dc.contributor.advisor | Setty, Vinay | |
dc.contributor.author | Le, Nguyen Khoa | |
dc.date.accessioned | 2020-09-27T18:45:50Z | |
dc.date.available | 2020-09-27T18:45:50Z | |
dc.date.issued | 2020-06-30 | |
dc.identifier.uri | https://hdl.handle.net/11250/2679791 | |
dc.description | Master's thesis in Computer science | en_US |
dc.description.abstract | The disinformation news in media channels such as social media websites or online newspapers has become a big challenge for many organizations, governments, and scientific researchers. In connection to fake news, the political bias (left-wing or right-wing) of the news articles are recently receiving more attention. In this thesis, we leverage the Adversarially Regularized AutoEncoder (ARAE) model, which enhances the adversarial autoencoder (AAE) by learning a parameterized prior as a Generative Adversarial Networks (GAN) to generate bias-flipped headlines. We perform the experiments with multiple datasets then discuss how these approaches contribute to the bias flipping and detecting problems. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | University of Stavanger, Norway | en_US |
dc.relation.ispartofseries | Masteroppgave/UIS-TN-IDE/2020; | |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.subject | informasjonsteknologi | en_US |
dc.subject | datateknikk | en_US |
dc.subject | GAN | en_US |
dc.subject | bias flipping | en_US |
dc.subject | ARAE | en_US |
dc.subject | Generative adversarial networks | en_US |
dc.subject | Autoencoder | en_US |
dc.title | Generative adversarial networks for bias flipping | en_US |
dc.type | Master thesis | en_US |
dc.subject.nsi | VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 | en_US |