Interesting: OpenFact - detecting fake news
Department of Information Systems
Poznań University of Economics and Business
A team of scientists from the Department of Information Systems at the Poznań University of Economics and Business took part in the “CheckThat! 2024” organized as part of the international conference CLEF (Conference and Labs of the Evaluation Forum). The goal was to verify the robustness of popular text classification approaches used for credibility assessment problems.
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.
On February 27, 2024, Prof. Preslav Nakov from Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) visited the Department of Information Systems at the Poznań University of Economics and Business. During the meeting, the next stages of cooperation in the field of fake news detection using artificial intelligence were discussed.
An open scientific seminar of the Institute of Informatics and Quantitative Economics on automatic quality assessment of articles in multilingual Wikipedia and identification of important sources of its information on various topics was held at the Poznań University of Economics and Business. During the seminar, Dr. Włodzimierz Lewoniewski discussed the methods and tools used to analyze and evaluate content in a popular multilingual encyclopedia and ways of identifying and assessing … Read More
Members of our department, Ewelina Księżniak and Marcin Sawiński, took part in the 14th edition of the international CLEF conference, which is devoted to natural language processing and information retrieval. During this event, our scientists presented a method for detecting check-worthy claims, which achieved the best result in a competition organized by one of the workshops – CheckThat!Lab. The workshop and competition is devoted to detecting fake news using artificial … Read More
The 10th International Scientific Conference “Knowledge and Information Technologies in Creating Entrepreneurship” and the 5th Congress of Business Informatics were held on October 5-6, 2023. During this event, representatives of our Department presented research results on assessing the quality of student essays written by ChatGPT. This year’s edition of the conference and congress was held in a hybrid mode (onsite in Olsztyn near Częstochowa and remotely). The organizers of these … Read More
During the Didactic Conference at the Poznań University of Economics and Business, employees of the Department of Information Systems presented research results on the possibilities and limitations of generating texts using tools based on generative artificial intelligence, analyzing both the advantages and potential threats. The research was conducted based on the analysis of texts generated by ChatGPT as part of student essays.
The beginning of the academic year in the United States coincided with a speech by Dr. Włodzimierz Lewoniewski at Tufts University. The colloquium discussed issues related to the use of artificial intelligence and large open data sets to automate the process of assessing the quality of Wikipedia articles and its information sources in various language versions.
The scientific work of members of our Department was published in the Economics and Business Review journal. The article “Artificial intelligence – friend or foe in fake news campaigns” focuses on analyzing the impact of large language models (LLM) on the phenomenon of fake news. On the one hand decent text‐generation capabilities can be misused for mass fake news production. On the other, LLMs trained on huge volumes of text … Read More
The OpenFact project team took part in the CheckThat! organized as part of the international conference CLEF 2023 (Conference and Labs of the Evaluation Forum). The method proposed by our scientists took first place. This method detects English sentences that need to be reviewed because of potential misleading and therefore are worth fact-checking.