Progressive Detecting Rumors from Streams of Social Platforms

EDIC candidacy exam
Exam president: Prof. Boi Faltings
Thesis advisor: Prof. Karl Aberer
Co-examiner: Prof. Denis Gillet

Abstract
With the advance of social media networks, people are sharing contents in an unprecedented scale. This makes social networks such as microblogs an ideal place for spreading rumors. Although rumors can have severe impact on real-life world, traditional approaches in rumor detection tend to identify rumors after the rumors have been spread widely, which limit their effectiveness. In this work, we propose a progressive approach to detect rumors from streams of social platforms, which allows us to detect rumors early and correctly.

Bacground papers
Rumor cascades, by Friggeri A, et al.
Enquiring Minds: Early Detection of Rumors in Social Media from Enquiry Posts, by Zhao Z., et al.
Detecting rumors from microblogs with recurrent neural networks, by Ma, J., et al.