Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387303027> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4387303027 endingPage "111029" @default.
- W4387303027 startingPage "111029" @default.
- W4387303027 abstract "In e-commerce, fake reviewers frequently post fake reviews to mislead consumers into making unwise shopping decisions, seriously affecting customers’ benefits. Graph neural networks (GNNs) have been widely cultivated in fake reviewer detection in recent years, but they exhibit two main limitations. Firstly, most approaches model reviewer detection with a homogeneous graph, ignoring the interdependent clues among reviewers, reviews, and products, making them ineffective against stealthy fake reviewers. Secondly, few works noticed the camouflage behavior of fake reviewers, i.e., fake reviewers disguise themselves as authentic ones by establishing links with genuine reviewers, which extremely weakens the suspiciousness of fake reviewers and undermines detection performance. This paper proposes RHGNN, a robust fake reviewers detection framework based on Reinforced Heterogeneous Graph Neural Networks. Particularly, we first model fake reviewer detection with a heterogeneous graph consisting of reviews, reviewers, and products, to capture stealthy fraud clues by investigating their heterogeneous interactive relations. Subsequently, we present a reinforced neighbor selector (RNS) to sample and aggregate top−k informative neighbors while filtering out the camouflaged relationships. Finally, we propose a self-supervised heterogeneous graph embedding method based on mutual information to learn the discriminative features of fake reviewers. Experimental results show that RHGNN demonstrates promising and robust performance, especially in detecting well-disguised fake reviewers." @default.
- W4387303027 created "2023-10-04" @default.
- W4387303027 creator A5028762600 @default.
- W4387303027 creator A5037079180 @default.
- W4387303027 creator A5047412687 @default.
- W4387303027 creator A5050765372 @default.
- W4387303027 creator A5068254136 @default.
- W4387303027 creator A5070659482 @default.
- W4387303027 date "2023-10-01" @default.
- W4387303027 modified "2023-10-04" @default.
- W4387303027 title "RHGNN: Fake reviewer detection based on reinforced heterogeneous graph neural networks" @default.
- W4387303027 cites W103340358 @default.
- W4387303027 cites W1967495422 @default.
- W4387303027 cites W2016266039 @default.
- W4387303027 cites W2064058256 @default.
- W4387303027 cites W2103063352 @default.
- W4387303027 cites W2189187207 @default.
- W4387303027 cites W2192783609 @default.
- W4387303027 cites W2782836818 @default.
- W4387303027 cites W2911286998 @default.
- W4387303027 cites W2921404976 @default.
- W4387303027 cites W2945996535 @default.
- W4387303027 cites W2952218416 @default.
- W4387303027 cites W2984239289 @default.
- W4387303027 cites W2990236433 @default.
- W4387303027 cites W3000682630 @default.
- W4387303027 cites W3003892205 @default.
- W4387303027 cites W3008101956 @default.
- W4387303027 cites W3093563174 @default.
- W4387303027 cites W3098259638 @default.
- W4387303027 cites W3114296101 @default.
- W4387303027 cites W3144760889 @default.
- W4387303027 cites W3171675996 @default.
- W4387303027 cites W3175747747 @default.
- W4387303027 cites W3183314233 @default.
- W4387303027 cites W4220742022 @default.
- W4387303027 cites W4283078748 @default.
- W4387303027 cites W4283159949 @default.
- W4387303027 cites W4283798273 @default.
- W4387303027 cites W4284698122 @default.
- W4387303027 cites W4285091574 @default.
- W4387303027 cites W4310012576 @default.
- W4387303027 cites W4318159260 @default.
- W4387303027 cites W4323312405 @default.
- W4387303027 doi "https://doi.org/10.1016/j.knosys.2023.111029" @default.
- W4387303027 hasPublicationYear "2023" @default.
- W4387303027 type Work @default.
- W4387303027 citedByCount "0" @default.
- W4387303027 crossrefType "journal-article" @default.
- W4387303027 hasAuthorship W4387303027A5028762600 @default.
- W4387303027 hasAuthorship W4387303027A5037079180 @default.
- W4387303027 hasAuthorship W4387303027A5047412687 @default.
- W4387303027 hasAuthorship W4387303027A5050765372 @default.
- W4387303027 hasAuthorship W4387303027A5068254136 @default.
- W4387303027 hasAuthorship W4387303027A5070659482 @default.
- W4387303027 hasBestOaLocation W43873030271 @default.
- W4387303027 hasConcept C108827166 @default.
- W4387303027 hasConcept C119857082 @default.
- W4387303027 hasConcept C121332964 @default.
- W4387303027 hasConcept C132525143 @default.
- W4387303027 hasConcept C154945302 @default.
- W4387303027 hasConcept C23123220 @default.
- W4387303027 hasConcept C2522767166 @default.
- W4387303027 hasConcept C2779756789 @default.
- W4387303027 hasConcept C41008148 @default.
- W4387303027 hasConcept C66882249 @default.
- W4387303027 hasConcept C80444323 @default.
- W4387303027 hasConcept C97355855 @default.
- W4387303027 hasConcept C97931131 @default.
- W4387303027 hasConceptScore W4387303027C108827166 @default.
- W4387303027 hasConceptScore W4387303027C119857082 @default.
- W4387303027 hasConceptScore W4387303027C121332964 @default.
- W4387303027 hasConceptScore W4387303027C132525143 @default.
- W4387303027 hasConceptScore W4387303027C154945302 @default.
- W4387303027 hasConceptScore W4387303027C23123220 @default.
- W4387303027 hasConceptScore W4387303027C2522767166 @default.
- W4387303027 hasConceptScore W4387303027C2779756789 @default.
- W4387303027 hasConceptScore W4387303027C41008148 @default.
- W4387303027 hasConceptScore W4387303027C66882249 @default.
- W4387303027 hasConceptScore W4387303027C80444323 @default.
- W4387303027 hasConceptScore W4387303027C97355855 @default.
- W4387303027 hasConceptScore W4387303027C97931131 @default.
- W4387303027 hasLocation W43873030271 @default.
- W4387303027 hasOpenAccess W4387303027 @default.
- W4387303027 hasPrimaryLocation W43873030271 @default.
- W4387303027 hasRelatedWork W2026121273 @default.
- W4387303027 hasRelatedWork W2102106825 @default.
- W4387303027 hasRelatedWork W2752271443 @default.
- W4387303027 hasRelatedWork W2801772698 @default.
- W4387303027 hasRelatedWork W2961085424 @default.
- W4387303027 hasRelatedWork W2983744209 @default.
- W4387303027 hasRelatedWork W3212730154 @default.
- W4387303027 hasRelatedWork W4306674287 @default.
- W4387303027 hasRelatedWork W66955737 @default.
- W4387303027 hasRelatedWork W2073139667 @default.
- W4387303027 isParatext "false" @default.
- W4387303027 isRetracted "false" @default.
- W4387303027 workType "article" @default.