Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/137346
Title: Information management in healthcare and environment: Towards an automatic system for fake news detection
Author: Lara-Navarra, Pablo  
Falciani, Hervé
Sánchez Pérez, Enrique Alfonso
Ferrer-Sapena, Antonia  
Others: Universitat Politècnica de València
Tactical Whistleblower Association
Universitat Oberta de Catalunya. Estudis de Ciències de la Informació i de la Comunicació
Citation: Lara-Navarra, P. [Pablo], Falciani, H.[Hervé], Sánchez-Pérez, E. [Enrique]. & Ferrer-Sapena, A. [Antonia]. (2020). Information management in healthcare and environment: Towards an automatic system for fake news detection. International Journal of Environmental Research and Public Health, 17(3), 1-12. doi: 10.3390/ijerph17031066
Abstract: Comments and information appearing on the internet and on different social media sway opinion concerning potential remedies for diagnosing and curing diseases. In many cases, this has an impact on citizens¿ health and affects medical professionals, who find themselves having to defend their diagnoses as well as the treatments they propose against ill-informed patients. The propagation of these opinions follows the same pattern as the dissemination of fake news about other important topics, such as the environment, via social media networks, which we use as a testing ground for checking our procedure. In this article, we present an algorithm to analyse the behaviour of users of Twitter, the most important social network with respect to this issue, as well as a dynamic knowledge graph construction method based on information gathered from Twitter and other open data sources such as web pages. To show our methodology, we present a concrete example of how the associated graph structure of the tweets related toWorld Environment Day 2019 is used to develop a heuristic analysis of the validity of the information. The proposed analytical scheme is based on the interaction between the computer tool¿a database implemented with Neo4j¿and the analyst, who must ask the right questions to the tool, allowing to follow the line of any doubtful data. We also show how this method can be used. We also present some methodological guidelines on how our system could allow, in the future, an automation of the procedures for the construction of an autonomous algorithm for the detection of false news on the internet related to health.
Keywords: reinforcement learning
graph
healthcare
environment
fake news
DOI: 10.3390/ijerph17031066
Document type: info:eu-repo/semantics/article
Version: info:eu-repo/semantics/publishedVersion
Issue Date: 8-Feb-2020
Publication license: http://creativecommons.org/licenses/by/3.0/es/  
Appears in Collections:Articles

Files in This Item:
File Description SizeFormat 
ijerph-17-01066.pdf4,78 MBAdobe PDFThumbnail
View/Open