Rumor Identification and Verification on Social Media

Social media users spend many hours each day reading, posting, and searchingfor news on microblogging platforms. Social media has emerged as a key channel forinformation. However, the inherently unmoderated features of social media renderidentifying misinformation ever more challenging, hence locating sound informationcan be elusive. This thesis assesses the problem of rumor identification, verification,and proliferation on social media platforms. Our primary objective is to identifywhether the insights gained from this study can be used to build computationalsystems that can automatically identify and verify rumors between the emergenceperiod and after verification. We mainly investigate rumor phenomena associatedwith people, entities, or events of public interest. We study the impact of differenttypes of attributes in rumor identification, spread, and verification tasks, namely:level of committed belief, subjectivity, pragmatic, user provenance, meta-linguistic,and network propagation features.

Author

• Hamidian, Sardar

Language

• en

Keyword

• Disinformation
• Machine Learning
• Rumor
• Fake News
• Misinformation
• Social Media

Date created

• 2019

Type of Work

• Dissertation

License

• All rights reserved

Rights statement

• In Copyright

GW Unit

• Computer Science

Degree

• D.Sc.

Advisor

• Diab, Mona

Committee Member(s)

• Diab, Mona
• Youssef, Abdou
• Broniatowski, David
• Pless, Robert

Persistent URL

•  https://scholarspace.library.gwu.edu/etd/zk51vh54h