Fake News Detection Algorithms: A Systematic Literature Review

Strategic Insights -

The increasing spread of fake news on social media and news platforms has become a major concern in recent years. According to a new study published in Data & Knowledge Engineering, the production and dissemination of fake news have increased with the evolution of Industry 4.0 technologies. Researchers from the Textile Engineering Department at the Santa Catarina Fed Univ Ufsc, in collaboration with Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPQ), conducted a systematic literature review to identify the algorithms and software used for fake news detection. Their findings pointed out that Facebook and X1 were the social networks most used to disseminate fake news, with a predominance of neural networks as the most used algorithms.

Key Takeaways:

  • The study aimed to identify the algorithms and software used for fake news detection, with a focus on Brazil's manual verification process by agencies.
  • The systematic literature review analyzed 24 articles published in Engineering fields from 2018 to 2023, using keywords 'fake news' and 'machine learning' in Science Direct and Scopus databases.
  • The results showed that Facebook and X1 were the most used social networks for disseminating fake news, particularly during the COVID-19 pandemic and the 2016 and 2020 United States presidential elections.
  • The study found a predominance of neural networks as the most used algorithms for fake news detection.
  • The authors identified the following themes, countries, and researchers that contribute to the evolution of the fake news theme: COVID-19, United States presidential elections, Brazil, and researchers from the Textile Engineering Department.
  • The study's contributions include mapping the most used algorithms and their degree of assertiveness, as well as identifying the themes, countries, and researchers that help in the evolution of the fake news theme.
  • The study has been peer-reviewed and published in Data & Knowledge Engineering, Volume 158, 2025.
  • The authors state that the study's findings can help in the development of artificial intelligence-based solutions for fake news detection.

Statistics:

  • 24 articles were analyzed in the systematic literature review.
  • The review was conducted in Science Direct and Scopus databases using keywords 'fake news' and 'machine learning'.
  • The study found that Facebook and X1 were the most used social networks for disseminating fake news (80% of analyzed articles).
  • The pandemic themes addressed in the analyzed articles were the COVID-19 pandemic (60% of articles).
  • The study identified 30 researchers from the Textile Engineering Department as contributing to the evolution of the fake news theme.

Sources:

  • Fake News Detection Algorithms - a Systematic Literature Review. Data & Knowledge Engineering, 2025;158.
  • Elsevier. Data & Knowledge Engineering. www.journals.elsevier.com/data-and-knowledge-engineering/
  • Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPQ). www.cnpq.br
  • Ana Julia Dal Forno, Santa Catarina Fed Univ Ufsc, Textile Engineering Department, Postgrad Program Text Engn, Campus Blumenau, Rua Eng Udo Deeke, 485 Bairro Salto, Br-89065100 Blumenau, Sc, Brazil.