @default.
- W3128655363 hasPublicationYear "2020" @default.
- W3128655363 type Work @default.
- W3128655363 sameAs 3128655363 @default.
- W3128655363 citedByCount "0" @default.
- W3128655363 crossrefType "proceedings-article" @default.
- W3128655363 hasAuthorship W3128655363A5019867041 @default.
- W3128655363 hasAuthorship W3128655363A5022634644 @default.
- W3128655363 hasAuthorship W3128655363A5081335221 @default.
- W3128655363 hasConcept C121332964 @default.
- W3128655363 hasConcept C136764020 @default.
- W3128655363 hasConcept C154945302 @default.
- W3128655363 hasConcept C203519979 @default.
- W3128655363 hasConcept C204321447 @default.
- W3128655363 hasConcept C23123220 @default.
- W3128655363 hasConcept C2779662365 @default.
- W3128655363 hasConcept C41008148 @default.
- W3128655363 hasConcept C58642233 @default.
- W3128655363 hasConcept C59822182 @default.
- W3128655363 hasConcept C62520636 @default.
- W3128655363 hasConcept C73555534 @default.
- W3128655363 hasConcept C86803240 @default.
- W3128655363 hasConceptScore W3128655363C121332964 @default.
- W3128655363 hasConceptScore W3128655363C136764020 @default.
- W3128655363 hasConceptScore W3128655363C154945302 @default.
- W3128655363 hasConceptScore W3128655363C203519979 @default.
- W3128655363 hasConceptScore W3128655363C204321447 @default.
- W3128655363 hasConceptScore W3128655363C23123220 @default.
- W3128655363 hasConceptScore W3128655363C2779662365 @default.
- W3128655363 hasConceptScore W3128655363C41008148 @default.
- W3128655363 hasConceptScore W3128655363C58642233 @default.
- W3128655363 hasConceptScore W3128655363C59822182 @default.
- W3128655363 hasConceptScore W3128655363C62520636 @default.
- W3128655363 hasConceptScore W3128655363C73555534 @default.
- W3128655363 hasConceptScore W3128655363C86803240 @default.
- W3128655363 hasOpenAccess W3128655363 @default.
- W3128655363 hasRelatedWork W2022741067 @default.
- W3128655363 hasRelatedWork W2099421013 @default.
- W3128655363 hasRelatedWork W2156927767 @default.
- W3128655363 hasRelatedWork W2186999845 @default.
- W3128655363 hasRelatedWork W2187456046 @default.
- W3128655363 hasRelatedWork W2259890326 @default.
- W3128655363 hasRelatedWork W2340869240 @default.
- W3128655363 hasRelatedWork W2900337683 @default.
- W3128655363 hasRelatedWork W2908644866 @default.
- W3128655363 hasRelatedWork W2912022157 @default.
- W3128655363 hasRelatedWork W2913027083 @default.
- W3128655363 hasRelatedWork W2929958937 @default.
- W3128655363 hasRelatedWork W2959160514 @default.
- W3128655363 hasRelatedWork W2971585879 @default.
- W3128655363 hasRelatedWork W3006091572 @default.
- W3128655363 hasRelatedWork W3012910066 @default.
- W3128655363 hasRelatedWork W3144376018 @default.
- W3128655363 hasRelatedWork W3145233627 @default.
- W3128655363 hasRelatedWork W3190702630 @default.
- W3128655363 hasRelatedWork W3212141159 @default.
- W3128655363 hasVolume "10" @default.
- W3128655363 isParatext "false" @default.
- W3128655363 isRetracted "false" @default.
- W3128655363 magId "3128655363" @default.
- W3128655363 workType "article" @default.