Early Detection of Online Misinformation using Deep Learning and Knowledge Graphs

Develop and evaluate techniques that use deep learning-based natural language processing and reasoning over knowledge graphs for the detection of online misinformation and fake news.
Master

Keywords: Social Cybersecurity, Natural Language Processing, Knowledge Graphs

Description: The spread of misinformation is one of the rapidly growing and concerning trends in today's social media. It has become a challenge to evaluate the authenticity of news items, and limit the effects of misinformation. Misinformation can affect people in various aspects; from incorrect healthcare advice to manufactured political agendas. The goal of this project is to support the analysis of misinformation on social media.

Goal

The goal is to develop and evaluate techniques that use deep learning-based natural language processing and reasoning over knowledge graphs for the early detection of misinformation and fake news in social media that will help to limit the impact of such misinformation campaigns.

Learning outcome

  • Application of misinformation/fake-news detection in social media context
  • Proficiency with techniques for natural language processing and inference over knowledge graphs
  • Gain an appreciation for the state of the art in analyzing misinformation/fake-news
  • Experience with working in an exciting and active research environment
  • Excellent opportunities to publish your research results in the form of a scientific publication

Qualifications

  • Interested in misinformation/fake-news detection and social cybersecurity
  • Interested in machine learning, in particular deep learning, natural language processing, and semantic text analysis
  • Preferably knowledge of python and LaTeX.

Supervisors

  • Sehrish Malik
  • Leon Moonen

References

  • K. M. Carley, “Social cybersecurity: an emerging science,” Comput Math Organ Theory, vol. 26, no. 4, pp. 365–381, Dec. 2020, doi: 10.1007/s10588-020-09322-9.

Contact person