USING MACHINE LEARNING IN DETECTING FAKE NEWS

Ștefan Bolotä‚ () and Mircea Asandului ()
Additional contact information
Ștefan Bolotä‚: Alexandru Ioan Cuza University of IaÅŸi, Faculty of Economics and Business Administration, IaÅŸi, Romania,
Mircea Asandului: Alexandru Ioan Cuza University of IaÅŸi, Faculty of Economics and Business Administration, IaÅŸi, Romania

Review of Economic and Business Studies, 2022, issue 30, 53-66

Abstract: In a world that has been greatly affected by the Coronavirus pandemic and more recently by the armed conflict between Russia and Ukraine, the flow of information is constantly increasing and at the same time the veracity of this information raises a big concern, and this makes the topic of fake news a problem of major interest. Our paper proposes a tool for fake news detection using different models of machine learning developed over a Fake News Corpus. Neural networks have proven to be the most effective method, reaching an accuracy of over 90%, but also Naive Bayes can be an excellent solution for classifying text data. Besides these two, we also developed and analyzed other models based on Naive Bayes and k-Nearest Neighbors. The results are promising and show that the problem of fake news can be managed by machine learning algorithms.

Keywords: fake news detection; neural networks; machine learning; artificial intelligence; natural language processing; Naive Bayes (search for similar items in EconPapers)
JEL-codes: C45 C63 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://rebs.feaa.uaic.ro/articles/pdfs/332.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aic:revebs:y:2022:j:30:bolotas

DOI: 10.47743/rebs-2022-2-0004

Access Statistics for this article

More articles in Review of Economic and Business Studies from Alexandru Ioan Cuza University, Faculty of Economics and Business Administration Contact information at EDIRC.
Bibliographic data for series maintained by Sireteanu Napoleon-Alexandru ().