Higher Ground? How Groundtruth Labeling Impacts Our Understanding of Fake News about the 2016 U.S. Presidential Nominees

  • Lia Bozarth University of Michigan
  • Aparajita Saraf University of Michigan
  • Ceren Budak University of Michigan

Abstract

The spread of fake news on social media platforms has garnered much public attention and apprehension. Consequently, both the tech industry and academia alike are investing increased effort to understand, detect, and curb fake news. Yet, researchers differ in what they consider to be fake news sites. In this paper, we first aggregate 5 lists of fake and 3 of mainstream news sites published by experts and reputable organizations. Then, focusing on tweets about the democratic (Hillary Clinton) and republican (Donald Trump) nominees in the 2016 U.S. presidential election, we use each pair of fake and traditional news lists as an independent “groundtruth” to examine i) the prevalence, ii) temporal characteristics and iii) the agenda-setting differences between fake and traditional news sites. We observe that depending on the groundtruth, the prevalence of fake news varies significantly. However, the temporal trends and agenda-setting differences between fake and mainstream news sites remain moderately consistent across different groundtruth lists.

Published
2020-05-26
How to Cite
Bozarth, L., Saraf, A., & Budak, C. (2020). Higher Ground? How Groundtruth Labeling Impacts Our Understanding of Fake News about the 2016 U.S. Presidential Nominees. Proceedings of the International AAAI Conference on Web and Social Media, 14(1), 48-59. Retrieved from https://www.aaai.org/ojs/index.php/ICWSM/article/view/7278