Extreme user and political rumor detection on Twitter
Files
(Restricted Access)
Date
2016
Authors
Chang, C.
Zhang, Y.
Szabo, C.
Sheng, Q.
Editors
Li, J.
Li, X.
Wang, S.
Li, J.
Sheng, Q.
Li, X.
Wang, S.
Li, J.
Sheng, Q.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Lecture Notes in Artificial Intelligence, 2016 / Li, J., Li, X., Wang, S., Li, J., Sheng, Q. (ed./s), vol.10086 LNAI, pp.751-763
Statement of Responsibility
Cheng Chang, Yihong Zhang, Claudia Szabo, and Quan Z. Sheng
Conference Name
12tth International Conference on Advanced Data Mining and Applications (ADMA) (12 Dec 2016 - 15 Dec 2016 : Gold Coast, Qld.)
Abstract
Twitter, as a popular social networking tool that allows its users to conveniently propagate information, has been widely used by politicians and political campaigners worldwide. In the past years, Twitter has come under scrutiny due to its lack of filtering mechanisms, which lead to the propagation of trolling, bullying, and other unsocial behaviors. Rumors can also be easily created on Twitter, e.g., by extreme political campaigners, and widely spread by readers who cannot judge their truthfulness. Current work on Twitter message assessment, however, focuses on credibility, which is subjective and can be affected by assessor’s bias. In this paper, we focus on the actual message truthfulness, and propose a rule-based method for detecting political rumors on Twitter based on identifying extreme users. We employ clustering methods to identify news tweets. In contrast with other methods that focus on the content of tweets, our unsupervised classification method employs five structural and timeline features for the detection of extreme users. We show with extensive experiments that certain rules in our rule set provide accurate rumor detection with precision and recall both above 80%, while some other rules provide 100% precision, although with lower recalls.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© Springer International Publishing AG 2016