Back to Search
Start Over
Automatic Online Fake News Detection Combining Content and Social Signals
- Source :
- Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 426, Iss 22, Pp 272-279 (2018), FRUCT
- Publication Year :
- 2018
- Publisher :
- IEEE, 2018.
-
Abstract
- The proliferation and rapid diffusion of fake news on the Internet highlight the need of automatic hoax detection systems. In the context of social networks, machine learning (ML) methods can be used for this purpose. Fake news detection strategies are traditionally either based on content analysis (i.e. analyzing the content of the news) or - more recently - on social context models, such as mapping the news' diffusion pattern.<br />In this paper, we first propose a novel ML, fake news detection method which, by combining news content and social context features, outperforms existing methods in the literature, increasing their already high accuracy by up to 4.8%. Second, we implement our method within a Facebook Messenger chatbot and validate it with a real-world application, obtaining a fake news detection accuracy of 81.7%.
- Subjects :
- fake news
social networks
Facebook
Computer science
Twitter
Context (language use)
automatic hoax detection
02 engineering and technology
Logistics
computer.software_genre
Chatbot
Facebook , Twitter , Context modeling , Training , Logistics , Crowdsourcing
lcsh:Telecommunication
020204 information systems
lcsh:TK5101-6720
0202 electrical engineering, electronic engineering, information engineering
Context modeling
Training
Information retrieval
business.industry
Crowdsourcing
Settore ING-INF/05 - SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
machine learning
Content analysis
Content (measure theory)
020201 artificial intelligence & image processing
The Internet
Fake news
business
computer
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 426, Iss 22, Pp 272-279 (2018), FRUCT
- Accession number :
- edsair.doi.dedup.....de454fe7cb57ea239406abd072f6c8f9