In the modern era, social media has taken off, and more individuals may now utilise it to communicate and learn about current events. Although people get much of their information online, some of the Internet news is questionable and even deceptively presented. It is harder to distinguish fake news from the real news as it is sent about in order to trick readers into believing fabricated information, making it increasingly difficult for detection algorithms to identify fake news based on the material that is shared. As a result, an urgent demand for machine learning (ML), deep learning, and artificial intelligence models that can recognize fake news arises. The linguistic characteristics of the news provide a simple method for detecting false news, which the reader does not need to have any additional knowledge to make use of. We discovered that NLP techniques and text-based word vector representation may successfully predict fabricated news using a machine learning approach. In this paper, on datasets containing false and genuine news, we assessed the performance of six machine learning models. We evaluated model performance using accuracy, precision, recall, and F1-score.

Machine Learning Technique for Fake News Detection Using Text-Based Word Vector Representation

Castiglione, Arcangelo;
2021-01-01

Abstract

In the modern era, social media has taken off, and more individuals may now utilise it to communicate and learn about current events. Although people get much of their information online, some of the Internet news is questionable and even deceptively presented. It is harder to distinguish fake news from the real news as it is sent about in order to trick readers into believing fabricated information, making it increasingly difficult for detection algorithms to identify fake news based on the material that is shared. As a result, an urgent demand for machine learning (ML), deep learning, and artificial intelligence models that can recognize fake news arises. The linguistic characteristics of the news provide a simple method for detecting false news, which the reader does not need to have any additional knowledge to make use of. We discovered that NLP techniques and text-based word vector representation may successfully predict fabricated news using a machine learning approach. In this paper, on datasets containing false and genuine news, we assessed the performance of six machine learning models. We evaluated model performance using accuracy, precision, recall, and F1-score.
2021
978-3-030-91433-2
978-3-030-91434-9
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11386/4856384
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 6
social impact