Semantic Text Analysis Research Articles

The Concept of Public Administration by S.E. Desnitsky (Reconstruction Experience).

S.E. Desnitsky's views on public administration occupy a special place in the history of managerial thought in Russia of the XVIII century. This place is determined by the fact that, unlike all those who wrote on management topics in that era, he was not an official. He was an observer and an expert, which gave him the opportunity to system analyze and develop a set of proposals for improving governance in Russia. The subject of the article is the set of views of S.E. Desnitsky, designated here as the "management concept". The purpose of the study is to identify the basic elements of this concept. The reference method is a combination of systematic and semantic analysis of Desnitsky's texts, in comparison with the texts of figures of the European Enlightenment. The main conclusion of the article is the complex of semantic blocks identified by the author, the combination of which makes up Desnitsky's management concept. The author comes to the conclusion that Desnitsky saw the purpose of management in introducing organizational principles into "natural" relations and, first of all, into property relations. Desnitsky supplemented the universal principle of the "common good" with the principles of the welfare of the state and estate management. To solve management problems, he proposed to follow two organizational principles: separation of powers and multi-level management. For each of the "authorities" allocated to him, he defined tasks peculiar only to her and the tools necessary for their solution. The preservation of the unity of governance in the state, according to Desnitsky, is achieved by highlighting the law as the main instrument of governance.

Perceptions of the Yangtze River cruise ship brand based on text semantic analysis: A web big data perspective

Relying on the rich natural and human resources of the Yangtze River, the Yangtze River cruise has been a popular and famous tourism route. This study adopts a big data approach to study the perception of and satisfaction with the Yangtze River cruise brand, so as to come up with some practical suggestions for the enhancement of its value. Based on the analysis of the current development of the Yangtze River cruise tour, this paper conducted a textual analysis on 2,260 user reviews of two important Chinese travel OTA companies (Ctrip.com and Tuniu.com) through the theory and method of web text mining. A word frequency analysis, the construction of semantic networks, and a sentiment analysis were carried out. The results of the study show that the market perception of each cruise company’s brand is not very different, and the relevant companies have not yet developed their own special products and services. “Service” is the most frequently mentioned high-frequency word in tourists’ reviews. The sentiment analysis shows that the frequency of positive emotions in tourists’ reviews is high (exceeding 80 %). Through the satisfaction analysis of six dimensions of Yangtze River cruises, it is found that “cruise dining” and “cruise entertainment” are weak points.

ANALYSIS OF THE PROBLEM OF BUILDING ONTOLOGICAL DICTIONARY OF CONSTRUCTION

The problem of the automated construction of ontology in construction based on the semantic analysis of texts in natural language is considered. The most important problem in the development of research in construction is its intellectualization, and the associated data integration and high-quality information retrieval. However, these technologies presuppose the presence of high-quality sources of semantic data. Overall, it can be argued that reuse and integration with data sources is low. This is because the data sources are not perfect enough to be used or integrated. In connection with this problem, the problem of the automated formation of ontology based on the analysis of texts in natural language in construction is quite relevant. A common criterion for the quality of an ontology is based on an assessment of the convenience and efficiency of work and the connection of cognitive processes with semantic ones with the aim of constructing and updating it in the field of construction. Assessment of constructed ontology based on automated tools is another separate complex task. The main difference between the study, the results of which are presented in this work, is a cognitive-semantic analysis based on category theory, mathematical logic and universal algebra, algebra of sets, cortege algebra and relational algebra, namely, the construction of an ontological dictionary of construction, ontological constructions in open languages representing knowledge in construction. The work includes classification and definition of information units and their sources. The features of the information resource in the construction industry have been determined.

Deep learning approach to text analysis for human emotion detection from big data

Abstract Emotional recognition has arisen as an essential field of study that can expose a variety of valuable inputs. Emotion can be articulated in several means that can be seen, like speech and facial expressions, written text, and gestures. Emotion recognition in a text document is fundamentally a content-based classification issue, including notions from natural language processing (NLP) and deep learning fields. Hence, in this study, deep learning assisted semantic text analysis (DLSTA) has been proposed for human emotion detection using big data. Emotion detection from textual sources can be done utilizing notions of Natural Language Processing. Word embeddings are extensively utilized for several NLP tasks, like machine translation, sentiment analysis, and question answering. NLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text. The numerical outcomes demonstrate that the suggested method achieves an expressively superior quality of human emotion detection rate of 97.22% and the classification accuracy rate of 98.02% with different state-of-the-art methods and can be enhanced by other emotional word embeddings.

What worries people with multiple sclerosis in Russia? Semantic analysis of patient messages using artificial intelligence tools

To study the needs of patients suffering from multiple sclerosis (MS) in Russia. The technologies of Big Data analysis and intelligent processing of unstructured information (semantic analysis of natural language texts), developed by Semantic Hub were used. Semantic Hub platform scans digital environment to connect to the sources of interest and to collect data of potential interest (i.e. texts generated by patients and their caregivers, in anonymized form). As the next step, each text is analyzed using natural language understanding technologies to build the knowledge base with aggregated data. The semantic analysis of natural language texts made it possible to describe virtual population of Russian patients with MS and their caregivers on the Web: age, gender, regions of residence, movements, key Web resources for getting information and communicating with each other, insights about medical care and the quality of life of patients with MS. In addition to doctors' recommendations, today the patient can get information from various sources, including other patients with MS. This trend requires attention of medical community: it is necessary to help patients get reliable information about the disease, and methods of therapy. Doctor-to-patient communication on the Web should be widely discussed to develop effective and ethical approaches.

Визуальный вандализм: маргинальная коммуникация в мегаполисе

A distinctive feature of a resident of a modern megapolis is the desire not just to live, but to participate in its management. A modern citizen is someone who has the right to the city and has the opportunity to implement it. Today, a citizen is deprived of this right, it is privatized by officials and local governments, as a result of which, a citizen turns out to be an outcast, alienated from the megapolis. But it is important for a modern person to be the master of his life, which encourages him to take actions to restore the right to the city, which determines the relevance of this study. In this regard, the aim of this work is to analyze the power-citizen communication and ways to activate it. For this purpose, the effectiveness of local self-government and various forms of visual vandalism were analyzed as a way of appropriating urban space and one of the options for attracting attention to the quality of communication between citizens and the authorities. The main research methods were trendwatching, semantic analysis of vandal images and texts, and regulatory analysis of legislation regulating the activities of local governments and acts of vandal behavior. Yekaterinburg acted as the empirical base of the study. During the study, two main areas of communication between citizens and municipal authorities were identified, this is a socio-political direction, including demographic problems, political experiences, problems of prices, road quality and others, and a cultural one, including a religious aspect, raising issues related to education, the fight against COVID-19, religious conflicts, etc. The results of the study were conclusions about the insufficient effectiveness of the activities of local self-government bodies; the low level of involvement of citizens in local self-government; the fact that residents of the megapolis are looking for ways to establish communication with municipal authorities; communication established by residents is marginal and is embodied in the form of vandal activity.

Borders as the ultimate (de)Fence of Identity: an ontological security approach to exclusionary populism in Italy and Spain

This paper looks at the discursive construction of the concept of border and its interaction with identity in two exclusionary populist movements: Lega in Italy and Vox in Spain. The study, based on the analysis of an ad hoc selection of discourses by the two parties’ leaders, applies clause-based semantic text analysis to detect the main discursive representations of the “us” and the “others” as threatening ontological security and the performative role played by borders as the ultimate (de)Fence for identity. Results show that Matteo Salvini focuses his discourse on the manipulation of physical space, representing Italy as the space for Italians and proposing to “close the borders” as the only way to stop the “invasion”. Santiago Abascal, on his side, constructs Spanish identity as inherently and proudly “anti-Islamic”. Borders, therefore, are invalicable for those considered incompatible with local values, namely “Muslims”, represented as a “natural threat” to Spanish identity.

СУБЪЕКТИВНЫЕ СОСТАВЛЯЮЩИЕ ЯЗЫКОВОГО ИМИДЖА ЖЕНЩИНЫ-ПОЛИТИКА: КОНТЕКСТ СОЦИАЛЬНО-РЕЧЕВОЙ ДЕЯТЕЛЬНОСТИ

Statement of the problem. This work is devoted to the study of the linguistic image of a Russian woman politician – a special type of public image that attracts the attention of both the mass addressee and the professional expert community. The very concept of “linguistic image” is used in many social and scientific practices, being of great interest for modern humanitarian knowledge – imageology, linguistics, psychology, sociology, philosophy, advertising, public relations, etc. Within the field of linguistic image, as well as in the linguistic theory of linguistic personality, the aspect of the subjective component of public speech, the so-called “author in the text”, has always been highlighted as a separate aspect. This is interconnected not only with anthropocentrism as a universal scientific idea of ​​the 21st century, but also with the global process of mediatization of all spheres of human activity. The purpose of the article is to reconstruct the subjective component of the linguistic image of a woman politician in the context of public social and speech activity. The methodology (materials and methods). The methodology of the analysis undertaken is based on the provisions and ideas of imageology, the theory of linguistic personality and linguistic semantics, in the context of which descriptive-analytical and comparative methods were used, as well as the method of semantic text analysis. The research material included the texts of public speeches and statements of 2016–2018, belonging to two representatives of modern Russian politics – Maria Zakharova and Natalia Poklonskaya. Research results. In the speeches of M. Zakharova and N. Poklonskaya, the description of social-speech communication corresponds to one language model and is presented in three aspects: 1) space (where?), 2) participants (who?), and 3) metascenarios of social-speech communication (what is happening?). In the texts of these women politicians, this semantic model is filled with its own content, which has general and specific elements that characterize their public images in different ways. Russia is described as a common communicative space for the activities of political subjects, despite the fact that for M. Zakharova the Ministry of Foreign Affairs turns out to be a specific medium of communication, and for N. Poklonskaya these are the State Duma, the Prosecutor’s Office and the Crimea. The common thing is that both speakers inscribe their own communicative activity in a threefold structure, where the main participants are a) the speaker himself, b) his associates and c) his opponents. In the contexts of M. Zakharova, the listed participants are embodied in roles: a) “Me” as “an intermediary” or “a moderator”, b) “We” as “diplomats”, as “teammates”, or a subject of the “conciliar” type (Russia, Moscow, diplomatic corps);in the contexts of M. Poklonskaya – a) “Me” as “a stateswoman” or “a prosecutor”, and also b) “We” as “prosecutors”, as “associates” and as “trustees”, respectively. As for the opponents, in both cases the set is practically the same: USA or the Ukrainian. The content of the described model is complemented by the so-called metascripts, which represent the social-speech situation in a new way and have a different functional purpose in every statement. Conclusion. The linguistic image of M. Zakharova is more objectified and restrained, in fact merging with the typical diplomatic image, while the image of N. Poklonskaya is more emotional and subjective, reinforced by the characteristic features of speech spontaneity and directness. At the same time, both images, framed by the modus of involvement and team goal-setting, organically fit into the space of the professional communication.

LEXICAL AND PHRASEOLOGICAL PARADIGMATICS OF THE FRENCH LANGUAGE: MADELEINE DE PROUST

The article is devoted to the linguocultural analysis of the idiom madeleine de Proust in modern French. The analysis is based on lexicographic data, component analysis method and text semantic analysis. Using the method of linguocultural decoding they find out emotional and sensual, ethical, aesthetic informations; archetypal, mythological, religious, philosophical and scientific informations, which are the deep foundations of the meaning of a phraseological unit. In the unit madeleine de Proust , the basic types of information are religious and philosophical. The first is associated with the polysemantic inner form of the word Madeleine. It is a nominative name - it means the name of a flour product and a proper name - Madeleine was the name of the girl who invented this culinary dish; this word is associated with the images of Magdalen-sinner and St. Mary-Magdalene, which is reflected in the phraseological system of the French language; with proper name Saint-Jacques, which is used to describe the subject of the material world, and accompanies the writer’s life, the hero in the novel. The philosophical type of information is associated with Proust’s reflections, signs, philosophy, with the concepts of the voluntary and involuntary memory. And all these were pushed by the sensual-emotional information. The polysemous word madeleine in the semantic space of the literary text thanks to the talent of the writer, his emotional and sensual experiences, his stream of consciousness, expanded its meaning and became one of the components of the new language unit madeleine de Proust .

Development of Semantic Analysis Software Tool for Solving Problems of Text Formalization

Problem of safety ensuring of children and underage adolescents in Web–space is becoming increasingly acute. Younger generation information security is the state of children and adolescents protection, in which there is no risk associated with harm to their health and (or) physical, mental, spiritual, moral development from destructive information. This article describes the development of new software product that allows analyzing text from files, Web sites, pages, applications, etc. Analog programs were reviewed; modern text recognition algorithms were described. Screenshots and flowchart of software parts designed functioning for semantic text analysis in Web space are presented. Any Web page is file with extension, and after analyzing, it is possible to evaluate the information and classify it by topics, as well as to determine whether there is destructive content. In the presented study, the software tool was developed for semantic analysis and formalization of text. Exact trigger points from 26 to 30 times evaluate the algorithm functioning. With accuracy of up to 80%, it can be argued that algorithm is suitable for determining the orientation of article and content of ideas expressed in it, taking into account duality of model.

SEMANTIC COMPARISON OF TEXTUAL INFORMATION USING ARTIFICIAL INTELLIGENCE MODELS

The means of artificial intelligence models, providing the users with the specialized algorithms enabling adequate and efficient comparison of the textual information content have been described in the article. The research conducted made it possible to accomplish analysis of the existing models of semantic comparison of the textual information and suggest the innovative way of developing the new algorithm, based on conducting semantic text analysis, applying models of artificial intelligence. The analyzed algorithm enables to extract the main content from the compared texts in the form of a semantic network, which in its turn allows to reliably assess the degree of their identity and as a result to make an objective comparison.

DWSA: An Intelligent Document Structural Analysis Model for Information Extraction and Data Mining

The structure of a document contains rich information such as logical relations in context, hierarchy, affiliation, dependence, and applicability. It will greatly affect the accuracy of document information processing, particularly of legal documents and business contracts. Therefore, intelligent document structural analysis is important to information extraction and data mining. However, unlike the well-studied field of text semantic analysis, current work in document structural analysis is still scarce. In this paper, we propose an intelligent document structural analysis framework through data pre-processing, feature engineering, and structural classification with a dynamic sample weighting algorithm. As a typical application, we collect more than 11,000 insurance document content samples and carry out the machine learning experiments to check the efficiency of our framework. Meanwhile, to address the sample imbalance problem in the hierarchy classification task, a dynamic sample weighting algorithm is incorporated into our Dynamic Weighting Structural Analysis (DWSA) framework, in which the weights of different category tags according to the structural levels are iterated dynamically in training. Our results show that the DWSA has significantly improved the comprehensive accuracy and the classification F1-score of each category. The comprehensive accuracy is as high as 94.68% (3.36% absolute improvement) and the Macro F1-score is 88.29% (5.1% absolute improvement).

The search for R&D partners based on patent data

Nowadays, companies still rely heavily on expert knowledge when selecting research and development partners (R&D, R&D). In this paper, it is proposed to identify and select potential technology partners based on the analysis of the USPTO patent array using the Problem & Solution model. The process of identifying R&D partners will be based on the similarity of solutions to technological problems. This paper shows the development of software for extracting the semantic SAO structures from USPTO patent documents, which are used to form the Problem and Solution structures, and selecting potential technology partners based on them. The theoretical significance of the study lies in the developed algorithms for parsing patents; extracting SAO using semantic text analysis; formation of Problem-Solution structures based on SAO data; identifying R&D partners based on similarities in solutions to technological problems.

Populism, Twitter, and COVID-19: Narrative, Fantasies, and Desires

During a global pandemic, the great impact of populist discourse on the construction of social reality is undeniable. This study analyzes the fantasmatic dimension of political discourse from Donald Trump’s and Jair Bolsonaro’s Twitter accounts between 1 March and 31 May. To do so, it applies a Clause-Based Semantic Text Analysis (CBSTA) methodology that categorizes speech in Subject-Verb-Object (SVO) triplets. The study findings show that in spite of the Coronavirus pandemic, the main beatific and horrific subjects remain the core populist signifiers: the people and the elite. While Bolsonaro’s narrative was predominantly beatific, centered on the government, Trump’s was mostly horrific, centered on the elite. Trump signified the pandemic as a subject and an enemy to be defeated, whereas Bolsonaro portrayed it as a circumstance. Finally, both leaders defined the people as working people, therefore their concerns about the pandemic were focused on the people’s ability to work.

On Bi-gram Graph Attributes

We propose a new approach to text semantic analysis and general corpus analysis using, as termed in this article, a "bi-gram graph" representation of a corpus. The different attributes derived from graph theory are measured and analyzed as unique insights or against other corpus graphs, attributes such as the graph chromatic number and the graph coloring, graph density and graph K-core. We observe a vast domain of tools and algorithms that can be developed on top of the graph representation; creating such a graph proves to be computationally cheap, and much of the heavy lifting is achieved via basic graph calculations. Furthermore, we showcase the different use-cases for the bi-gram graphs and how scalable it proves to be when dealing with large datasets.

“Africa does not Fit in Europe”

The politicization of immigration has moved the debate about immigration at the center of the run-up of elections, creating the breeding ground for the electoral breakthrough and success of right-wing populist parties.
 This article aims at disclosing the narrative of immigration and its politicization in VOX’s discourse, comparing it to the Italian Lega party.
 Clause-based semantic text analysis reveals that both parties share the classic characteristics of nativist populism: the representation of a virtuous and hardworking people, threatened by the invasion by some “others”, immigrants, who intrude the sovereign, antispace of natives to exploit and commit crimes. In both cases, the concept of space is manipulated, representing countries as limited spaces, allowing to depict immigrants as a threat to legitimize negative political responses.
 The study also identifies a novelty: the construction of the rescue NGOs as the new antagonist actor.

Transformer-based identification of stochastic information cascades in social networks using text and image similarity

Identifying the origin of information posted on social media and how this may have changed over time can be very helpful to users in determining whether they trust it or not. This currently requires disproportionate effort for the average social media user, who instead has to rely on fact-checkers or other intermediaries to identify information provenance for them. We show that it is possible to disintermediate this process by providing an automated mechanism for determining the information cascade where a post belongs. We employ a transformer-based language model as well as pretrained ResNet50 model for image similarity, to decide whether two posts are sufficiently similar to belong to the same cascade. By using semantic similarity, as well as image in addition to text, we increase accuracy where there is no explicit diffusion of reshares. In a new dataset of 1,200 news items on Twitter, our approach is able to increase clustering performance above 7% and 4.5% for the validation and test sets respectively over the previous state of the art. Moreover, we employ a probabilistic subsampling mechanism, reducing significantly cascade creation time without affecting the performance of large-scale semantic text analysis and the quality of information cascade generation. We have implemented a prototype that offers this new functionality to the user and have deployed it in our own instance of social media platform Mastodon.

Elements of expressionism in the story of A. Green «Gray Car»

The topic of the work is relevant, since at present the Russian literary criticism is rediscovering the features of the artistic expression of Soviet literature of the 1920s. The aim of the study was to discover the features of the poetics of Greens text that allow us to identify the novel under consideration as expressionist. Research methods used in the article: comparative-historical and semantic analysis of texts. At the beginning of the article, the research of the novella Gray Car by A.V. Polupanova and L.U. Zvonareva is considered, inaccuracies and obvious factual errors are noted, indicating a lack of understanding of the text, a mixture of such forms of expression of the authors position (according to B.O. Korman) as hero-narrator and author-narrator. As an empirical material, in addition to the novel by A. Green, the works of G. Mayrink, F. Kafka and L. Perutz were used. As a result of consideration of the novels the Golem, Castle, the Cossack and the Nightingale, the Wizard of judgment was allocated with the following features art in the world of the expressionist literary works: a) the problem of identity associated, as a rule, the main character; 2) semema madness, which became a constant for expressionist texts; 3) mysterious (hidden) order of a seemingly chaotic world; 4) the lack of success of speech acts. All these features were found in the story of A. Green, so it seems that the new approach to the work of the writer as a representative of Russian expressionism, demonstrates its consistency and can be contrasted with the more traditional consideration of the authors prose as a super-textual unity.

빅데이터 분석을 통한 화장품 트렌드 변화 추이에 관한 연구 - 텍스트마이닝과 의미연결망 분석을 중심으로 -

빅데이터 분석을 통한 화장품 트렌드 변화 추이에 관한 연구 - 텍스트마이닝과 의미연결망 분석을 중심으로 -

СПЕЦИФИКА ФОРМИРОВАНИЯ И ОБОГАЩЕНИЯ ТЕРМИНОЛОГИЧЕСКОЙ СИСТЕМЫ ПОДЪЯЗЫКА СТРОИТЕЛЬСТВА (НА МАТЕРИАЛЕ ТЕКСТА ПОЯСНИТЕЛЬНОЙ ЗАПИСКИ К ПРОЕКТУ)

Objective of the article is to consider the question of the origin, formation, and enrichment of the terminological system of the construction language for specific purposes. The article analyzes the ways of formation and development of the terminological system of the lexical subsystem, as well as the classification of lexical and semantic ways of term formation. The following tasks were defined: to consider the formation of a terminological system in the construction language for specific purposes, to determine the place of the term system in the language subsystem, to identify lexical and semantic ways of word formation in the construction term system. Applied methods . The article applies linguistic and structural methods and semantic analysis of authentic texts of the explanatory notes to the projects. The relevance of the presented research lies in the need to specify ways to form and enrich the ontological base of construction texts for their application in applied and theoretical linguistics. Results . The study analyzed and identified the main ways of developing the lexical subsystem of the construction ontology: terminologization of words in common language, metaphorization, metonymization, narrowing of meaning. Conclusions . The presented classification of semantic derivation of lexical units based on the analysis of authentic texts of explanatory notes can be used in the development of tools for analyzing the term systems of the construction language for specific purposes, creating dictionaries of terms, databases and information nodes of the virtual learning environment for both specialists and students in construction specialties.