METHOD FOR DETECTING FAKE NEWS BASED ON NATURAL LANGUAGE PROCESSING

Authors

  • Liudmyla Mishchenko National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Ukraine
  • Valerii Simonenko National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Ukraine

Keywords:

Natural Language Processing technology, fake, manipulation, text analysis, Levenshtein distance

Abstract

The paper considers the method for detecting fake news based on Natural Language Processing (NLP) technology. NLP technology is used to divide text into tokens and parsing it. To compare similarity tokens, Levenstein's algorithm is used, as well as the coefficient of semantic similarity of words and phrases TF-IDF.

References

EU vs Disinfo. База даних ЄС зі спростованими фейками. Дата оновлення: 3.05.2020. URL: https://euvsdisinfo.eu/disinformation-cases/?text=Sputnik&date (дата звернення: 03.03.2020).

Natural Language Toolkit. Дата оновлення: 13.04.2020. URL: https://www.nltk.org (дата звернення: 10.03.2020).

Bird Steven. Natural Language Processing with Python / Bird Steven, Edward Loper and Ewan Klein: O’Reilly Media Inc, 2009 - ст. 87 - 93, 97 - 102.

The Levenshtein-Algorithm. URL: http://www.levenshtein.net (дата звернення: 17.03.2020).

Downloads

Published

2023-06-08

Issue

Section

Global Networks, Grid and Cloud