Detection of fake news in a new corpus for the Spanish language

Research output: Contribution to journalArticlepeer-review

77 Scopus citations

Abstract

We present a new resource to analyze and detect deceptive information that is present in a huge amount of news websites. Specifically, we compiled a corpus of news in the Spanish language extracted from several websites. The corpus is annotated with two labels (real and fake) for automatic fake news detection. Furthermore, the corpus also provides the category of the news, presenting a detailed analysis on vocabulary overlap among categories. Finally, we present a style-based fake news detection method. The obtained results showthat the introduced corpus is an interesting resource for future research in this area.

Original languageEnglish
Pages (from-to)4868-4876
Number of pages9
JournalJournal of Intelligent and Fuzzy Systems
Volume36
Issue number5
DOIs
StatePublished - 2019

Keywords

  • Corpus
  • Fake news
  • Machine learning
  • Resource
  • Spanish

Fingerprint

Dive into the research topics of 'Detection of fake news in a new corpus for the Spanish language'. Together they form a unique fingerprint.

Cite this