SciELO - Scientific Electronic Library Online

 
vol.23 número3Recognizing Musical Entities in User-generated ContentCochlear Mechanical Models used in Automatic Speech Recognition Tasks índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

  • Não possue artigos similaresSimilares em SciELO

Compartilhar


Computación y Sistemas

versão On-line ISSN 2007-9737versão impressa ISSN 1405-5546

Resumo

JANICKA, Maria; PSZONA, Maria  e  WAWER, Aleksander. Cross-Domain Failures of Fake News Detection. Comp. y Sist. [online]. 2019, vol.23, n.3, pp.1089-1097.  Epub 09-Ago-2021. ISSN 2007-9737.  https://doi.org/10.13053/cys-23-3-3281.

Fake news recognition has become a prominent research topic in natural language processing. Researchers reported significant successes when applying methods based on various stylometric and lexical features and machine learning, with accuracy reaching 90%. This article is focused on answering the question: are the fake news detection models universally applicable or limited to the domain they have been trained on? We used four different, freely available English language Fake News corpora and trained models in both in-domain and cross-domain setting. We also explored and compared features important in each domain. We found that the performance in cross-domain setting degrades by 20% and sets of features important to detect fake texts differ between domains. Our conclusions support the hypothesis that high accuracy of machine learning models applied to fake news detection may be related to over-fitting, and models need to be trained and evaluated on mixed types of texts.

Palavras-chave : Fake news detection; cross-domain; cross-domain failures.

        · texto em Inglês     · Inglês ( pdf )