Study of different machine learning approaches for identification of fake news articles

In this document multiple machine learning approaches, including Supervised, Semi-supervised and Unsupervised learning are explored with the objective of finding the best algorithm for the task of identifying fake news. The corpus used consists on pure text data extracted from news articles. TF-IDF...

Descripción completa

Detalles Bibliográficos
Autor: Zurita Nicolas, Josep Ricard
Tipo de recurso: tesis de maestría
Fecha de publicación:2019
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/184331
Acceso en línea:https://hdl.handle.net/2117/184331
Access Level:acceso abierto
Palabra clave:Fake news
Machine learning
Aprenentatge automàtic
Aprenentatge automàtic -- Algorismes
Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario:In this document multiple machine learning approaches, including Supervised, Semi-supervised and Unsupervised learning are explored with the objective of finding the best algorithm for the task of identifying fake news. The corpus used consists on pure text data extracted from news articles. TF-IDF and word2vec features are studied. Python is used for the implementation