Título: Exploring Natural Language Processing for FakeNews Detection and Classification: A Comparative Analysis of Naive Bayes, SVM and XGBoost
Autores: Paulo Henrique Lira Jr, Luciano de Souza Cabral
Resumo: In the digital age, the spread of fake news has emerged as a significant issue, demanding the need for reliable and scalable solutions to preserve the trustworthiness of news sources and safeguard public opinion. This study proposes an exploration of the application of Natural Language Processing (NLP) techniques for the detection and categorization of fake news. Our specific focus lies on three widely used machine learning algorithms: Naive Bayes, Support Vector Machines (SVM), and XGBoost. By conducting a comprehensive evaluation of these approaches, our objective is to assess their effectiveness in identifying fake news articles and contribute to the development of robust tools for countering misinformation.
Palavras-chave: machine, learning, natural language processing, Naive Bayes, SVM, XGBoost, fake news
Páginas: 4
Código DOI: 10.21528/CBIC2023-117
Artigo em pdf: CBIC_2023_paper117.pdf
Arquivo BibTeX: CBIC_2023_117.bib