Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311753802> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4311753802 endingPage "103206" @default.
- W4311753802 startingPage "103206" @default.
- W4311753802 abstract "A news article's online audience provides useful insights about the article's identity. However, fake news classifiers using such information risk relying on profiling. In response to the rising demand for ethical AI, we present a profiling-avoiding algorithm that leverages Twitter users during model optimisation while excluding them when an article's veracity is evaluated. For this, we take inspiration from the social sciences and introduce two objective functions that maximise correlation between the article and its spreaders, and among those spreaders. We applied our profiling-avoiding algorithm to three popular neural classifiers and obtained results on fake news data discussing a variety of news topics. The positive impact on prediction performance demonstrates the soundness of the proposed objective functions to integrate social context in text-based classifiers. Moreover, statistical visualisation and dimension reduction techniques show that the user-inspired classifiers better discriminate between unseen fake and true news in their latent spaces. Our study serves as a stepping stone to resolve the underexplored issue of profiling-dependent decision-making in user-informed fake news detection." @default.
- W4311753802 created "2022-12-28" @default.
- W4311753802 creator A5062734231 @default.
- W4311753802 creator A5064148555 @default.
- W4311753802 creator A5075796989 @default.
- W4311753802 date "2023-03-01" @default.
- W4311753802 modified "2023-10-06" @default.
- W4311753802 title "Preventing profiling for ethical fake news detection" @default.
- W4311753802 cites W1984007049 @default.
- W4311753802 cites W2035392043 @default.
- W4311753802 cites W2048993342 @default.
- W4311753802 cites W2054834816 @default.
- W4311753802 cites W2082398846 @default.
- W4311753802 cites W2086220442 @default.
- W4311753802 cites W2090396718 @default.
- W4311753802 cites W2122305905 @default.
- W4311753802 cites W2173611154 @default.
- W4311753802 cites W2281420995 @default.
- W4311753802 cites W2507977639 @default.
- W4311753802 cites W2531862055 @default.
- W4311753802 cites W2582561810 @default.
- W4311753802 cites W2610765098 @default.
- W4311753802 cites W2742330194 @default.
- W4311753802 cites W2970129024 @default.
- W4311753802 cites W2991596147 @default.
- W4311753802 cites W2998395006 @default.
- W4311753802 cites W3031781733 @default.
- W4311753802 cites W3033077667 @default.
- W4311753802 cites W3101908935 @default.
- W4311753802 cites W3125182500 @default.
- W4311753802 cites W3172717122 @default.
- W4311753802 cites W3178700851 @default.
- W4311753802 cites W3186955206 @default.
- W4311753802 cites W3194651497 @default.
- W4311753802 cites W3196248941 @default.
- W4311753802 cites W3207776204 @default.
- W4311753802 cites W3216370178 @default.
- W4311753802 cites W4237723258 @default.
- W4311753802 cites W4285783891 @default.
- W4311753802 doi "https://doi.org/10.1016/j.ipm.2022.103206" @default.
- W4311753802 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36874352" @default.
- W4311753802 hasPublicationYear "2023" @default.
- W4311753802 type Work @default.
- W4311753802 citedByCount "1" @default.
- W4311753802 countsByYear W43117538022023 @default.
- W4311753802 crossrefType "journal-article" @default.
- W4311753802 hasAuthorship W4311753802A5062734231 @default.
- W4311753802 hasAuthorship W4311753802A5064148555 @default.
- W4311753802 hasAuthorship W4311753802A5075796989 @default.
- W4311753802 hasBestOaLocation W43117538021 @default.
- W4311753802 hasConcept C111919701 @default.
- W4311753802 hasConcept C119857082 @default.
- W4311753802 hasConcept C136764020 @default.
- W4311753802 hasConcept C154945302 @default.
- W4311753802 hasConcept C187191949 @default.
- W4311753802 hasConcept C199360897 @default.
- W4311753802 hasConcept C23123220 @default.
- W4311753802 hasConcept C2522767166 @default.
- W4311753802 hasConcept C39920170 @default.
- W4311753802 hasConcept C41008148 @default.
- W4311753802 hasConcept C518677369 @default.
- W4311753802 hasConcept C66402592 @default.
- W4311753802 hasConceptScore W4311753802C111919701 @default.
- W4311753802 hasConceptScore W4311753802C119857082 @default.
- W4311753802 hasConceptScore W4311753802C136764020 @default.
- W4311753802 hasConceptScore W4311753802C154945302 @default.
- W4311753802 hasConceptScore W4311753802C187191949 @default.
- W4311753802 hasConceptScore W4311753802C199360897 @default.
- W4311753802 hasConceptScore W4311753802C23123220 @default.
- W4311753802 hasConceptScore W4311753802C2522767166 @default.
- W4311753802 hasConceptScore W4311753802C39920170 @default.
- W4311753802 hasConceptScore W4311753802C41008148 @default.
- W4311753802 hasConceptScore W4311753802C518677369 @default.
- W4311753802 hasConceptScore W4311753802C66402592 @default.
- W4311753802 hasIssue "2" @default.
- W4311753802 hasLocation W43117538021 @default.
- W4311753802 hasLocation W43117538022 @default.
- W4311753802 hasLocation W43117538023 @default.
- W4311753802 hasOpenAccess W4311753802 @default.
- W4311753802 hasPrimaryLocation W43117538021 @default.
- W4311753802 hasRelatedWork W2019096655 @default.
- W4311753802 hasRelatedWork W2252197266 @default.
- W4311753802 hasRelatedWork W3049681097 @default.
- W4311753802 hasRelatedWork W3118656355 @default.
- W4311753802 hasRelatedWork W3148756070 @default.
- W4311753802 hasRelatedWork W3192794374 @default.
- W4311753802 hasRelatedWork W4205350312 @default.
- W4311753802 hasRelatedWork W4362613237 @default.
- W4311753802 hasRelatedWork W4379932966 @default.
- W4311753802 hasRelatedWork W4382286084 @default.
- W4311753802 hasVolume "60" @default.
- W4311753802 isParatext "false" @default.
- W4311753802 isRetracted "false" @default.
- W4311753802 workType "article" @default.