A Probabilistic Model for Malicious User and Rumor Detection on Social Media
Files
Date
2020-01-07
Authors
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Narrator
Transcriber
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
Ending Page
Alternative Title
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.
Description
Keywords
Decision Making in Online Social Networks, probabilistic model, rumor detection, social media, user behavior
Citation
Extent
10 pages
Format
Geographic Location
Time Period
Related To
Proceedings of the 53rd Hawaii International Conference on System Sciences
Related To (URI)
Table of Contents
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Local Contexts
Collections
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.