The Database of Known Fakes: a Valuable EU Research Result to Streamline Fact-checking

EU research and innovation portal CORDIS features the Database of Known Fakes as a helpful tool in verification workflows

New York, Sofia, Basel Monday, December 4, 2023

As advances in AI have made it far easier to generate and spread fake news all over the digital space, EU-backed projects like are working hard to help journalists, fact-checkers, and researchers. They provide relevant AI-driven instruments to combat disinformation across modalities and languages. Among the helpful systems in this toolbox comes in the Database of Known Fakes (DBKF for short), as highlighted in a dedicated article on the Scientific Advances section of the CORDIS EU research portal.

Ontotext started developing DBKF within another EU-supported project, WeVerify, to answer the needs of verification experts for gathering already debunked claims in one place and enabling search over this collection. Approaching the solution of this task through a semantic data store appeared as a natural fit, given the diverse modalities of content in debunking articles (text, images, videos) that have to be uniformly stored and efficiently queried. 

Additionally, advanced text analysis and image processing methods are applied to enrich the content and enable meaningful searches. This is how the DBKF came to life, powered by Ontotext’s graph database GraphDB and built on the well-established ontology of

DBKF offer is a powerful search tool that enables users to find relevant debunks not only through keyword search but also based on multi-media content (image, video) and gathered metadata. This includes mentions of general concepts such as people, locations, organizations and other topics of interest. 

Another valuable search option is the multilingual search, which retrieves results for a query in several languages at once. This unlocks greater insights into disinformation narrative spread across different contexts and geographies. Notably, the award-winning InVID-WeVerify plugin has also integrated DBKF’s search functionalities. A fairly detailed walkthrough of DBKF capabilities is available in a demo video, posted on the YouTube channel.

The database continues to be enhanced in alignment with the most pertinent user needs and contributes to the fight against disinformation on the broader EU level, and at a regional scale as part of the Bulgarian-Romanian EDMO hub, BROD. It is also a great example of how knowledge graphs and semantic technologies can bring value not only to business users but also to a wide range of other stakeholders.

If you want to learn more about partners’ commitment to the topic of fighting disinformation and to be the first to learn about project contributions at the European level, follow the consortium’s Twitter and YouTube channels.

DBKF has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No:825297, from Horizon Europe research and innovation programme under grant agreement No:101070093, and from Digital Europe programme under grant agreement No:101083730. Views and opinions expressed are however those of the author only and do not necessarily reflect those of the European Union or the European Research Executive Agency. Neither the European Union nor the granting authority can be held responsible for them.

For more information, contact Doug Kimball, Chief Marketing Officer at Ontotext