Our team recently analyzed the Veridica database, a complex set of fact-check articles. With a significant number of 617 entries extracted, some interesting patterns emerged regarding the most frequent terms and entities.
To structure and analyze the data, all statements were organized within a Neo4J graph. Each statement was linked to the entities involved, the channels through which information propagated, and relevant political figures.
Analyzing word frequency across various texts provides insights into the central themes and subjects of discussion. In our analysis, we have identified the three most highly connected entities: "Ukraine" with 422 connections, "Russia" with 366 connections, and "Romania" with 175 connections. This finding suggests a potential correlation between disinformation statements and the prevailing national sentiment among the populace.
Delving into the assessment of frequently used propagation channels, "ukraina.ru" emerges as the source of 68 disinformation statements within the dataset, closely followed by "sputnik.md" with 56, and "ria.ru" with 43.
Turning our attention to the most frequently mentioned individuals, we observe a notable decrease in frequency. The "Volodymyr Zelenskyy" node is connected to 30 disinformation statements, "Vladimir Putin" to 20, and "Igor Dondon" to 11.
It's important to note that rather than providing a definitive depiction of misinformation, this article offers a concise glimpse into the narratives explored by the Veridica organization. The emphasis on certain countries, individuals, or narratives within the dataset may influence the higher numbers associated with them.
For those seeking a more comprehensive understanding of propaganda narratives, their structure, interconnections, and origins, we encourage you to visit our website at www.discovery.mindbugs.ro. Our project is still in its early stages, and we aspire to contribute to the protection of democracy by enhancing the efficiency of fact-checking organizations and promoting transparency in information dissemination.
The MindBugs Discovery has indirectly received funding from the European Union’s Horizon 2020 research and innovation action programme, via the AI4Media Open Call #2 issued and executed under the AI4Media project (Grant Agreement no. 951911).
Any promotion made by the beneficiary about the project, in whatever form and by whatever medium reflects only the author’s views and that the EC or the AI4Media project is not responsible for any use that may be made of the information contained therein.