NewsFire: Discovering the triggers for viral news stories

Sometimes mass-media, news agencies and social networks start to write, post and re-post a huge amount of information about a single event that can be both real and fake. Can we detect this waves at early stage, especially if the initial source was completely fake?

With the rapid grow of social networks and further development of automated and bot-like news-posting tools, the problem of digital wildfires - fast-spreading online misinformation have been identified as a considerable risk to developed societies. In this project we will investigate common triggers for digital wildfires and build the system is able to ring a bell in the very beginning of the upcoming news fire. While several approaches have been developed in the recent past, almost all of these attempts attack the problem purely from the technical side, generally using machine-learning techniques. Our approach differs in that we will study the problem from both sides, from the technical, but also form the human side of view aiming at understanding how people assess trustworthiness online, which content is likely to spread far, and why actors spread misinformation. The GDELT event monitoring and collection project will be used as the main source of data for analysis.


The goal of the thesis is to produce an algorithm that will be able to detect and point an the potential news digital wildfire ignition point (a particular news even) in real-time.

Learning outcome

During the course of this master thesis, the candidate will gain in-depth knowledge of Machine and Deep learning, Text analysis and BigData queries.


Python programming, Knowledge about machine learning and SQL is an advantage


  • Johannes Langguth
  • Konstantin Pogorelov


Contact person