04619ntm a22006137i 4500 000725228 CZ-PrVSE 20250824103944.0 m d cr n|||||||||| 250824s2025 xr fsbm 000 0 eng d NEZPRACOVANÝ IMPORT ABA006 cze ABA006 ABA006 rda Mládek, Richard ISIS:169854 dis Detekce a interpretabilita argumentačních vzorců ve fact-checkingových reportech pomocí LLMs eng Detection and explanation of misinformation patterns in fact-checked claims using LLMs / Richard Mládek 2025 ?? stran : digital, PDF soubor Vedoucí práce: Kateřina Haniková Bakalářská práce (Bc.)—Vysoká škola ekonomická v Praze. Fakulta informatiky a statistiky, 2025 Obsahuje bibliografii Textový (vysokoškolská kvalifikační práce) Rok obhajoby 2025 This bachelor's thesis explores automated approaches to combating misinformation. It proposes a method for modeling argumentation in fact-checked claims using entity graphs and large language models (LLMs). The source dataset consists of 50 fact-check reports from the PolitiFact website. The argumentation in each report was analysed during an annotation campaign conducted by a team from VŠE. Annotators classified misleading claims based on predefined misinformation patterns in a Catalogue of Misinformation Patterns and created brief summaries of the argumentation in each fact-check report. The automated misinformation pattern detection approach proposed in this thesis achieved an exact agreement with annotators in 46% of reports, with an additional 36% of cases where the model proposed partially matching misinformation patterns. Evaluation of a wide selection of LLMs demonstrated that the Gemini 2.5 Pro model, created by Google, performed best in argumentation modeling. The experiments revealed that some examined claims are more challenging to model automatically than others. Based on this observation, a set of parameters that determine the complexity of a fact-check report is proposed. This metric has the potential to serve as an indicator of how confident we can be in an LLM's automated decision. To improve the interpretability of argumentation in fact-check reports, a method for automatically sketching entity graphs using LLMs is presented. Preliminary experiments indicate that this approach shows promise, with automatically generated graphs often approaching the quality of those created manually by human annotators. This thesis demonstrates that it is possible to model argumentation within fact-check reports fully automatically. The proposed approach has the potential to be used for evaluating the quality of fact-check reports, which could enable fully automated refutation of examined problematic claims in the future. Additionally, it improves the interpretability of argumentation in fact-checked claims. Způsob přístupu: Internet data analytics [obor bakal. práce] bakalářské práce fd132403 czenas bachelor's theses eczenas fact-checking entity graphs large language models argumentation misinformation interpretability Haniková, Kateřina ISIS:133094 ths Zamazal, Ondřej ISIS:7282 opn Vysoká škola ekonomická v Praze. Fakulta informatiky a statistiky kn20010709399 dgg https://insis.vse.cz/zp/91512/podrobnosti VŠKP v InSIS https://insis.vse.cz/zp/91512 Hlavní práce https://insis.vse.cz/zp/91512/posudek/vedouci Hodnocení vedoucího https://insis.vse.cz/zp/91512/posudek/oponent/88041 Oponentura https://insis.vse.cz/zp/91512/priloha/32290 Přiloha k práci https://insis.vse.cz/zp/91512/priloha/32291 Přiloha k práci https://insis.vse.cz/zp/91512/priloha/32292 Přiloha k práci https://insis.vse.cz/zp/91512/priloha/32293 Přiloha k práci https://insis.vse.cz/zp/91512/priloha/32294 Přiloha k práci https://insis.vse.cz/zp/91512/priloha/32295 Přiloha k práci https://insis.vse.cz/zp/91512/podrobnosti dc:identifier NEPOSILAT VSKP vse91512 250822 91512