Institute for Web Science and Technologies · Universität Koblenz - Landau

Novelty and Misinformation Spread

[go to master theses]

Open Master Thesis - Contact a supervisor for more details!


Context: For the future of misinformation research, the behavior of users is the necessary counterpart to fake news existence and spreading, because the former factor can be the underlying source of the latter. A recent paper (1) suggests that the topical similarity between posting user, news content, and sharing user tends to enable misinformation spread, due to users who are biased in the same direction. Furthermore, in (3), evidence was provided that humans significantly contributed to false news spread. 

Aim: This thesis further takes into account how users will react to the novelty of news, and examines the added effect of such shocking or surprising news. The main challenge in this thesis will be to classify user homogeneity and news content novelty. 

Method: The student will i) develop a theoretical framework for detecting novelty (meaning that a news content has homogeneous topics but also an attention-grabbing new element).

ii) then identify a method that incorporates a novelty measure: to this end, inspiration can be drawn from (3), using topic modelling, which can be augmented with sentiment analysis. Eventually, the desing of a measure akin to a derivative could also be envisioned. 

Literature

  1. Kim, Jooyeon, Dongkwan Kim, and Alice Oh. "Homogeneity-Based Transmissive Process to Model True and False News in Social Networks." Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. ACM, 2019.

  2. Vargo, Chris J., Lei Guo, and Michelle A. Amazeen. "The agenda-setting power of fake news: A big data analysis of the online media landscape from 2014 to 2016." New Media & Society 20.5 (2018): 2028-2049.

  3. Soroush Vosoughi, Deb Roy, Sinan Aral, The spread of true and false news online, Science 09 Mar 2018 : 1146-1151

Supervisors

  • denigris@uni-koblenz.de
  • Scientific Employee
  • B 122
  • +49 261 287-2756
  • han@uni-koblenz.de
  • Scientific Employee
  • B 006
  • +49 261 287-2864