Modeling Malicious Behaviors and Fake News Dissemination on Social Networks - Responsible AI and Analytics for an Ethical and Inclusive Digitized Society Access content directly
Conference Papers Year : 2021

Modeling Malicious Behaviors and Fake News Dissemination on Social Networks

Abstract

As social media has become widely used, fake news has become a serious problem. A representative countermeasure is fake news detection. However, this countermeasure is not sufficient because people using social media tend to ignore facts that contradict their beliefs. To develop effective countermeasures, it is necessary to clarify the influence of fake news and the nature of its dissemination from the perspective of communication. In this paper, we propose two models explaining the dissemination of opinions about fake news: one in which the presence of the ground truth is assumed and one in which it is not assumed. In both models, an attacker disseminates fake news by imitating or hijacking target accounts. In evaluations on real-world social networks, the model in which the ground truth is assumed demonstrates that, contrary to our expectations, account imitation is a more harmful attack than account hijacking. The model in which ground truth is not assumed demonstrates that both account imitation and account hijacking are harmful attacks.
Fichier principal
Vignette du fichier
512902_1_En_53_Chapter.pdf (771.82 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03648116 , version 1 (21-04-2022)

Licence

Attribution

Identifiers

Cite

Kento Yoshikawa, Masatsugu Ichino, Hiroshi Yoshiura. Modeling Malicious Behaviors and Fake News Dissemination on Social Networks. 20th Conference on e-Business, e-Services and e-Society (I3E), Sep 2021, Galway, Ireland. pp.643-655, ⟨10.1007/978-3-030-85447-8_53⟩. ⟨hal-03648116⟩
14 View
3 Download

Altmetric

Share

Gmail Facebook X LinkedIn More