Automatic Extraction of Rhythm Figures and Analysis of Their Dynamics in Prose of 19th-21st Centuries

Lagutina, Ksenia; Poletaev, Anatoliy Yurievich; Lagutina, Nadezhda; Boychuk, Elena; Paramonov, Ilya

doi:10.23919/fruct48808.2020.9087430

Cited by 14 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…В данном исследовании используются лексико-грамматические средства: анафора, эпифора, симплока, анадиплозис, эпаналепсис, многосоюзие, диакопа, эпизевксис, хиазм, апозиопеза, повторяющиеся вопросительные и восклицательные предложения. Определения ритмических средств и алгоритмы их поиска приведены в предыдущих работах авторов [9,10]. Апозиопеза и повторяющиеся вопросительные и восклицательные предложения основываются на появлениях знаков препинания.…”

Section: ритмические характеристикиunclassified

“…Для обоих способов применялись одни и те же классификаторы: • классификатор AdaBoost -мета-алгоритм машинного обучения, который объединяет результаты 50 классификаторов-деревьев решений, корректирующих неправильно классифицированные тексты; • двунаправленная LSTM -рекуррентная нейронная сеть со слоем двунаправленной долгой краткосрочной памяти (LSTM) с 64 блоками и полносвязным выходным слоем, использующим функцию активации Softmax для мультиклассовой классификации и Sigmoid для бинарной; • GRU -рекуррентная нейронная сеть со слоем Gated Recurrent Unit (GRU) с 4 блоками и полносвязным выходным слоем, использующим функцию активации Softmax для мультиклассовой классификации и Sigmoid для бинарной. Данные классификаторы уже доказали свое качество в решении современных задач обработки ритма текстов [9,10], поэтому они были выбраны для экспериментов.…”

Section: классификация по жанрамunclassified

“…Полученные результаты по количеству ритмических средств в текстах разных жанров позволяет судить о ритмической специфике того или иного жанра в рамках одного языка. В русском языке, в котором по сравнению с другими языками, как показали ранние исследования [9], частотность ритмических средств ниже, чем в других языках, что подтверждают показатели по жанрам. Это безусловно связано с языковой спецификой, типологическими особенностями языка, в особенности с критериями частеречной классификации.…”

Section: обсуждение результатов с лингвистической точки зренияunclassified

“…В своих работах авторы данного исследования предложили комплекс высокоуровневых параметров художественного текста, основанных на фигурах речи образуемых повторением слов и словосочетаний [9,10]. Эти параметры описывают ритм текста, который позволяет выявить уникальный авторский стиль и успешно классифицировать тексты по времени и авторам.…”

Section: Introductionunclassified

See 3 more Smart Citations

Text Classification by Genre Based on Rhythm Features

Lagutina

Boychuk

2021

Model. anal. inf. sist.

View full text Add to dashboard Cite

The article is devoted to the analysis of the rhythm of texts of different genres: fiction novels, advertisements, scientific articles, reviews, tweets, and political articles. The authors identified lexico-grammatical figures in the texts: anaphora, epiphora, diacope, aposiopesis, etc., that are markers of the text rhythm. On their basis, statistical features were calculated that describe quantitatively and structurally these rhythm features.The resulting text model was visualized for statistical analysis using boxplots and heat maps that showed differences in the rhythm of texts of different genres. The boxplots showed that almost all genres differ from each other in terms of the overall density of rhythm features. Heatmaps showed different rhythm patterns across genres. Further, the rhythm features were successfully used to classify texts into six genres. The classification was carried out in two ways: a binary classification for each genre in order to separate a particular genre from the rest genres, and a multi-class classification of the text corpus into six genres at once. Two text corpora in English and Russian were used for the experiments. Each corpus contains 100 fiction novels, scientific articles, advertisements and tweets, 50 reviews and political articles, i.e. a total of 500 texts. The high quality of the classification with neural networks showed that rhythm features are a good marker for most genres, especially fiction. The experiments were carried out using the ProseRhythmDetector software tool for Russian and English languages. Text corpora contains 300 texts for each language.

show abstract

Section: ритмические характеристикиunclassified

Section: классификация по жанрамunclassified

Section: обсуждение результатов с лингвистической точки зренияunclassified

Section: Introductionunclassified

See 2 more Smart Citations

Text Classification by Genre Based on Rhythm Features

Lagutina

Boychuk

2021

Model. anal. inf. sist.

View full text Add to dashboard Cite

show abstract

“…Порядок проведения экспериментов был следующим. С помощью алгоритмов, разработанных ранее в рамках проекта ProseRhythmDetector [22], для текстов были подсчитаны стилометрические характеристики разного уровня, а затем записаны в csv-таблицы.…”

Section: постановка экспериментовunclassified

Analysis of the Impact of the Stylometric Characteristics of Different Levels for the Verification of Authors of the Prose

Manakhova

Lagutina

2021

Model. anal. inf. sist.

View full text Add to dashboard Cite

This article is dedicated to the analysis of various stylometric characteristics combinations of different levels for the quality of verification of authorship of Russian, English and French prose texts. The research was carried out for both low-level stylometric characteristics based on words and symbols and higher-level structural characteristics.All stylometric characteristics were calculated automatically with the help of the ProseRhythmDetector program. This approach gave a possibility to analyze the works of a large volume and of many writers at the same time. During the work, vectors of stylometric characteristics of the level of symbols, words and structure were compared to each text. During the experiments, the sets of parameters of these three levels were combined with each other in all possible ways. The resulting vectors of stylometric characteristics were applied to the input of various classifiers to perform verification and identify the most appropriate classifier for solving the problem. The best results were obtained with the help of the AdaBoost classifier. The average F-score for all languages turned out to be more than 92 %. Detailed assessments of the quality of verification are given and analyzed for each author. Use of high-level stylometric characteristics, in particular, frequency of using N-grams of POS tags, offers the prospect of a more detailed analysis of the style of one or another author. The results of the experiments show that when the characteristics of the structure level are combined with the characteristics of the level of words and / or symbols, the most accurate results of verification of authorship for literary texts in Russian, English and French are obtained. Additionally, the authors were able to conclude about a different degree of impact of stylometric characteristics for the quality of verification of authorship for different languages.

show abstract

Automated Approach to Semantic Dominant Identification as Applied to English Literary Texts

Boychuk¹,

Vorontsova²

2022

Proceedings of the X International Research Conference Topical Issues of Linguistics and Teaching Methods in Business and Profe

View full text Add to dashboard Cite

The article investigates the phenomenon of the semantic dominant of a literary text, the central focus being given to its definition, typology and means of expression. The article provides an overview of works addressing the above issues, defines the key tools for semantic dominant identification, and evaluates the results of text analysis performed to establish the relationship of the text dominant to the various types of repetitions which, in terms of text meaning and rhythmic organization, express the key ideas and intentions of the author. The study is based on short stories by R. Kipling, J. Joyce and W.S.Maugham. The research shows that the domination of some concepts and meanings over the others is strongly associated with the repetition of a specific lexicon and its derivatives as well as the frequency of occurrence of lexical units belonging to a single lexical-semantic field. Added to this are the correlation of the most frequent lexical units with different semantic dominants and the existence of semantic dominants which have varying effects on the author's style, ranging between the non-determinant and idiospecific, e.g. dominants related to colonial policy ideas in Kipling, semantic dominants and metaphorical images of the city in Joyce, "aquatic" dominants and symbols in Maugham. Finally, the study allows for the detection of some background dominants which define the topos and the chronotopos of the texts.

show abstract

Automatic Extraction of Rhythm Figures and Analysis of Their Dynamics in Prose of 19th-21st Centuries

Cited by 14 publications

References 16 publications

Text Classification by Genre Based on Rhythm Features

Text Classification by Genre Based on Rhythm Features

Analysis of the Impact of the Stylometric Characteristics of Different Levels for the Verification of Authors of the Prose

Automated Approach to Semantic Dominant Identification as Applied to English Literary Texts

Contact Info

Product

Resources

About