OpenFact is again the most effective in detecting fake news

The National Center for Research and Development has completed the evaluation of the results of the second phase of the INFOSTRATEG program. The evaluation included the results achieved by three competing teams whose task is to develop solutions for detecting fake news using artificial intelligence.

The OpenFact project implemented by scientists from the Department of Information Systems received the highest number of points and a positive assessment after the second phase of the project. Thus, it repeated the success from a year ago, when after the first phase it was also rated the best among all teams participating in the program. Thanks to a positive assessment, the team can start implementing the third and final phase of the project.

The OpenFact project has been implemented since 2021 by the team of the Department of Information Systems led by Prof. Witold Abramowicz, in cooperation with many technological and substantive partners, including: Google, Facebook, Bright Data, Mohamed bin Zayed University of Artificial Intelligence as well as leading fact-checking organizations in Poland. Members of the OpenFact project team: Prof. Krzysztof Węcel, Dr. Włodzimierz Lewoniewski, Dr. Milena Stróżyna, Ewelina Księżniak, Oskar Riewe-Perła, Marcin Sawiński, Aleksandra Wojewoda.

The results of the first two phases of the project are a data set containing examples of fake news and real information in Polish, which can be used to train artificial intelligence algorithms, and methods for detecting fake news trained on this set. The final solution of the project will be designed to work in Polish and will cover various thematic areas. Its task will be to inform users about the results of assessing the truthfulness and credibility of texts published on the Internet.

The OpenFact project is financed by the National Center for Research and Development under the INFOSTRATEG I program “Advanced information, telecommunications and mechatronic technologies”.