Research Projects

We actively participate in various media-related research projects. We conduct interdisciplinary studies on the broad topics of News Analytics, Data Journalism, and Misinformation.

Media in the Digital Age

We co-organize Media in the Digital Age, a special interest group coordinated by the Alan Turing Institute (UK). We host several events during the year with the goal of fostering interdisciplinary research and collaboration with media practitioners.

  • Mediate is a workshop on Social and News Media Misinformation held at the International AAAI Conference on Web and Social Media (ICWSM).
  • Framing is a colloquium on Narrative Framing and its Linguistic Forms in Online Media held at the Communication in Multicultural Society Conference (CMSC).


We participate in the National Research Programme Digital Transformation (NRP 77), in which we systematically analyze the news diet of young adults in Switzerland and examine what the changes mean for professional journalism.

Media Laboratory

Media Laboratory is a initiative aiming to develop data-journalism in Switzerland. We provide a virtual space (the Laboratory) for journalists, engineers and students to collaborate on data-visualization projects. The laboratory hosts the resulting visualizations, update them automatically and makes it easy to embed them in news articles. The initiative intends to lay the first stone of a long-term strategical collaboration across organizations by creating new bridges between academic institutions and the news industry.

The Laboratory is still under development and testing. However, you can find below a few examples of data-visualizations in the Swiss medias.

SciClops & SciLens

SciClops involves three main steps to process scientific claims found in online news articles and social media postings: extraction, clustering, and contextualization. First, the extraction of scientific claims takes place using a domain-specific, fine-tuned transformer model. Second, similar claims extracted from heterogeneous sources are clustered together with related scientific literature using a method that exploits their content and the connections among them. Third, check-worthy claims, broadcasted by popular yet unreliable sources, are highlighted together with an enhanced fact-checking context that includes related verified claims, news articles, and scientific papers. Extensive experiments show that SciClops assists effectively non-expert fact-checkers in the verification of complex scientific claims, outperforming commercial fact-checking systems.

SciClops Fact-Checking Context | Non-Experts + Context > Commercial Systems | Context => Confidence↑ Effort↑

SciLens is a framework for evaluating the quality of scientific news articles based on heterogeneous indicators. These indicators derive from: i) the content of articles, where we consider metrics such as clickbaitness, sentiment, and readability, and distinguish between attributed and unattributed quotes, ii) the scientific context of articles, where we measure the semantic textual similarity and the web-graph proximity to the related scientific literature, and iii) the social media context of articles, where we measure the audience's reach and stance. SciLens combines these indicators with expert reviews in a unified environment, bridging the gap between traditional and computational journalism. This augmented view of the articles has provably helped non-expert users to acquire better consensus about the quality of scientific news articles.

SciLens Indicators Overview | Indicators => Accuracy↑ | Replies Stance > Title Clickbaitness

  • [CIKM'21]
    SciClops: Detecting and Contextualizing Scientific Claimspaper
    Panayiotis Smeros, Carlos Castillo, Karl Aberer
  • [VLDB'20]
    SciLens News Platform: A System for Real-Time Evaluation of News Articlespaper
    Angelika Romanou, Panayiotis Smeros, Carlos Castillo, Karl Aberer
  • [WWW’19]
    SciLens: Evaluating the Quality of Scientific News Articlespaper
    Panayiotis Smeros, Carlos Castillo, Karl Aberer

Media Observatory

Media Observatory is a research effort for the automatic mapping of news sources based on their selection of subjects. By tracking sources' evolution over time, our model identifies driving forces, from the influence of ownership to large-scale content diffusion patterns. We release an open and interactive map based on these insights, which can be used by anyone, from viewers to journalists.

  • [WWW’19]
    A Dynamic Embedding Model of the Media Landscapepaper
    Jérémie Rappaz, Dylan Bourgeois, Karl Aberer
  • [WWW'18]
    Selection Bias in News Coverage: Learning it, Fighting itpaper
    Dylan Bourgeois, Jérémie Rappaz, Karl Aberer