CYBERLINGUISTIC IDENTIFICATION OF A CYBERSPACE ACTOR BASED ON INTERFERENCE MARKS OF BILINGUALISM

Abstract

The article is devoted to the introduction and scientific substantiation of the concept of cyberlinguistic
identification as a method for determining the sociolinguistic profile of a cyberspace actor based on the analysis of
interference markers of their first language in written texts composed in a second language. A critical analysis of existing
scientific approaches – Native Language Identification, Author Profiling, and forensic linguistics – is performed. Their
conceptual and instrumental insufficiency for solving technical intelligence and cyber intelligence tasks is demonstrated
due to the lack of a holistic mathematical model and a primary focus on qualitative assessments or narrow educational
applications. A mathematical model of the state of a bilingual linguistic personality as a dynamic system is proposed. The
model formalizes the decay of interference marker intensity using a system of first-order differential equations, taking
into account the individual learning rate coefficient, language adaptation time, and normalized typological distance
between languages. Based on Shannon's information theory framework, the cognitive limitations of working memory
capacity, and empirical data, the residual interference hypothesis is substantiated: it is proven that the residual entropy of
native language markers fundamentally cannot equal zero in finite time, which provides the fundamental solvability of
the identification problem. A text feature vector space is formed, a Bayesian model for searching the sociolinguistic profile
is formulated, and the applicability boundaries of the method are defined as a function of text volume, duration of
adaptation, and language pair kinship. Practical results are oriented toward integration into cyber intelligence suites,
OSINT analytical systems, and tools for automated verification of information sources.
Keywords: cyberlinguistic identification, cyberspace actor, interference markers, bilingualism, mathematical
model, technical intelligence, cyber intelligence, linguistic distance, sociolinguistic profile.

References
1. Goswami D., Thilagan S., North K., Malmasi S., Zampieri M. 2024. Native Language Identification in Texts:
A Survey. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol. 1: Long Papers), P. 3149-3160, Mexico City, Mexico. Association for
Computational Linguistics. URL: https://aclanthology.org/2024.naacl-long.173/ https://doi.org/10.18653/v1/2024.naacllong.173.
2. Markov I, Nastase V, Strapparava C. Exploiting native language interference for native language identification.
Natural Language Engineering. 2022. Vol. 28 no. 2. P. 167-197. URL: https://doi.org/10.1017/S1351324920000595.
3. Bevendorff, J. et al. (2023). Overview of PAN 2023: Authorship Verification, Multi-Author Writing Style
Analysis, Profiling Cryptocurrency Influencers, and Trigger Detection: Condensed Lab Overview. In: Experimental IR
Meets Multilinguality, Multimodality, and Interaction (CLEF 2023). Lecture Notes in Computer Science, vol 14187.
Springer, Cham. https://doi.org/10.1007/978-3-031-42448-9_29.
4. Roemling D., Scherrer Y., Miletić A. Explainability of machine learning approaches in forensic linguistics: a
case study in geolinguistic authorship profiling. Proceedings of the 1st Workshop on NLP for AI, Cyber Security and
Forensic Linguistics (NLP4AICS 2024). Bangkok, Thailand: Association for Computational Linguistics, 2024. P. 1–12.
URL: https://doi.org/10.18653/v1/2024.nlp4aics-1.1.
5. Krashen S.D. Principles and Practice in Second Language Acquisition. Oxford: Pergamon Press, 1982. 202 p.
6. Jarvis S., Pavlenko A. Crosslinguistic influence in language and cognition. New York: Routledge, 2008. 264 p.
URL: https://doi.org/10.4324/9780203935927
7. Wichmann S. et al. The ASJP Database (v19). 2020. URL: https://asjp.clld.org
8. Cover T.M., Thomas J.A. Elements of Information Theory. 2nd ed. Wiley, 2006. 748 p.
9. Shannon C.E. A Mathematical Theory of Communication // Bell System Technical Journal. 1948. – Vol. 27. P.
379–423.
10. Baddeley A. Working Memory, Thought, and Action. Oxford University Press, 2007. 412 p.
11. Williams H., Blum I. Defining Second Generation Open-Source Intelligence (OSINT) for the Defense
Enterprise. – RAND Corporation, 2018. URL: https://doi.org/10.7249/RR1964.