The widespread of false information represents an open issue in the research, due to the heavy consequences in several contexts. Therefore, several detection methodologies have been developed to discern reliable information from false ones and provide different tools to support the users. There exists four principal methods: Knowledge-Based, Style-Based, Network-Based, and Source-Based. Moreover, the analysis of social features on networks allows to identify the reliability of information and represents a helpful tool for improving the classification of disinformation. For this reason, this work aims to propose a detection architecture able to identify false information and to analyze information diffusion through epidemiological models. Numerical tests on real data support the effectiveness and reliability of the proposed approaches.
Disinformation detection and diffusion analysis through a modified SEIR model
Angelamaria Cardone;Patricia Diaz de Alba
;Beatrice Paternoster
2023-01-01
Abstract
The widespread of false information represents an open issue in the research, due to the heavy consequences in several contexts. Therefore, several detection methodologies have been developed to discern reliable information from false ones and provide different tools to support the users. There exists four principal methods: Knowledge-Based, Style-Based, Network-Based, and Source-Based. Moreover, the analysis of social features on networks allows to identify the reliability of information and represents a helpful tool for improving the classification of disinformation. For this reason, this work aims to propose a detection architecture able to identify false information and to analyze information diffusion through epidemiological models. Numerical tests on real data support the effectiveness and reliability of the proposed approaches.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
