Please use this identifier to cite or link to this item:

A Probabilistic Model for Malicious User and Rumor Detection on Social Media

File Size Format  
0249.pdf 2.89 MB Adobe PDF View/Open

Item Summary

Title:A Probabilistic Model for Malicious User and Rumor Detection on Social Media
Authors:Zhang, Yihong
Hara, Takahiro
Keywords:Decision Making in Online Social Networks
probabilistic model
rumor detection
social media
user behavior
Date Issued:07 Jan 2020
Abstract:Rumor detection in recent years has emerged as an important research topic, as fake news on social media now has more significant impacts on people's lives, especially during complex and controversial events. Most existing rumor detection techniques, however, only provide shallow analyses of users who propagate rumors. In this paper, we propose a probabilistic model that describes user maliciousness with a two-sided perception of rumors and true stories. We model not only the behavior of retweeting rumors, but also the intention. We propose learning algorithms for discovering latent attributes and detecting rumors based on such attributes, supposedly more effectively when the stories involve retweets with mixed intentions. Using real-world rumor datasets, we show that our approach can outperform existing methods in detecting rumors, especially for more confusing stories. We also show that our approach can capture malicious users more effectively.
Pages/Duration:10 pages
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections: Decision Making in Online Social Networks

Please email if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons