Computational Linguistics Based Identification of Regional Features of the Russian Language

The master's thesis is made on 76 pages, contains 24 sources of literature, as well as 2 appendices. The purpose of the study is to identify the linguistic features of Russian-language materials in foreign media using computer linguistics. The object of the study is Russian-language materials from foreign media available on web resources. The subject of the study is to identify the linguistic features of Russian-language materials in foreign media. As a result of the study, a collection of texts from Russian-language media in Kyrgyzstan was collected with a volume of approximately 5 million word usages. Also, using computer linguistics, a study of the characteristics of the collected material was carried out. Analysis of statistical metrics showed the differences between the Russian language of the Kyrgyz media and the Russian media and confirmed the special nature of the Russian language of diasporas in the post-Soviet space. The study showed greater conservatism of the Russian language in the Kyrgyz media compared to the texts of Russian media, as well as a tendency to replace Russian words related to the sphere of socio-political life with their synonyms in the national language.