Show simple item record

dc.contributor.authorMartin-Gutierrez, Davides_ES
dc.contributor.authorHernandez-Penaloza, Gustavoes_ES
dc.contributor.authorHernandez, Alberto Belmontees_ES
dc.contributor.authorLozano-Diez, Alicia 
dc.contributor.authorAlvarez, Federicoes_ES
dc.contributor.otherUAM. Departamento de Tecnología Electrónica y de las Comunicacioneses_ES
dc.date.accessioned2022-10-31T16:06:00Zen_US
dc.date.available2022-10-31T16:06:00Zen_US
dc.date.issued2021-03-24en_US
dc.identifier.citationIEEE Access 9 (2021) 54591-54601en_US
dc.identifier.issn2169-3536 (online)en_US
dc.identifier.urihttp://hdl.handle.net/10486/704866en_US
dc.description© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other workses_ES
dc.description.abstractDuring the last decades, the volume of multimedia content posted in social networks has grown exponentially and such information is immediately propagated and consumed by a significant number of users. In this scenario, the disruption of fake news providers and bot accounts for spreading propaganda information as well as sensitive content throughout the network has fostered applied researh to automatically measure the reliability of social networks accounts via Artificial Intelligence (AI). In this paper, we present a multilingual approach for addressing the bot identification task in Twitter via Deep learning (DL) approaches to support end-users when checking the credibility of a certain Twitter account. To do so, several experiments were conducted using state-of-the-art Multilingual Language Models to generate an encoding of the text-based features of the user account that are later on concatenated with the rest of the metadata to build a potential input vector on top of a Dense Network denoted as Bot-DenseNet. Consequently, this paper assesses the language constraint from previous studies where the encoding of the user account only considered either the metadatainformation or the metadata information together with some basic semantic text features. Moreover, the Bot-DenseNet produces a low-dimensional representation of the user account which can be used for any application within the Information Retrieval (IR) frameworkes_ES
dc.format.extent11 pag.en_US
dc.format.mimetypeapplication/pdfen_US
dc.language.isoengen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc. (IEEE)en_US
dc.relation.ispartofIEEE Accessen_US
dc.rights© The author(s)en_US
dc.subject.otherArtificial intelligenceen_US
dc.subject.otherbot detectoren_US
dc.subject.otherdeep learningen_US
dc.subject.otherfeature representationen_US
dc.subject.otherlanguage modelsen_US
dc.subject.othermisinformation detectionen_US
dc.subject.othersocial media miningen_US
dc.subject.othertransfer learningen_US
dc.subject.othertransformersen_US
dc.titleA Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformersen_US
dc.typearticleen_US
dc.subject.ecienciaTelecomunicacioneses_ES
dc.relation.publisherversionhttps://doi.org/10.1109/ACCESS.2021.3068659en_US
dc.identifier.doi10.1109/ACCESS.2021.3068659en_US
dc.identifier.publicationfirstpage54591es_ES
dc.identifier.publicationlastpage54601es_ES
dc.identifier.publicationvolume9en_US
dc.type.versioninfo:eu-repo/semantics/publishedVersionen_US
dc.contributor.groupAudias - Audio, Data Intelligence and Speeches_ES
dc.rights.ccReconocimientoes_ES
dc.rights.accessRightsopenAccessen_US
dc.facultadUAMEscuela Politécnica Superiores_ES


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record