FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226103313> ?p ?o ?g. }

• W4226103313 abstract "The diffusion of rumors on social media generally follows a propagation tree structure, which provides valuable clues on how an original message is transmitted and responded by users over time. Recent studies reveal that rumor verification and stance detection are two relevant tasks that can jointly enhance each other despite their differences. For example, rumors can be debunked by cross-checking the stances conveyed by their relevant posts, and stances are also conditioned on the nature of the rumor. However, stance detection typically requires a large training set of labeled stances at post level, which are rare and costly to annotate. Enlightened by Multiple Instance Learning (MIL) scheme, we propose a novel weakly supervised joint learning framework for rumor verification and stance detection which only requires bag-level class labels concerning the rumor's veracity. Specifically, based on the propagation trees of source posts, we convert the two multi-class problems into multiple MIL-based binary classification problems where each binary model is focused on differentiating a target class (of rumor or stance) from the remaining classes. Then, we propose a hierarchical attention mechanism to aggregate the binary predictions, including (1) a bottom-up/top-down tree attention layer to aggregate binary stances into binary veracity; and (2) a discriminative attention layer to aggregate the binary class into finer-grained classes. Extensive experiments conducted on three Twitter-based datasets demonstrate promising performance of our model on both claim-level rumor detection and post-level stance classification compared with state-of-the-art methods." @default.
• W4226103313 created "2022-05-05" @default.
• W4226103313 creator A5009514550 @default.
• W4226103313 creator A5017322880 @default.
• W4226103313 creator A5034823980 @default.
• W4226103313 creator A5078451082 @default.
• W4226103313 date "2022-07-06" @default.
• W4226103313 modified "2023-10-14" @default.
• W4226103313 title "A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning" @default.
• W4226103313 cites W1546111015 @default.
• W4226103313 cites W1638051351 @default.
• W4226103313 cites W2050619059 @default.
• W4226103313 cites W2051405935 @default.
• W4226103313 cites W2084591134 @default.
• W4226103313 cites W2142869398 @default.
• W4226103313 cites W2250539671 @default.
• W4226103313 cites W2281420995 @default.
• W4226103313 cites W2424495361 @default.
• W4226103313 cites W2515728551 @default.
• W4226103313 cites W2533452169 @default.
• W4226103313 cites W2557798836 @default.
• W4226103313 cites W2607700676 @default.
• W4226103313 cites W2741930413 @default.
• W4226103313 cites W2742144412 @default.
• W4226103313 cites W2774484786 @default.
• W4226103313 cites W2788235048 @default.
• W4226103313 cites W2798640866 @default.
• W4226103313 cites W2798966390 @default.
• W4226103313 cites W2914572204 @default.
• W4226103313 cites W2951288507 @default.
• W4226103313 cites W2954444514 @default.
• W4226103313 cites W2962739339 @default.
• W4226103313 cites W2963277000 @default.
• W4226103313 cites W2963355447 @default.
• W4226103313 cites W2963811339 @default.
• W4226103313 cites W2964199361 @default.
• W4226103313 cites W2964303953 @default.
• W4226103313 cites W2970683844 @default.
• W4226103313 cites W2987229106 @default.
• W4226103313 cites W2997128522 @default.
• W4226103313 cites W3004409790 @default.
• W4226103313 cites W3012895527 @default.
• W4226103313 cites W3017402509 @default.
• W4226103313 cites W3101026830 @default.
• W4226103313 cites W3102743123 @default.
• W4226103313 cites W3104186312 @default.
• W4226103313 cites W3115830738 @default.
• W4226103313 cites W3125491592 @default.
• W4226103313 cites W3207512843 @default.
• W4226103313 doi "https://doi.org/10.1145/3477495.3531930" @default.
• W4226103313 hasPublicationYear "2022" @default.
• W4226103313 type Work @default.
• W4226103313 citedByCount "7" @default.
• W4226103313 countsByYear W42261033132022 @default.
• W4226103313 countsByYear W42261033132023 @default.
• W4226103313 crossrefType "proceedings-article" @default.
• W4226103313 hasAuthorship W4226103313A5009514550 @default.
• W4226103313 hasAuthorship W4226103313A5017322880 @default.
• W4226103313 hasAuthorship W4226103313A5034823980 @default.
• W4226103313 hasAuthorship W4226103313A5078451082 @default.
• W4226103313 hasBestOaLocation W42261033132 @default.
• W4226103313 hasConcept C113174947 @default.
• W4226103313 hasConcept C11413529 @default.
• W4226103313 hasConcept C119857082 @default.
• W4226103313 hasConcept C12267149 @default.
• W4226103313 hasConcept C134306372 @default.
• W4226103313 hasConcept C154945302 @default.
• W4226103313 hasConcept C159985019 @default.
• W4226103313 hasConcept C177264268 @default.
• W4226103313 hasConcept C17744445 @default.
• W4226103313 hasConcept C192562407 @default.
• W4226103313 hasConcept C197855036 @default.
• W4226103313 hasConcept C199360897 @default.
• W4226103313 hasConcept C2777212361 @default.
• W4226103313 hasConcept C2780469804 @default.
• W4226103313 hasConcept C33923547 @default.
• W4226103313 hasConcept C39549134 @default.
• W4226103313 hasConcept C41008148 @default.
• W4226103313 hasConcept C4679612 @default.
• W4226103313 hasConcept C48372109 @default.
• W4226103313 hasConcept C66905080 @default.
• W4226103313 hasConcept C94375191 @default.
• W4226103313 hasConcept C97931131 @default.
• W4226103313 hasConceptScore W4226103313C113174947 @default.
• W4226103313 hasConceptScore W4226103313C11413529 @default.
• W4226103313 hasConceptScore W4226103313C119857082 @default.
• W4226103313 hasConceptScore W4226103313C12267149 @default.
• W4226103313 hasConceptScore W4226103313C134306372 @default.
• W4226103313 hasConceptScore W4226103313C154945302 @default.
• W4226103313 hasConceptScore W4226103313C159985019 @default.
• W4226103313 hasConceptScore W4226103313C177264268 @default.
• W4226103313 hasConceptScore W4226103313C17744445 @default.
• W4226103313 hasConceptScore W4226103313C192562407 @default.
• W4226103313 hasConceptScore W4226103313C197855036 @default.
• W4226103313 hasConceptScore W4226103313C199360897 @default.
• W4226103313 hasConceptScore W4226103313C2777212361 @default.
• W4226103313 hasConceptScore W4226103313C2780469804 @default.
• W4226103313 hasConceptScore W4226103313C33923547 @default.
• W4226103313 hasConceptScore W4226103313C39549134 @default.
• W4226103313 hasConceptScore W4226103313C41008148 @default.

• next