E. I. Boychuk’s research while affiliated with Yaroslavl State University and other places

The article is devoted to the task of the sentiment detection towards an aspect of economic and social development in Russian sentences. The aspect, the attitude to which is determined, can be either explicitly mentioned or implied. The authors investigated possibilities of using neural network classifiers and proposed an algorithm for determining the sentiment towards an aspect based on semantic rules implemented with the use of constituency trees. The sentiment towards an aspect is determined in two stages. At the first stage, aspect terms (explicitly mentioned events or phenomena associated with the aspect) are found in the sentence. At the second stage, the sentiment towards an aspect is calculated as the sentiment towards the aspect term that is most closely associated with the aspect. The paper proposes several methods for searching the aspect terms. The performance was assessed on a corpus of 468 sentences extracted from election campaign materials. The best result for neural network classifiers was obtained using the BERT-SPC neural network pretrained on the task of identifying the sentiment towards an explicitly mentioned aspect, the macro F-score was 0.74. The best result for the semantic rule-based algorithm was obtained using the method of aspect term searching based on semantic similarity, the macro-F-score was 0.63. When combining BERT-SPC and the rule-based algorithm into an ensemble, the macro-F-score was 0.79, which is the best result obtained in this work.

The article presents an analysis of English-language sports news journalism from the point of view of the implementation of lexical-grammatical and stylistic means of speech expressiveness in the texts. The research is conducted on the material of modern American journalism presented in the Internet and is focused on the search for the most frequent and active stylistic means that allow to reveal the mechanisms of influence of information material on the consumer, whose impression of the provided information is formed depending on the degree of accuracy of transmission and emotional presentation of the material. The article includes a theoretical section, which is devoted to the specifics of sports discourse in general, its functions, the main means of conveying the expressiveness of the text, as well as the research part, which includes the analysis of the main lexical-grammatical and stylistic means, statistics of their use and linguistic features, supported by many examples. The main result of the research has been the conclusion that stylistic means of expressiveness account for about 50% of all existing techniques. The most active are metonymy and epithets. Grammatical means are represented to a much lesser extent.

The article focuses on the study of trans-media in the aspect of linguistic pragmatics and translation studies. The main emphasis of the study is on the Wanda/ Vision line of the multimodal fictional MARVEL universe, represented by comics and TV series. The authors come to the conclusion that the key strategy of translating texts included in the trans-media system should be recognized as adherence to the canon, which guarantees the character and narrative framework recognizability, creates the impression of the wholeness of the trans-media project, and provides the depth of aesthetic experience for the viewer, reader, and fan of the trans-media universe. On the pragmalinguistic plane, the canon definitely includes the semantic and stylistic dominants of the transmedia discourse, formed from the intersections of the dominants of the texts and discourses that form the elements of the project. In the tactical aspect, the translator should be guided by the rules of translation of audiovisual works of the genres that form the trans-media project. Thus, in the context of translating content related to the Wanda/ Vision line, these are, first of all, the rules of translating comics and feature film text.

The article is devoted to the task of sentiment detecton of Russian sentences, which is understood as the author’s attitude on the sentence topic expressed through linguistic expression features. Today most studies on this subject utilize texts of colloquial style, limiting the applicability of their results to other styles of speech, particularly to the publicism. To fill the gap, the authors developed a novel publisism sentences oriented sentiment detection algorithm. The algorithm recursively applies appropriate rules to sentence parts represented as constituency trees. Most of the rules were proposed by a philology expert, based on knowledge on the expression features from Russian philology, and algorithmized using constituency trees generated by the algorithm. A decision tree and a sentiment vocabulary are also used in the work. The article contains the results of evaluation of the algorithm on the publicism sentences corpus OpenSentimentCorpus, F-measure is 0.80. The results of errors analysis are also presented.

Построен алгоритм поиска и статистического анализа ритмических средств в тексте. Выявлены характеристики по векам с 19 до 21 вв. Определена частотность и специфика употребления средств для каждой эпохи.