Identification of Vortex Information. Detection of fake news eruption time



Słowa kluczowe:

fake news, harmful information, bigrams (letter pairs), fake news detection, information vortex, Big Data, AI, information refininig


The purpose of this study is to develop and validate a procedure known as the Information Vortex Indicator (IVI) for its effectiveness, designed to detect the timing of information vortex formation in textual data streams. Research has established that the formation of this vortex coincides with the onset of the dissemination of fake news (FN) concerning a particular object (such as a person, organization, company, event, etc.). The primary aim of this detection is to minimize the time required for an appropriate response or defense against the adverse effects of information turbulence caused by the spread of fake news. Methodology: The study used Big Data information resources analysis instruments (Gogołek, 2019, 2022), including selected statistical and artificial intelligence techniques and tools, to automatically detect vortex occurrence in real time. Experimental validation of the efficacy of these tools has been conducted, enabling a reliable assessment of the timing of vortex emergence. This assessment is quantified using the V-function, procedure, or test, which formally describes the IVI procedure. The V-function’s parameters are derived from the distribution patterns of letter pair clusters within the textual information stream. Conclusions: A comparison of manual (reference) and automatic detection of vortex emergence times confirmed an accuracy rate of over 80% in detecting the appearance of fake news. These results underscore the effectiveness of the IVI procedure and the utility of the selected tools for rapidly automating the detection of information vortices, which herald the propagation of fake news. Furthermore, the study demonstrates the applicability of IVI for the continuous monitoring of information with significant media value across multiple multilingual data streams. Originality: This research introduces a novel approach utilizing the distribution of letter pair clusters within information streams to detect the onset of information vortices, coinciding with the emergence of fake news. This methodology represents a unique contribution to the field, as prior research on this subject is limited.


Arutyunov, A., Borisov, L., Fedorov, S., Ivchenko, A., Kirina-Lilinskaya, E., Orlov, Y., Osminin, K., Shilin, S., & Zeniuk, D. (2016). Statistical Properties of European Languages and Voynich Manuscript Analysis. CoRR, abs/1611.09122. DOI:

Camps, J.-B., Clérice, T., & Pinche, A. (2021). Noisy medieval data, from digitized manuscript to stylometric analysis: Evaluating Paul Meyer’s hagiographic hypothesis. Digital Scholarship in the Humanities, 36(2), ii49–ii71. DOI:

Gogołek, W. (2006). Hit z komputera. Polityka, 45. Pobrane z

Gogołek, W., & Kuczma, P. (2013). Rafinacja informacji sieciowych na przykładzie wyborów parlamentarnych. Część 1. Blogi, fora, analiza sentymentów. Studia Medioznawcze, 2(53), 89–109.

Gogołek, W. (2019). Refining Big Data. Bulletin of Science. Technology & Society, 37(4), 212–217. DOI:

Gogołek, W. (2022). Big Data o mediach. Dominanty świata mediów. Studia Medioznawcze, 23(2), 1171–1180. DOI:

Gogołek, W., & Jaruga, D. (2016). Z badań nad systemem rafinacji sieciowej. Identyfikacja sentymentów. Studia Medioznawcze, 4(67), 103–111. DOI:

Gogołek, W., Jarzyńska, K., Żukowski, K., Wierzbicki, P., & Durlak, U. (2022). Citizen Big Data Refining on the example of the capital city of Warsaw. Urban Development Issues, 73, 08. DOI:

Gomes, H. M., Grzenda, M., Mello, R., Read, J., Le Nguyen, M. H., & Bifet, A. (2023). A Survey on Semi-supervised Learning for Delayed Partially Labelled Data Streams. ACM Computing Surveys, 55(4), 1–42. DOI:

Hirst, G., & Feiguina, O. (2007). Bigrams of Syntactic Labels for Authorship Discrimination of Short Texts. Literary and Linguistic Computing, 22(4), 405–417. DOI:

Huang, J. (2020). Detecting Fake News With Machine Learning. Journal of Physics: Conference Series, 1693, The 2020 3rd International Conference on Computer Information Science and Artificial Intelligence (CISAI) 2020 25-27 September 2020, Inner Mongolia, China. DOI:

Koczkodaj, W. W., Mazurek, M., Pedrycz, W., Rogalska, E., Roth, R., Strzalka, D.,… Zbyrowski, R. (2022). Combating harmful Internet use with peer assessment and differential evolution. 2022 International Conference on Electrical, Computer and Energy Technologies (ICECET), Prague, Czech Republic, 2022. DOI:

Litvinova, T. A., Seredin, P. V., & Litvinova, O. A. (2015). Using Part-of-Speech Sequences Frequencies in a Text to Predict Author Personality: a Corpus Study. Indian Journal of Science and Technology, 8(S9), 93–97. DOI:

Luo, M., & Mu, X. (2022). Entity sentiment analysis in the news: A case study based on Negative Sentiment Smoothing Model (NSSM). International Journal of Information Management Data Insights, 2(1), 100060. DOI:

Markov, A. A. (2006). An Example of Statistical Investigation of the Text Eugene Onegin Concerning the Connection of Samples in Chains. Science in Context, 19(4), 591–600. DOI:

Meel, P., & Vishwakarma, D. K. (2020). Fake news, rumor, information pollution in social media and web: A contemporary survey of state-of-the-arts, challenges and opportunities. Expert Systems with Applications, 153, 112986. DOI:

Meel, P., & Vishwakarma, D. K. (2021). A temporal ensembling based semi-supervised ConvNet for the detection of fake news articles. Expert Systems with Applications, 177, 115002. DOI:

Operation of police powers under the Terrorism Act 2000 and subsequent legislation: Arrests, outcomes, and stop and search, Great Britain, quarterly update to December 2022. (2023, March 9). Home Office. Retrieved June, 2023, from

Rohit, B. (2011, March 31). The 5 Models Of Content Curation. [Blog Post]. Retrieved from

Sanger, D., E., & Bumiller, E. (2011, May 31). Pentagon to Consider Cyberattacks Acts of War. The New York Times. Retrieved from

Sękiewicz, J. (2012). Łańcuchy Markowa i ich zastosowanie w filogenetyce. Praca magisterska na Wydziale Matematyki i Informatyki Uniwersytetu Jagiellońskiego. Pobrane z

Shawkat, N., Simpson, J., & Saquer, J. (2022). Evaluation of Different ML and Text Processing Techniques for Hate Speech Detection. 2022 4th International Conference on Data Intelligence and Security (ICDIS), Shenzhen, China, 2022, 213–219. DOI:

Školkay, A., & Filin, J. (2019). A Comparison of Fake News Detecting and Fact-Checking AI Based Solutions. Studia Medioznawcze, 20(4), 365–383. DOI:

Wang, T., Lu, K., Chow, K. P., & Zhu, Q. (2020). COVID-19 Sensing: Negative Sentiment Analysis on Social Media in China via BERT Model. IEEE Access, 8, 138162–138169. DOI:

Wierzbicki, P. (2022). Identyfikacja zmian frekwencji publikowanych wpisów na przykładzie Twittera. Segmentacja strumienia informacyjnego. Praca magisterska na kierunku studiów Zarządzanie Big Data na Wydziale Dziennikarstwa, Informacji i Bibliologii Uniwersytetu Warszawskiego.

Zhou, Z.-H. (2022). Open-environment machine learning. National Science Review, 9(8), nwac123. DOI:



Jak cytować

Gogołek, W. (2024). Identification of Vortex Information. Detection of fake news eruption time. Studia Medioznawcze, 25(1), 1–12.