Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284664815> ?p ?o ?g. }
- W4284664815 abstract "This paper develops a novel unsupervised algorithm for belief representation learning in polarized networks that (i) uncovers the latent dimensions of the underlying belief space and (ii) jointly embeds users and content items (that they interact with) into that space in a manner that facilitates a number of downstream tasks, such as stance detection, stance prediction, and ideology mapping. Inspired by total correlation in information theory, we propose the Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e.g., posts that represent user views) into an appropriate disentangled latent space. To better disentangle latent variables in that space, we develop a total correlation regularization module, a Proportional-Integral (PI) control module, and adopt rectified Gaussian distribution to ensure the orthogonality. The latent representation of users and content can then be used to quantify their ideological leaning and detect/predict their stances on issues. We evaluate the performance of the proposed InfoVGAE on three real-world datasets, of which two are collected from Twitter and one from U.S. Congress voting records. The evaluation results show that our model outperforms state-of-the-art unsupervised models by reducing 10.5% user clustering errors and achieving 12.1% higher F1 scores for stance separation of content items. In addition, InfoVGAE produces a comparable result with supervised models. We also discuss its performance on stance prediction and user ranking within ideological groups." @default.
- W4284664815 created "2022-07-08" @default.
- W4284664815 creator A5002058484 @default.
- W4284664815 creator A5008609730 @default.
- W4284664815 creator A5040820975 @default.
- W4284664815 creator A5041685416 @default.
- W4284664815 creator A5068043486 @default.
- W4284664815 creator A5072084780 @default.
- W4284664815 creator A5087114395 @default.
- W4284664815 creator A5087363413 @default.
- W4284664815 creator A5091362073 @default.
- W4284664815 date "2022-07-06" @default.
- W4284664815 modified "2023-10-16" @default.
- W4284664815 title "Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders" @default.
- W4284664815 cites W1544399847 @default.
- W4284664815 cites W2003303386 @default.
- W4284664815 cites W2154321364 @default.
- W4284664815 cites W2155183960 @default.
- W4284664815 cites W2160450239 @default.
- W4284664815 cites W2166944917 @default.
- W4284664815 cites W2250747954 @default.
- W4284664815 cites W2406537964 @default.
- W4284664815 cites W2604260814 @default.
- W4284664815 cites W2741386817 @default.
- W4284664815 cites W2768226620 @default.
- W4284664815 cites W2798491376 @default.
- W4284664815 cites W2799305561 @default.
- W4284664815 cites W2884014654 @default.
- W4284664815 cites W2885316213 @default.
- W4284664815 cites W2897729462 @default.
- W4284664815 cites W2903782687 @default.
- W4284664815 cites W2911286998 @default.
- W4284664815 cites W2962972034 @default.
- W4284664815 cites W2984259019 @default.
- W4284664815 cites W3003506483 @default.
- W4284664815 cites W3033229230 @default.
- W4284664815 cites W3035238981 @default.
- W4284664815 cites W3080295236 @default.
- W4284664815 cites W3090515407 @default.
- W4284664815 cites W3102042889 @default.
- W4284664815 cites W3104097132 @default.
- W4284664815 cites W4298135524 @default.
- W4284664815 doi "https://doi.org/10.1145/3477495.3532072" @default.
- W4284664815 hasPublicationYear "2022" @default.
- W4284664815 type Work @default.
- W4284664815 citedByCount "3" @default.
- W4284664815 countsByYear W42846648152023 @default.
- W4284664815 crossrefType "proceedings-article" @default.
- W4284664815 hasAuthorship W4284664815A5002058484 @default.
- W4284664815 hasAuthorship W4284664815A5008609730 @default.
- W4284664815 hasAuthorship W4284664815A5040820975 @default.
- W4284664815 hasAuthorship W4284664815A5041685416 @default.
- W4284664815 hasAuthorship W4284664815A5068043486 @default.
- W4284664815 hasAuthorship W4284664815A5072084780 @default.
- W4284664815 hasAuthorship W4284664815A5087114395 @default.
- W4284664815 hasAuthorship W4284664815A5087363413 @default.
- W4284664815 hasAuthorship W4284664815A5091362073 @default.
- W4284664815 hasBestOaLocation W42846648152 @default.
- W4284664815 hasConcept C101738243 @default.
- W4284664815 hasConcept C111919701 @default.
- W4284664815 hasConcept C118505674 @default.
- W4284664815 hasConcept C119857082 @default.
- W4284664815 hasConcept C132525143 @default.
- W4284664815 hasConcept C154945302 @default.
- W4284664815 hasConcept C17744445 @default.
- W4284664815 hasConcept C199539241 @default.
- W4284664815 hasConcept C2776359362 @default.
- W4284664815 hasConcept C41008148 @default.
- W4284664815 hasConcept C50644808 @default.
- W4284664815 hasConcept C51167844 @default.
- W4284664815 hasConcept C73555534 @default.
- W4284664815 hasConcept C8038995 @default.
- W4284664815 hasConcept C80444323 @default.
- W4284664815 hasConcept C94625758 @default.
- W4284664815 hasConceptScore W4284664815C101738243 @default.
- W4284664815 hasConceptScore W4284664815C111919701 @default.
- W4284664815 hasConceptScore W4284664815C118505674 @default.
- W4284664815 hasConceptScore W4284664815C119857082 @default.
- W4284664815 hasConceptScore W4284664815C132525143 @default.
- W4284664815 hasConceptScore W4284664815C154945302 @default.
- W4284664815 hasConceptScore W4284664815C17744445 @default.
- W4284664815 hasConceptScore W4284664815C199539241 @default.
- W4284664815 hasConceptScore W4284664815C2776359362 @default.
- W4284664815 hasConceptScore W4284664815C41008148 @default.
- W4284664815 hasConceptScore W4284664815C50644808 @default.
- W4284664815 hasConceptScore W4284664815C51167844 @default.
- W4284664815 hasConceptScore W4284664815C73555534 @default.
- W4284664815 hasConceptScore W4284664815C8038995 @default.
- W4284664815 hasConceptScore W4284664815C80444323 @default.
- W4284664815 hasConceptScore W4284664815C94625758 @default.
- W4284664815 hasLocation W42846648151 @default.
- W4284664815 hasLocation W42846648152 @default.
- W4284664815 hasLocation W42846648153 @default.
- W4284664815 hasOpenAccess W4284664815 @default.
- W4284664815 hasPrimaryLocation W42846648151 @default.
- W4284664815 hasRelatedWork W2554952599 @default.
- W4284664815 hasRelatedWork W2770818364 @default.
- W4284664815 hasRelatedWork W2933374552 @default.
- W4284664815 hasRelatedWork W3196155444 @default.
- W4284664815 hasRelatedWork W3211507797 @default.