Semantic Text Analysis Research Articles

An Intelligent Algorithm for Semantic Feature Analysis and Translation of English Texts

Accurate and rapid translation is conducive to the cultural communication of different languages. This paper briefly introduces the long short-term memory (LSTM) algorithm. To enhance the performance of the LSTM algorithm, semantic features were introduced, and semantic similarity was used to screen the translations that are more in line with the semantics of the source text. Then, simulation experiments were conducted. The experiments first examined the effects of the quantity of hidden layer nodes and the type of activation function in LSTM on the translation performance. Then, the LSTM algorithm was compared with the recurrent neural network (RNN) and traditional LSTM algorithms.The proposed translation algorithm showed the best performance when there were 512 hidden layer nodes and the activation function was sigmoid, it performed better than the other two translation algorithms, and the obtained result was consistent with the semantic meaning of the source text and smooth.

Measuring Chinese online populist discourse: an automated semantic text analysis method

Based on conceptualizing Chinese online populism as a grassroots discourse and operationalizing it in terms of people-centrist and anti-elitist dimensions, we developed an automated semantic text analysis method for analyzing Chinese online populist discourse both quantitatively and qualitatively. First, we introduced semantic role labeling to reformulate the original text into semantic triplets. Second, we created a Chinese populism dictionary containing terms signifying “the people,” “elites,” and “popular sovereignty.” Third, we developed a rule-based method to recognize populist discourse automatically. The automated semantic text analysis method can capture a great deal of qualitative information throughout this process for further analysis. The validation test showed that the automated semantic text analysis method performed satisfactorily (accuracy > 0.9). This method not only creates a broadly applicable and reliable tool for studying Chinese online populism, but it also contributes to the literature on how populism manifests in various cultural and political contexts, expanding the possibilities of populism research globally.

РОЗРОБКА АДАПТИВНИХ АЛГОРИТМІВ РОЄВОГО ІНТЕЛЕКТУ У ПРОЕКТУВАННІ ТА УПРАВЛІННІ ІНЖЕНЕРНИМИ СИСТЕМАМИ

The article examines the design and management of engineering systems in the context of growing data volumes in local computer networks. With the development of swarm intelligence, the probability of the existence of the necessary information for managing engineering systems increases, but the possibility of finding it decreases. This creates the need to develop new methods and tools for using adaptive algorithms of swarm intelligence. The purpose of such algorithms is to ensure the ability to process information and find queries with maximum relevance, generating the largest number of search results (SERPs) containing technical information. The development of swarm intelligence algorithms is impossible without their intellectualization, which includes semantic and syntactic analysis of texts, natural language tools, and intelligent algorithms for determining the significance of information resources. In digital information retrieval systems (DIRS), a query is formed in the form of keywords or their combinations, connected by logical operations. To search for the same information, different keywords are used, the choice of which is subjective. The first stage of the algorithm consists in determining the set of meaningful correspondences and forming the initial set of requests within the engineering system. To ensure the completeness of the selection, the total relevance of the SERP in relation to the group of significance criteria is considered. There is a need to develop an efficient neural network algorithm to solve the problem of assigning one SERP to each group of query criteria. This will make it possible to distribute SERPs by criteria groups so that each page is evaluated mainly by one criteria group, and the total relevance of all groups is maximized. Thus, the article emphasizes the importance of developing new methods and tools for implementing adaptive swarm intelligence algorithms in engineering systems. Special attention is paid to the development of effective neural network algorithms that will ensure optimal distribution of the relevance of search pages, which will increase the accuracy and efficiency of information search in complex engineering systems.

Sentiment Analysis and Facial Expression Recognition in Customer Service Interactions

In the evolving landscape of digital customer service, the need for advanced methods to accurately understand and respond to customer emotions has become critical. Traditional systems often rely solely on textual data, missing non-verbal cues that significantly contribute to the customer's emotional state. This study proposes a combined approach integrating Facial Expression Recognition (FER) and Natural Language Processing (NLP) to enhance emotion detection accuracy in customer service interactions. The FER component employs Convolutional Neural Networks (CNNs) to analyze facial expressions, while the NLP component uses Long Short-Term Memory (LSTM) networks to process textual data. This multimodal system aims to provide a comprehensive understanding of customer emotions by capturing both verbal and non-verbal cues. Experiments demonstrate that the integrated FER and NLP model significantly outperforms standalone models, achieving an accuracy of 92.3%, compared to 85.2% for FER-only and 87.4% for NLP-only models. The results highlight the benefits of a multimodal approach, showing substantial improvements in both training and validation performance. This study also compares the proposed model with other state-of-the-art models such as the Deep Learning Assisted Semantic Text Analysis (DLSTA) and Multimodal Emotion Recognition using Deep Belief Networks (DBN). While DLSTA achieves higher accuracy in text-based emotion detection, and DBNs provide robust emotion classification by integrating various modalities, our model effectively balances the strengths of both visual and textual data. The findings suggest that integrating FER and NLP can significantly enhance the quality of customer service by enabling more empathetic and effective interactions. Future work will focus on optimizing computational efficiency, addressing data variability, and ensuring adaptability across diverse customer service scenarios.

Identification and Evaluation of Representative Places in Cities Using Multisource Data: Focusing on Human Perception

Discovering the Representative places (RPs) of a city will benefit the understanding of local culture and help to improve life experiences. Previous studies have been limited in regard to the large-scale spatial identification of RPs due to the vagueness of boundaries and the lack of appropriate data sources and efficient tools. Furthermore, human perception of these places remains unclear. To address this gap, this research adopts a novel approach to identify and evaluate the RPs of a city from the perspective of human perception. Our methodology involves the utilization of deep learning systems, text semantic analysis, and other techniques to integrate multi-source data, including points of interest (POIs), street view images, and social media data. Taking Nanjing, China, as a case, we identified 192 RPs and their perceptual ranges (PRRPs). The results show the following: (1) Comparing RPs to non-RPs, RPs show higher average scores across four perceptual dimensions (positive indicators): Beautiful (7.11% higher), Lively (34.23% higher), Safety (28.42% higher), and Wealthy (28.26% higher). Conversely, RPs exhibit lower average scores in two perceptual dimensions (negative indicators): Boring (79.04% lower) and Depressing (20.35% lower). (2) Across various perceptual dimensions, RPs have utilized 15.13% of the land area to effectively cover approximately 50% of human perceptual hotspots and cold spots. (3) The RPs exhibit significant variations across different types, levels, and human preferences. These results demonstrate the positive perceived effects that RPs have, providing valuable insights to support urban management, the transformation of the built environment, and the promotion of sustainable urban development, and provide guidance for urban planners and designers to make improvements in urban design and planning to make these sites more attractive.

Сравнение схожести интеллект-карт в задачах маркетингового анализа

High competition requires new methods, tools, and technologies for implementing marketing efforts. Mind maps represent marketing information in a compact way, which facilitates classification and visualization of the marketing phenomenon under analysis. The method of text analysis can be applied to marketing research because mind maps that represent marketing information are a structured text; such an approach makes it possible to subject mind maps to linguistic processing. This research combined the conventional semantic analysis with comparing mind maps as a method of semantic-graph analysis. Initial marketing data were converted into a structured graph of lexical units, which were them compared pairwise to calculate similarity, taking into account the structural-multiple approach. The methods of semantic text analysis proved applicable to marketing data and effective in extracting additional information from a set of heterogeneous sources or different experts. Text analysis tools demonstrated a good potential for broadening the rage of marketing research methods.

Governance and Development of Tourism in Rural Areas through the Lens of Media in South Bukovina (Romania)

Agritourism and rural tourism represent an essential growing sector in certain EU regions, particularly in restructured and rebranded Central and Eastern European countries (CEECs) like Romania that display important rural areas and face important societal and economic changes. The rapid growth of rural tourism activities in the South Bukovina region (historically overlapping most of Suceava County) led, in the new legislative frame, to the establishment of the first regional Destination Management Organization (DMO) in Romania. By an exploratory qualitative, mixed-method case study approach, this study underscores important factors for tourism development in the region, outlining rural and agritourism variables integrated into the public authorities’ discourse. The paper innovatively focuses on the semantic analysis of online newspaper media texts and videos, complementarily analyzed by appropriate software solutions. The main results emphasize the factors for tourism development in the area through a dual cluster centered around the multilevel governance and tourism management structures represented by public authorities on the one hand and the projects, investments, and EU funding on the other. Key stakeholders’ opinion underscored public–private partnerships, supportive administrative structures, tourism events and various natural and cultural resources as sustainable elements that contribute to the successful development of tourism in the region.

Analysis and justification of the use of existing blockchain solutions for the protection of digital assets

The subject of this article is consideration of modern blockchain solutions and their potential use in the context of digital asset protection. Various aspects of blockchain technology are explored, including consensus mechanisms, security levels, and functionality. The goal of the work is a systematic analysis and justification of the application of various blockchain solutions for the protection of digital assets. The article is aimed at determining the effectiveness and feasibility of using specific blockchain protocols and their functional elements to ensure the safety, reliability, and integrity of digital assets. The following tasks were solved in the article: consideration of modern blockchain technologies and consideration of their role in ensuring the security of digital assets. Conducting a detailed analysis of popular blockchain protocols, including Bitcoin, Ethereum, and Hyperledger Fabric, with a focus on their security against various types of cyber threats and attacks. The following methods are used: analysis of blockchain protocols, expert evaluations of the effectiveness of protection of digital assets, and study of the technical features of each solution. The following results were obtained: clearly defined advantages and disadvantages of each protocol were obtained, taking into account their applicability in the field of digital assets in various fields of application, such as semantic analysis of texts, E-Learning, Big Data, DDP-systems, finance, etc. In addition, the issue of network privacy in the context of information protection was investigated and justifies the choice of the optimal blockchain solution for a specific use. Conclusions: The article provides readers with an overview of how to effectively use blockchain to ensure the reliability and security of digital assets in a variety of usage scenarios. In today's digital world, where the value of digital assets is growing exponentially, protecting them from cyber threats becomes a critical task. Blockchain technologies, originally developed for cryptocurrencies, have gained recognition as an effective tool in the field of cyber security. The importance of standardization and regulation in the field of blockchain technologies to ensure their effective integration and compliance with the requirements of the law is put forward.

NATIONAL COLOURING IN ROMANTICISM ON THE EXAMPLE OF LITERARY-CRITICAL STUDIES BY K. ZHUSSIP

Nowadays, the study of Romanticism as a significant phenomenon in literary studies is mainly focused on the investigation of its development under the influence of national characteristics. This research aims to identify the distinctive interpretations of romantic motifs in the works of Kazakh Romanticism poets. Specifically, the article provides an analysis of the development of romantic ideas using Kazakh romantic poetry of the 19th and 20th centuries as a case study, addressing the manifestation of Kazakh national characteristics rooted in Kazakh culture. By analysing the romantic works of Kazakh poets, the conceptual imagery of Romanticism is elucidated. Various research methods, including content analysis and semantic analysis of poetic texts, were used to demonstrate that Romanticism, as an emotional perception of the world and reality, transcends national boundaries. The study concludes that literary creativity is multifaceted, and linguistic analysis helps authors to effectively advocate Romanticism as a means of expressing national characteristics in literature, thereby contributing to the globalisation of cultural understanding. In addition, the study of the emergence of a new hero in romantic works, particularly in religious discourse, as exemplified by the literary-critical contributions of K. Zhussip, is identified as a promising avenue for future research. Keywords: Romanticism, national colouring, romantic hero, literary critical studies, images.

Development of an Algorithm and Module for Automatic Evaluation of Student Papers Based on Semantic Analysis of Text

Research objective. The main objectives of developing a module for automatic assessment of students’ papers based on the Russian grading scale system are:– Increased grading efficiency: the automatic system can process a larger number of papers in less time than a lecturer, reducing the time spent on checking;– Grading objectivity: the automated system is not subject to bias and other human factors, which ensures more objective grading of papers;– Standardization of grading: the automated system provides a uniform approach to grading, making it more transparent and comparable;– Reduced workload for lecturers: freeing lecturers from the routine work of checking papers allows them to devote more time to individual work with students.Materials and methods. Various methods can be used to develop a module for automatic assessment of students’ work, such as:Machine learning techniques: these techniques allow the module to learn from a set of examples where lecturers have already assessed students’ papers and automatically grade new papers.Natural Language Processing (NLP) methods: these methods allow the module to understand the meaning of text and evaluate it against given criteria.Expert systems methods: these methods allow the module to utilize the knowledge of experts in assessing students’ papers. For this project, we have chosen a combination of Levenshtein and Jaro index algorithms based on the method of assessing students’ knowledge in the Russian system.Results. The following main results were obtained in the course of this research. The module of automatic evaluation of student papers has been successfully developed and implemented on the basis of the Russian system of evaluation scales. Test evaluations of papers showed high accuracy of the module’s predictions and reliability of its work. Comparison of the module with manual assessment confirmed its ability to give comparable results. The module proved to be useful for lecturers, providing them with the ability to quickly and objectively assess students’ papers. Integration of the module with existing learning management systems facilitates its implementation in the educational environment. All the obtained results testify to the high efficiency and prospectivity of the developed module.Conclusion. As a result of this work, a module for automatic evaluation of students’ papers based on the Russian system of evaluation scales was developed and implemented. The main results of the work are that the module has been successfully tested and demonstrated high accuracy and reliability in the assessment of papers. The module has also demonstrated its usefulness for lecturers, providing them with an opportunity to quickly and objectively assess students’ papers. Due to its integration with existing learning management systems, the module can be easily implemented into the educational environment. In general, the results of the work confirm the effectiveness and prospects of using automatic assessment of students’ papers based on the Russian system of assessment scales.

Application of semantic analysis in strategic marketing using the mind map tool

The article discusses the marketing use of a tool used to find solutions and systematize information as mind maps. Due to the increase in the volume and flow of information, a high degree of laboriousness of the analysis of texts in natural languages appears. To solve marketing problems and develop effective marketing strategies, the processing and analysis of the information received is of great importance. For more efficient use of tools, like mind maps, and minimization of manual data processing, there are requests such as combining maps into one from several experts or different map iterations from one expert. A technique is proposed for solving the problem of combining information from mind maps into one by semantic analysis methods, consisting of five stages. An algorithm for combining a set of mind maps into one using the methods of semantic text analysis is presented. To test the methodology, an experiment was conducted, during which more than 30 mind maps were analyzed. Based on the results of the analysis, a combined mind map based on the proposed methodology is presented and the problem of combining a number of heterogeneous maps into one is solved using semantic analysis. The article uses such methods, as literature analysis, experiment, semantic analysis of the text.

A hybrid deep semantic mining method considering fuzzy expressions for the automatic recognition of construction safety hazard information

Safety hazards are a key consideration in construction management. The efficient recognition of safety hazard information can help managers formulate safety hazard management measures and improve the efficiency of construction safety management. However, construction site safety hazard data are stored in semistructured and unstructured text formats, which cannot be directly converted into understandable and usable information. Moreover, safety hazard text contains many fuzzy expressions, thereby increasing the difficulty of text semantic analysis; thus, how to accurately mine safety hazard information from complex and diverse text data is an urgent problem that must be solved. In consideration of this problem, we propose a bidirectional long short-term memory (BiLSTM) method with a fuzzy word vector and self-attention mechanism (FSABiLSTM) to automatically recognize safety hazard information. This method adopts TextRank and Word2vec to calculate the fuzzy word vector and process fuzzy expressions in safety hazard text. The safety hazard text semantic features are deeply extracted based on BiLSTM and a fuzzy word vector, and the extracted semantic features are analyzed via a self-attention mechanism. Actual construction safety hazard text is used to verify the reliability and applicability of the method, and the results indicate that the accuracy of this method, which outperforms existing machine learning methods, is 91.70%. In addition, the FSABiLSTM method can be used to automatically evaluate the risk degree of safety hazards; this use is beneficial to managing and controlling safety hazards. Concerning safety hazard text data, this study provides a new deep mining approach that can enhance safety management efficiency.

Evaluating cultural ecosystem services in China's modern historic parks: A sentiment computing approach

China's modern historic parks (MHPs) are a subcategory of modern heritage, yet their values remain underappreciated. Cultural ecosystem services (CESs) provide a holistic framework to assess MHPs’ values. However, evaluating CESs remains a challenge due to their intangible nature, subjectivity, and the imperative of public involvement. Few studies focused on CES perception in MHPs. In response to the gap, an aspect-based sentiment computing (ABSC) method was employed for CES evaluation in Shanghai’s MHPs. We created 3 lexicons of space types, CES types, and sentiment modifiers based on semantic syntax analysis of texts and identified 14 types of CESs and 22 types of spaces. The results show that “sense of place” and “relaxation” were the most prominent CESs in most MHPs. CESs could be classified into 2 categories, indicating the significance and the components of commemorative values and present-day values of MHPs. The overall CES perception varies in different MHPs at both individual park level and at space unit level. Our research enriches the understanding of the heritage values of MHPs, and offers CES trade-off principles for the balance between MHPs’ preservation and regeneration.

Representation of the lyrical "I" in the poetry by A. Podgornova

The multidimensional study of women's poetry is one of the promising strategies of modern Russian literary criticism, which allows us to reveal not only the tools of women's writing, but also the female mentality, feminine identity, and the peculiarities of reflection by a female author of the natural and social world. Among the female authors, a special place is occupied by the Erzya poet Alina Podgornova, whose works trace postmodern trends. The subject of the research in the article is the means of representing the lyrical "I" in the poet's poems. The purpose of the work is to analyze a number of the author's works, to determine the system of images through which the lyrical "I" is represented, to trace their conditioning by the postmodern worldview of the poetess. The material was composed of poems from the collections "Except rhymes", "Stranded" ("Thought"). The methodological basis of the work is determined by the structural and semantic analysis of the lyrical text, through which the structural components of the poetic image, its semantic organization, and symbolic semantics are described. The scientific novelty of the study is determined by the fact that, in the stated aspect, A. Podgornova's lyrics are for the first time considered and introduced into the context of Russian literary criticism. The article argues that the emotional and psychological state of the lyrical heroine A. Podgornova is due to the author's worldview and axiological concept, his perception of the world as chaos, moral apocalypse. The poetess's worldview is filled with negative social manifestations that destroy the spiritual and moral essence of a person, leveling universal values. The conclusions and provisions presented in the article expand the understanding of the state and development of modern Mordovian literature.

Leveraging Semantic Text Analysis to Improve the Performance of Transformer-Based Relation Extraction

Keyword extraction from Knowledge Bases underpins the definition of relevancy in Digital Library search systems. However, it is the pertinent task of Joint Relation Extraction, which populates the Knowledge Bases from which results are retrieved. Recent work focuses on fine-tuned, Pre-trained Transformers. Yet, F1 scores for scientific literature achieve just 53.2, versus 69 in the general domain. The research demonstrates the failure of existing work to evidence the rationale for optimisations to finetuned classifiers. In contrast, emerging research subjectively adopts the common belief that Natural Language Processing techniques fail to derive context and shared knowledge. In fact, global context and shared knowledge account for just 10.4% and 11.2% of total relation misclassifications, respectively. In this work, the novel employment of semantic text analysis presents objective challenges for the Transformer-based classification of Joint Relation Extraction. This is the first known work to quantify that pipelined error propagation accounts for 45.3% of total relation misclassifications, the most poignant challenge in this domain. More specifically, Part-of-Speech tagging highlights the misclassification of complex noun phrases, accounting for 25.47% of relation misclassifications. Furthermore, this study identifies two limitations in the purported bidirectionality of the Bidirectional Encoder Representations from Transformers (BERT) Pre-trained Language Model. Firstly, there is a notable imbalance in the misclassification of right-to-left relations, which occurs at a rate double that of left-to-right relations. Additionally, a failure to recognise local context through determiners and prepositions contributes to 16.04% of misclassifications. Furthermore, it is highlighted that the annotation scheme of the singular dataset utilised in existing research, Scientific Entities, Relations and Coreferences (SciERC), is marred by ambiguity. Notably, two asymmetric relations within this dataset achieve recall rates of only 10% and 29%.

On Defining Smart Cities using Transformer Neural Networks

Cities worldwide are rapidly adopting “smart” technologies, transforming urban life. Despite this trend, a universally accepted definition of “smart city” remains elusive. Past efforts to define it haven’t yielded a consensus, as evidenced by the numerous definitions in use. In this paper, we endeavored to create a new “compromise” definition that should resonate with most experts previously involved in defining this concept and aimed to validate one of the existing definitions. We reviewed 60 definitions of smart cities from industry, academia, and various relevant organizations, employing transformer architecture-based generative AI and semantic text analysis to reach this compromise. We proposed a semantic similarity measure as an evaluation technique, which could generally be used to compare different smart city definitions, assessing their uniqueness or resemblance. Our methodology employed generative AI to analyze various existing definitions of smart cities, generating a list of potential new composite definitions. Each of these new definitions was then tested against the pre-existing individual definitions we’ve gathered, using cosine similarity as our metric. This process identified smart city definitions with the highest average cosine similarity, semantically positioning them as the closest on average to all the 60 individual definitions selected.

Text classification method based on dependency parsing and hybrid neural network

Due to the vigorous development of big data, news topic text classification has received extensive attention, and the accuracy of news topic text classification and the semantic analysis of text are worth us to explore. The semantic information contained in news topic text has an important impact on the classification results. Traditional text classification methods tend to default the text structure to the sequential linear structure, then classify by giving weight to words or according to the frequency value of words, while ignoring the semantic information in the text, which eventually leads to poor classification results. In order to solve the above problems, this paper proposes a BiLSTM-GCN (Bidirectional Long Short-Term Memory and Graph Convolutional Network) hybrid neural network text classification model based on dependency parsing. Firstly, we use BiLSTM to complete the extraction of feature vectors in the text; Then, we employ dependency parsing to strengthen the influence of words with semantic relationship, and obtain the global information of the text through GCN; Finally, aim to prevent the overfitting problem of the hybrid neural network which may be caused by too many network layers, we add a global average pooling layer. Our experimental results show that this method has a good performance on the THUCNews and SogouCS datasets, and the F-score reaches 91.37% and 91.76% respectively.

Short Text Semantic Sentiment Analysis Based on Dual Channel Aspect Attention in Intelligent Systems

Traditional deep learning models for text sentiment analysis fail to fully harness the contextual semantic information of aspect nodes or use prior sentiment resources. This paper proposes a dual channel sentiment analysis model named M2BERT-BLSTM AA that is based on an enhanced Bidirectional Encoder Representations from Transformers(BERT)and Bidirectional Long short-term memory(BLSTM) model and incorporates a Dual Attention Mechanism. Firstly, an emotional resource database is constructed using existing emotional resources. Secondly, vectors are concatenated following mean and max pooling along the dimension of sentence length. These semantic features mitigate evaluation imbalance.Then the text and sentiment information are encoded separately, using distinct Attention Mechanism(Att-M) to extract contextual relationships and emotional features. The model's Aspect-Based multi-class sentiment prediction accuracies on the three Chinese datasets of Meituan ordering, restaurants, and laptops are 75.2%, 87.5%, and 75%, respectively, showing improved performance on sentiment classification.

Development of an error correction algorithm for Kazakh language

This article discusses a method for correcting spelling errors in the Kazakh language using the advantages of morphological analysis and a model based on noisy channels. To achieve this goal, modern problems of automatic processing of Kazakh textual information were analyzed, existing linguistic resources and processing systems of the Kazakh language were systematized, the basic requirements for the development of a system for analyzing Kazakh textual information based on machine learning were determined, and models and algorithms for extracting facts from unstructured and poorly structured text arrays were developed. The search function, an enhanced spelling correction algorithm, was utilized in this work and has the ability to recommend the proper spelling of the input text. The maximum editing distance, whether to include the original word when near matches are not found, and how to handle case sensitivity and exclusion based on regular expressions are all easily adjustable features of this functionality. Because of their adaptability, algorithms can be applied to a wide range of problems, from straightforward spell checks in user interfaces to intricate natural language processing assignments. Because of the way it’s designed, the search function finds possible corrections and verifies the context of words while accounting for user preferences like verbosity and ignore markers. Most modern multilingual natural language processing programs use only the graphical stage of text processing. On the other hand, semantic text analysis or analysis of the meaning of natural language is still an important problem in the theory of artificial intelligence and computational linguistics. But in order to process the grammar and semantics of multilingual information, precreated semantic and grammatical corpora of each natural language are necessary. To solve this problem, several tasks were considered and solved. These tasks included the analysis of research in the field of machine learning methods used in the processing of textual information, the existing problems of formalization and modeling of the Kazakh language, as well as the development and implementation of models, methods and algorithms for morphological and semantic analysis of texts of the Kazakh language.

Imagery Recognition and Semantic Analysis Techniques in Chinese Literary Texts

Abstract Chinese literary texts contain a sizeable vivid imagery vocabulary, which makes it difficult for average readers to judge the boundaries between words, and the current pre-trained language model is also difficult for them to learn its implicit knowledge effectively, which brings troubles to machine semantic analysis. The study uses CRF training to obtain a semantic analysis model of Chinese literary texts that recognizes the semantic relationship between two words. SVM is used to train classifiers for confusing categories, and the two semantic relations in the output of the CRF model are further recognized to determine the final semantic relations between word pairs. Finally, the LCQMC dataset is used as the experimental data, and the semantic analysis technique based on CRF and SVM is employed to obtain the participle, lexical, and dependent syntactic annotations. According to the results, the model’s correct rates on the LAS for paraphrase recognition and dependency analysis of Chinese literary texts are 74.83% and 92.05%, respectively. The study enhances the efficiency of semantic analysis of relevant Chinese texts and is crucial for the study on the semantic analysis of terms.