FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295088581> ?p ?o ?g. }

• W4295088581 endingPage "6652" @default.
• W4295088581 startingPage "6652" @default.
• W4295088581 abstract "With the development of social media, social communication has changed. While this facilitates people’s communication and access to information, it also provides an ideal platform for spreading rumors. In normal or critical situations, rumors can affect people’s judgment and even endanger social security. However, natural language is high-dimensional and sparse, and the same rumor may be expressed in hundreds of ways on social media. As such, the robustness and generalization of the current rumor detection model are in question. We proposed a novel hierarchical adversarial training method for rumor detection (HAT4RD) on social media. Specifically, HAT4RD is based on gradient ascent by adding adversarial perturbations to the embedding layers of post-level and event-level modules to deceive the detector. At the same time, the detector uses stochastic gradient descent to minimize the adversarial risk to learn a more robust model. In this way, the post-level and event-level sample spaces are enhanced, and we verified the robustness of our model under a variety of adversarial attacks. Moreover, visual experiments indicate that the proposed model drifts into an area with a flat loss landscape, thereby, leading to better generalization. We evaluate our proposed method on three public rumor datasets from two commonly used social platforms (Twitter and Weibo). Our experimental results demonstrate that our model achieved better results compared with the state-of-the-art methods." @default.
• W4295088581 created "2022-09-10" @default.
• W4295088581 creator A5025583151 @default.
• W4295088581 creator A5046609960 @default.
• W4295088581 creator A5076323286 @default.
• W4295088581 date "2022-09-02" @default.
• W4295088581 modified "2023-10-18" @default.
• W4295088581 title "HAT4RD: Hierarchical Adversarial Training for Rumor Detection in Social Media" @default.
• W4295088581 cites W2064675550 @default.
• W4295088581 cites W2250539671 @default.
• W4295088581 cites W2753727548 @default.
• W4295088581 cites W2788235048 @default.
• W4295088581 cites W2798787718 @default.
• W4295088581 cites W2914116198 @default.
• W4295088581 cites W2949128310 @default.
• W4295088581 cites W2951307134 @default.
• W4295088581 cites W2963811339 @default.
• W4295088581 cites W2963969878 @default.
• W4295088581 cites W3014820715 @default.
• W4295088581 cites W3101890897 @default.
• W4295088581 cites W3103872969 @default.
• W4295088581 cites W3107267763 @default.
• W4295088581 cites W3184617674 @default.
• W4295088581 cites W3215354115 @default.
• W4295088581 cites W4210622371 @default.
• W4295088581 doi "https://doi.org/10.3390/s22176652" @default.
• W4295088581 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36081111" @default.
• W4295088581 hasPublicationYear "2022" @default.
• W4295088581 type Work @default.
• W4295088581 citedByCount "1" @default.
• W4295088581 countsByYear W42950885812023 @default.
• W4295088581 crossrefType "journal-article" @default.
• W4295088581 hasAuthorship W4295088581A5025583151 @default.
• W4295088581 hasAuthorship W4295088581A5046609960 @default.
• W4295088581 hasAuthorship W4295088581A5076323286 @default.
• W4295088581 hasBestOaLocation W42950885811 @default.
• W4295088581 hasConcept C104317684 @default.
• W4295088581 hasConcept C119857082 @default.
• W4295088581 hasConcept C121332964 @default.
• W4295088581 hasConcept C134306372 @default.
• W4295088581 hasConcept C136764020 @default.
• W4295088581 hasConcept C153258448 @default.
• W4295088581 hasConcept C154945302 @default.
• W4295088581 hasConcept C177148314 @default.
• W4295088581 hasConcept C17744445 @default.
• W4295088581 hasConcept C185592680 @default.
• W4295088581 hasConcept C2779662365 @default.
• W4295088581 hasConcept C2780469804 @default.
• W4295088581 hasConcept C33923547 @default.
• W4295088581 hasConcept C37736160 @default.
• W4295088581 hasConcept C38652104 @default.
• W4295088581 hasConcept C39549134 @default.
• W4295088581 hasConcept C41008148 @default.
• W4295088581 hasConcept C41608201 @default.
• W4295088581 hasConcept C50644808 @default.
• W4295088581 hasConcept C518677369 @default.
• W4295088581 hasConcept C55493867 @default.
• W4295088581 hasConcept C62520636 @default.
• W4295088581 hasConcept C63479239 @default.
• W4295088581 hasConcept C76155785 @default.
• W4295088581 hasConcept C94915269 @default.
• W4295088581 hasConceptScore W4295088581C104317684 @default.
• W4295088581 hasConceptScore W4295088581C119857082 @default.
• W4295088581 hasConceptScore W4295088581C121332964 @default.
• W4295088581 hasConceptScore W4295088581C134306372 @default.
• W4295088581 hasConceptScore W4295088581C136764020 @default.
• W4295088581 hasConceptScore W4295088581C153258448 @default.
• W4295088581 hasConceptScore W4295088581C154945302 @default.
• W4295088581 hasConceptScore W4295088581C177148314 @default.
• W4295088581 hasConceptScore W4295088581C17744445 @default.
• W4295088581 hasConceptScore W4295088581C185592680 @default.
• W4295088581 hasConceptScore W4295088581C2779662365 @default.
• W4295088581 hasConceptScore W4295088581C2780469804 @default.
• W4295088581 hasConceptScore W4295088581C33923547 @default.
• W4295088581 hasConceptScore W4295088581C37736160 @default.
• W4295088581 hasConceptScore W4295088581C38652104 @default.
• W4295088581 hasConceptScore W4295088581C39549134 @default.
• W4295088581 hasConceptScore W4295088581C41008148 @default.
• W4295088581 hasConceptScore W4295088581C41608201 @default.
• W4295088581 hasConceptScore W4295088581C50644808 @default.
• W4295088581 hasConceptScore W4295088581C518677369 @default.
• W4295088581 hasConceptScore W4295088581C55493867 @default.
• W4295088581 hasConceptScore W4295088581C62520636 @default.
• W4295088581 hasConceptScore W4295088581C63479239 @default.
• W4295088581 hasConceptScore W4295088581C76155785 @default.
• W4295088581 hasConceptScore W4295088581C94915269 @default.
• W4295088581 hasIssue "17" @default.
• W4295088581 hasLocation W42950885811 @default.
• W4295088581 hasLocation W42950885812 @default.
• W4295088581 hasLocation W42950885813 @default.
• W4295088581 hasLocation W42950885814 @default.
• W4295088581 hasLocation W42950885815 @default.
• W4295088581 hasOpenAccess W4295088581 @default.
• W4295088581 hasPrimaryLocation W42950885811 @default.
• W4295088581 hasRelatedWork W2978686724 @default.
• W4295088581 hasRelatedWork W2979999556 @default.
• W4295088581 hasRelatedWork W3046550781 @default.
• W4295088581 hasRelatedWork W3046843850 @default.

• next