Fake news detection on Twitter using a data mining framework based on explainable machine learning techniques

Vista sencilla de ítem
dc.contributor.authorPuraivan, E.
dc.contributor.authorGodoy, E.
dc.contributor.authorRiquelme, F.
dc.contributor.authorSalas, R.
dc.date.accessioned2022-11-30T02:46:49Z
dc.date.available2022-11-30T02:46:49Z
dc.date.issued2021
dc.description.abstractOnline social networks are a powerful communication and information dissemination tool, particularly useful in complex scenarios such as social crises, natural disasters, and pandemics. However, one of the main problems, especially in socio-political crises, is the automatic detection of fake news. This problem is usually addressed with greater or lesser success using supervised machine learning techniques. In this work, we propose a mixed approach, using unsupervised learning for feature extraction, and supervised learning for the prediction of fake news on microblogging networks. We consider Twitter news with linguistic and network features. To identify hidden patterns in the data, we use Principal Component Analysis and t-Distributed Stochastic Neighbor Embedding. The results show that the data can be better classified using non-linear rather than linear separability. Moreover, when using Extreme Gradient Boosting (XGBoost), an accuracy of 99.26% is obtained, and the most relevant features are identified.en_ES
dc.facultadFacultad de Ingenieríaen_ES
dc.file.namePuraivan_Fak2021.pdf
dc.identifier.citationE. Puraivan, E. Godoy, F. Riquelme and R. Salas, "Fake news detection on Twitter using a data mining framework based on explainable machine learning techniques," 11th International Conference of Pattern Recognition Systems (ICPRS 2021), 2021, pp. 157-162, doi: 10.1049/icp.2021.1450.en_ES
dc.identifier.doihttps://dx.doi.org/10.4067/S0718-330520210001001411
dc.identifier.isbn9781839534300
dc.identifier.urihttp://repositoriobibliotecas.uv.cl/handle/uvscl/7502
dc.languageen
dc.publisherIEEE
dc.source11th International Conference of Pattern Recognition Systems (ICPRS 2021)
dc.subjectTWITTERen_ES
dc.subjectFAKE NEWSen_ES
dc.subjectSOCIAL CRISISen_ES
dc.subjectEXPLAINABLE MACHINE LEARNINGen_ES
dc.subjectDATA MININGen_ES
dc.titleFake news detection on Twitter using a data mining framework based on explainable machine learning techniques
dc.typeArticulo
uv.departamentoEscuela de Ingenieria Informatica
uv.notageneralNo disponible para descarga

Archivos

Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Puraivan_Fak2021_noaccesible_.pdf
Tamaño:
952.11 KB
Formato:
Adobe Portable Document Format
Descripción:
Descargar

Colecciones

Artículos investigadores UV