000145143 001__ 145143
000145143 005__ 20241003094705.0
000145143 0247_ $$2doi$$a10.1075/ps.21009.fra
000145143 0248_ $$2sideral$$a129445
000145143 037__ $$aART-2022-129445
000145143 041__ $$aeng
000145143 100__ $$aFrancisco, Manuel
000145143 245__ $$aA semi-supervised algorithm for detecting extremism propaganda diffusion on social media
000145143 260__ $$c2022
000145143 5060_ $$aAccess copy available to the general public$$fUnrestricted
000145143 5203_ $$aExtremist online networks reportedly tend to use Twitter and other Social Networking Sites (SNS) in order to issue propaganda and recruitment statements. Traditional machine learning models may encounter problems when used in such a context, due to the peculiarities of microblogging sites and the manner in which these networks interact (both between themselves and with other networks). Moreover, state-of-the-art approaches have focused on non-transparent techniques that cannot be audited; so, despite the fact that they are top performing techniques, it is impossible to check if the models are actually fair. In this paper, we present a semi-supervised methodology that uses our Discriminatory Expressions algorithm for feature selection to detect expressions that are biased towards extremist content (Francisco and Castro 2020). With the help of human experts, the relevant expressions are filtered and used to retrieve further extremist content in order to iteratively provide a set of relevant and accurate expressions. These discriminatory expressions have been proved to produce less complex models that are easier to comprehend, and thus improve model transparency. In the following, we present close to 70 expressions that were discovered by using this method alongside the validation test of the algorithm in several different contexts.
000145143 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/BES-2017-081202$$9info:eu-repo/grantAgreement/ES/MINECO/FFI2016-79748-R
000145143 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000145143 590__ $$a0.8$$b2022
000145143 591__ $$aLINGUISTICS$$b126 / 193 = 0.653$$c2022$$dQ3$$eT2
000145143 592__ $$a0.434$$b2022
000145143 593__ $$aLinguistics and Language$$c2022$$dQ1
000145143 594__ $$a1.3$$b2022
000145143 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000145143 700__ $$0(orcid)0000-0001-8514-5943$$aBenítez Castro, Miguel Ángel$$uUniversidad de Zaragoza
000145143 700__ $$aHidalgo Tenorio, Encarnación
000145143 700__ $$aCastro, Juan Luis
000145143 7102_ $$13004$$2345$$aUniversidad de Zaragoza$$bDpto. Filolog.Inglesa y Alema.$$cÁrea Filología Inglesa
000145143 773__ $$g13, 3 (2022), 532-554$$pPragmatics and society$$tPragmatics and society$$x1878-9714
000145143 8564_ $$s714786$$uhttps://zaguan.unizar.es/record/145143/files/texto_completo.pdf$$yPostprint
000145143 8564_ $$s1709503$$uhttps://zaguan.unizar.es/record/145143/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000145143 909CO $$ooai:zaguan.unizar.es:145143$$particulos$$pdriver
000145143 951__ $$a2024-10-03-08:55:46
000145143 980__ $$aARTICLE