Abstract
Political scientists are concerned about the impact of fake news (a.k.a. misinformation) on democracy, while fake news could also escalate to life-threatening problems, e.g. UNESCO states that during COVID-19 pandemic fake news is putting lives at risk. Fake news continues to spread, so does people’s behaviour and emotions about fake news via social media platforms.Cyber-criminals take advantage of people’s emotional and behavioural aspects to conduct cyber-attacks (e.g. phishing) via fake news. We investigate how people’s behaviour and emotions influence on falling for fake news in social media, and propose a classification model incorporating these features to better detect fake news. Experiments conducted on five datasets reveal strong correlations between emotional and behavioural features and validate the efficacy of our model in terms of improved prediction accuracy. The findings of our study can ultimately be used to predict risk scores of news in social media.
Original language | English |
---|---|
Journal | Preprints |
Publication status | Submitted - 2021 |
Externally published | Yes |