CC BY
0DEVELOPING AN UZBEK LITERATURE CORPUS: ENHANCING LITERARY SELECTION FOR 5TH-GRADE
EDUCATION
Sattarova S.B.
Computer Science department Urgench State University, https://doi.org/10.5281/zenodo.13774214
Abstract. The formation of a reading culture in students plays a decisive role in their overall development as well-rounded individuals. This reading culture is primarily developed through engaging with literary works. In secondary school, students lay the foundation of essential knowledge needed for their future. The books that secondary school students read should align with their intellectual abilities. This paper discusses the creation of a literary corpus model for selecting literary works appropriate to the intellectual abilities of 5th-grade students. NLP methods were employed in this process, and the issue was thoroughly addressed based on 5th-grade literature textbooks. The scientific novelty of the article lies in the statistical data formed in the literary corpus created by the authors, including the list and number of writers, their countries of origin, and the types of literary works used. This literary corpus provides significant opportunities for selecting appropriate literary works using text similarity algorithms, which can lead to improvements in the reading culture of students in school education.
Keywords: cognitive abilities, NLP methods, Uzbek Literature Corpus.
INTRODUCTION
Students entering secondary school begin to face some difficulties in the educational process due to the diversity of school's curriculum and subjects. Because in secondary education, more complex training begins than in primary school. They may have trouble learning new subjects at this time due to the transition period. The role of interesting literary genres appropriate to their age and intellectual potential is extremely important in the adaptation of secondary school students to this period. Because literary works of various genres distract students from the difficulties of their studies and invite them into the world of their heroes. In contrast to primary school, in secondary school they are given the task of reading a large volume of literary genres. In the beginning, it can definitely be a bit overwhelming for students. However, this problem imposes on the pedagogues the task of including literary genres suitable for the age, psychological state and intellectual potential of students, that is, fairy tales, proverbs, stories and novels in the curriculum. This task, in turn, requires the creation of a literary corpus consisting of a vocabulary suitable for the intellectual potential of students.
In the educational journey of young learners, particularly at the elementary level, the selection of literary works is a task of profound significance. At this stage, students are not only developing foundational skills in reading and comprehension but are also beginning to form their understanding of the world through the stories and texts they encounter. For 5th-grade students, who are typically around ten or eleven years old, the literature they engage with must be carefully chosen to align with their intellectual, emotional, and cultural development. When the selected texts do not match students' cognitive abilities or cultural context, several issues can arise, including difficulty in understanding complex themes, confusion with advanced vocabulary, and
a general disengagement from the reading process. These challenges can lead to frustration and, ultimately, a loss of interest in literature - a loss that can have lasting implications on their academic success and personal growth.
The importance of providing students with age-appropriate and intellectually stimulating literature cannot be overstated. Literature that is either too simplistic or overly complex can hinder the development of critical thinking skills and reduce students' enthusiasm for reading. Inappropriate selections can lead to misinterpretations of key concepts and diminish the enjoyment that comes from understanding and connecting with a text. This disconnection from literature at an early age can result in students avoiding reading altogether, thereby missing out on the numerous benefits that regular engagement with literature offers, such as enhanced vocabulary, improved writing skills, and a deeper appreciation of diverse cultures and perspectives.
To address these educational challenges, a comprehensive and structured Uzbek Literature Corpus Based on the 5th Grade Literature Textbook has been developed. This corpus is specifically designed to support the selection of literary works for the 5th-grade literature textbook, ensuring that the texts chosen are not only suitable for students' intellectual levels but also rich in cultural and pedagogical value. The creation of this corpus involved the application of advanced computer linguistics methods, enabling a detailed analysis of the texts in terms of thematic relevance, linguistic complexity, and educational appropriateness. By analyzing factors such as the number of tokens, unique words, and sentence structures within the texts, the corpus provides educators with critical data to make informed decisions that will enhance the reading experience for students.
Moreover, the Uzbek Literature Corpus Based on the 5th Grade Literature Textbook includes a carefully curated list of authors, both local and foreign, whose works contribute to a diverse and well-rounded literary education. The corpus also categorizes the various genres represented in the 5th-grade literature textbook, offering a broad spectrum of literary forms and styles that cater to the varied interests and intellectual needs of young readers.
This paper will delve into the process of creating the Uzbek Literature Corpus, detailing the methodologies used in its construction and the statistical data derived from its analysis. We will explore how this corpus serves as an essential tool for educators in selecting literary works that not only align with the intellectual potential of 5th-grade students but also foster a lifelong love for reading. By ensuring that the chosen texts are both challenging and accessible, we aim to contribute to a more effective and meaningful literature curriculum in primary education, one that cultivates not only literacy skills but also a deep appreciation for the rich literary heritage of Uzbekistan and the wider world.
LITERATURE REVIEW
Numerous studies by both local and international researchers have focused on developing educational resources and enhancing school textbooks. However, there has been little research on creating a corpus and selecting literary books aimed at evaluating the potential for increasing the knowledge of secondary school students in Uzbek language.
The literary process involves not only an authorial subject who generates the artistic text, but another subject—the reader—who must perceive the text as artistic. Each subject is governed in part by the socially shared artistic norms of his time and place. And since "high" literature because of its written form is open to history, literary works of art are perceived against the background of artistic norms different from those which gave birth to them [1].
The article [2] describes the goals and tasks of teaching Uzbek literature in Uzbek language classes in Russian-system schools, the problems of defining the educational content and ways to solve them. Also, selecting high-level artistic works from the new Uzbek literature, including to the works of famous writers, lexical and grammatical difficulties that arouse respect in the representatives of Uzbek literature with their works, striving to get samples of their own works. This article [3] examines the theoretical and practical aspects of Uzbek electronic corpus as a linguistic tool in computer linguistics. It details the corpus' functional capabilities, development experiences, and conceptual architecture, including its structure, linguistic annotation, metadata, and management. The platform supports linguistic analysis in computer linguistics and NLP, with ongoing development of Uzbek language technology. The article [4] discusses the basic principles of corpus linguistics, a new field in applied Uzbek linguistics, as well as the process of designing and constructing corpus. Examples of achievements of world linguistics in the creation of corpus resources in Uzbek language are given. Practical linguistic experience proves how to set up the first stage of corpus linguistics. The research [5] examines the automatic categorization of Ottoman texts using transliterated versions of Latin alphabet. The authors use the method of applying Naive Bayes and Support vector machines to features such as word frequency and token length. The results of the statistical analysis will help to recommend style markers and methods for future work. This article [6] explores the concept of corpora as essential tools in linguistic analysis, defined as collections of texts representing a language (Tognini-Bonelli, 2001). It examines how corpus linguistics, leveraging computer technology, goes beyond mere methodology to integrate data gathering with theoretical insights, offering a new perspective on language.
The field of semantic analysis of any text is crucial in computer linguistics, where the focus is on improving the processing of text corpora through algorithms. In this research work [7], a keyword search algorithm for Kazakh language texts was developed, in which a reference dictionary was created using the Porter stemmer tool. The method used in the paper covers semantic affinity and vector marking for neural network learning. The advantage of this approach is that it automates text analysis and has potential applications in online student performance assessment. The novelty of the algorithm is its use of neural networks for Kazakh text and elimination of shortcomings in local computer linguistics research. This article examines the development issues of Uzbek WordNet modeled after Turkish WordNet [8]. In another article [9], a study on the detection of stop words is carried out using the "School Corpus" as an example, and the detection of stop words in Uzbek texts is summarized through automatic analysis of previous research. It is important to create an educational corpus suitable for the intellectual potential of primary school students to improve the quality of education. Educational materials that are not appropriate for the age and intellectual potential of students can diminish their interest in learning.
In a different article [10], research is conducted on the creation of educational materials suitable for primary school students based on a corpus developed from 35 Uzbek primary school textbooks. In this paper [11], the educational corpus, which is a fragment of Uzbek National Corpus taken from school textbooks and dictionaries, is studied. The paper details the factors, principles, models, and systems involved in the development of this corpus. In this study, the authors of [12] proposed a method for evaluating the list of stop words, tested in Uzbek but adapted to similar agglutinative languages, showing acceptable accuracy in automatic detection. Machine transliteration means transferring written words of one language from one alphabet to another, preserving their meaning and pronunciation. This article [13] presents a transliteration tool
between three Uzbek scripts: Old Cyrillic, Official Latin, and New Latin. Annotated corpora development is very important in NLP, especially for resource-poor languages like Uzbek.
The paper [14] addresses automatic text summarization, focusing on two main approaches: summarizing with equivalent words and extracting key sentences. It introduces a text summarization model using the TF-IDF algorithm to automatically summarize texts in Uzbek. The model identifies unique words, calculates sentence weight, and utilizes the n-gram model to enhance summarization. The paper [15] tackles the scarcity of such resources by creating a novel POS and syntactic tag set for Uzbek. This article [16] examines the application of the Jaccard similarity method to the creation of appropriate reading lists for high school students. To achieve this, a corpus is created based on high-quality literature textbooks, and this corpus is compared with literary works. Books with the highest similarity results are recommended for reading. The problem was fully addressed using literature textbooks for 5th-11th grade students and literary works in Uzbek language.
Natural Language Processing (NLP) technologies have revolutionized various domains by enabling machines to understand, interpret, and generate human language data. However, for languages with limited digital resources and complex linguistic structures, such as Uzbek, NLP faces unique challenges. This paper [17] delves into the specific challenges encountered in NLP for Uzbek, focusing on lemmatization, stemming, sound recognition, and semantic analysis. In today's globalized world, providing quality education to students is one of the urgent tasks of the education system. This article [18] details how to create a model of the solar system using Python's graphical capabilities. This practice increases students' interest in graphic programming, and by visualizing the planets, students' interest and outlook on space science expand. In this article [19], the problem of creating a terminological dictionary for the chapter on the Delphi programming language, based on the textbook for academic lyceum students on Informatics and Information Technology, is considered. These articles [20, 21, 22] provide information about the importance of forming a culture of reading in students, creating the TF-IDF process for Uzbek literary texts, and what needs to be done in this regard.
METHODOLOGY
In this section, we provide a methodology for creating a literature corpus tailored to 5th-grade students. Since students build and enrich their vocabulary through textbook materials, which are crucial for vocabulary development, we have decided to create a foundational corpus based on the literature textbook for grade 5. This corpus aims to develop a methodology for selecting literary works that align with students' intellectual potential. If 5th-grade pupils develop a love for reading literary works, they are likely to continue reading throughout their lives, which can positively impact their future.
Methodology for Creating "School Literature Corpus" for Grade 5
Download: Obtain the PDF version of the 5th-grade literature textbookfrom free Android app MAKTAB DARSLIKLARI | SCHOOL TEXTBOOKS.
Format Conversion: Convert the PDFs to text format using appropriate tools.
Text Cleaning: Remove punctuation, special characters, and other unnecessary elements from the text.
Tokenization: Break the cleaned text into tokens, phrases, or sentences.
Corpus Assembly: Compile the tokenized texts into a structured file.
Data Storage: Save the corpus dataset in a text file.
Algorithm: Count Tokens, Sentences, and Unique Words
The algorithm for creating the literature corpus based on the 5th-grade school literature textbook is implemented using the following steps Input: Literature corpus (text file)
Output: Number of tokens, number of sentences, number of unique words Steps:
1. Begin
2. Load Corpus
Load the literature corpus from the text file.
3. Initialize Counters
Set tokencount to 0
Set sentence count to 0
Initialize unique_words as an empty set
4. Process Each Text
For each text in the corpus:
1. Tokenization Tokenize text into tokens
2. Sentence Splitting Split text into sentences
3. Update Counts
token_count = token_count + Length of tokens sentence_count = sentence_count + Length of sentences
4. Update Unique Words For each token in tokens: Add token to unique_words
5. Count Unique Words
Set unique_word_count to the Length of unique_words
6. Output Results
Print "Number of tokens: ", token_count
Print "Number of sentences: ", sentence_count
Print "Number of unique words: ", unique_word_count
7. End
DISCUSSION AND RESULTS
Based on the created Literature Corpus, various studies related to the educational process of the literature class can be conducted. In particular, it can be used for several purposes, such as developing educational content, language learning, creating a tagged corpus, selecting appropriate textbooks for 5th graders, preparing exam materials, parallel vocabulary, and applications for 5th grade. This corpus consists of tokens, sentences, and unique words, as shown in Table 1.
Table 1: Literary Metrics for 5th Grade Corpus: Writers, Tokens, Unique Words, and
Sentences
Grade Number of Writers Total Tokens Number of Sentences Unique words
5 th 23 67476 6396 20696
This table provides an overview of the literary content studied in the 5th grade. It includes the total number of writers covered, the number of sentences in the text, the count of unique words, and the total number of tokens used in the literature curriculum
Table 2. List of Authors Being Studied in the 5th Grade Literature Textbook
The works of the following writers are studied in the 5th-grade literature textbook. We list the names of these authors in Table 2 in the same order as they appear in the textbook.
№ Names of Writers Description of Nationality and Field
1. Imom Bukhory Uzbek, notable Islamic scholar.
2. Aesop Greek, fable writer (famous for Aesop's Fables).
3. Khamid Olimjon Uzbek poet.
4. Maqsud Shayxzoda Uzbek writer and poet.
5. Jonathan Swift English satirist, known for Gulliver's Travels.
6. Hans Christian Andersen Danish author, known for fairy tales
7. Abdulla Kodiry Uzbek novelist.
8. Mirkarim Osim Uzbek writer and poet.
9. Gafur Gulom Uzbek poet and writer.
10. Oybek Uzbek poet and writer.
11. Usmon Nosir Uzbek poet.
12. Mirtemir Uzbek poet and writer.
13. Askad Mukhtor Uzbek writer.
14. Utkir Khoshimov Uzbek writer and public figure.
15. Antoine de Saint-Exupéry French writer, known for The Little Prince.
16. Alisher Navoy Uzbek and Turkic, famous poet and philosopher
17. Zakhiriddin Mukhammad Bobur Uzbek, founder of the Mughal Empire and poet.
18. Mukhammad Aminkhuja Mukimy Uzbek poet.
19. Sa'dy Sherozy Persian poet, known for Gulistan and Bustan.
20. Abdulla Avlony Uzbek educator and writer.
21. Erkin Vokhidov Uzbek poet and writer.
22. Abdulla Oripov Uzbek poet.
23. Nodar Dumbadze Georgian writer.
This table presents a curated list of 23 influential writers from diverse cultural backgrounds, including Uzbek, Greek, English, Danish, French, Persian, and Georgian. It provides detailed information on each writer's nationality and field of expertise, featuring prominent figures such as Imom Bukhory, a notable Islamic scholar, and Alisher Navoy, a renowned 15th-century poet and philosopher. Internationally, it includes Aesop, the Greek fable writer; Jonathan Swift, the English satirist known for Gulliver's Travels; and Antoine de Saint-Exupéry, the French author of The Little Prince.
This list is crucial for the curriculum as it exposes students to a broad spectrum of literary traditions and styles, enhancing their cultural awareness, literary appreciation, and language skills. By engaging with these diverse authors, students gain a richer understanding of both local and global literary heritage, contributing to their overall educational development.
Table 3. List of Literary Works in Uzbek and Their English Equivalents
№ Name of Literary work (Uzbek) English
1. doston epic
2. ertak fairy tale
3. hadis hadith (Islamic tradition)
4. hikoya story
5. maqol proverb
6. masal fable
7. qasida qasida (a form of poetry)
8. qissa tale (or short story)
9. ruboiy rubai (a type of quatrain)
10. sayohatnoma travelogue
11 she'r poem
12. topishmoq riddle
This table provides a list of various literary terms in Uzbek along with their English
equivalents. It includes a range of genres and forms:
Doston - Epic: A lengthy narrative poem detailing heroic deeds and events.
Ertak - Fairy Tale: A short story featuring magical or fantastical elements.
Hadis - Hadith (Islamic Tradition): Recorded sayings and actions of the Prophet Muhammad.
Hikoya - Story: A narrative that recounts events or experiences.
Maqol - Proverb: A traditional saying that expresses a general truth or piece of advice.
Masai - Fable: A brief story, often with animals as characters, that conveys a moral lesson.
Qasida - Qasida: A form of poetry, typically an ode with a specific structure.
Qissa - Tale (or Short Story): A brief narrative often focusing on a single incident or character.
Ruboiy - Rubai: A type of quatrain or four-line verse, often used in Persian and Turkic
poetry.
Sayohatnoma - Travelogue: A narrative describing the experiences and observations of a journey.
She'r - Poem: A composition written in verse that expresses ideas, emotions, or stories.
Topishmoq - Riddle: A question or statement requiring ingenuity to solve or interpret.
This table serves as a useful reference for understanding different literary forms and genres in both Uzbek and English.
CONCLUSION
The development of a literature corpus tailored to 5th-grade students represents a crucial advancement in educational practice, offering numerous benefits to students, educators, and the educational process as a whole. This paper has outlined a comprehensive methodology for creating such a corpus, utilizing Natural Language Processing (NLP) tools and techniques to ensure that selected literary works are aligned with students' intellectual abilities and developmental needs.
Importance of the Literature Corpus: A well-constructed literature corpus serves as a foundational tool for selecting and organizing literary works appropriate for the educational level of students. For 5th-grade students, who are at a critical stage of cognitive and linguistic development, exposure to literature that matches their intellectual capacity is essential. This corpus
not only helps in curating a diverse selection of texts but also in ensuring that these texts contribute effectively to vocabulary enrichment, comprehension skills, and overall academic growth. By focusing on texts that are developmentally appropriate, educators can provide a more engaging and relevant reading experience for students.
NLP Tools and Techniques: In the creation of this corpus, various NLP tools and techniques have been employed to facilitate the selection and categorization of texts. NLP methods, such as text classification, tokenization, and named entity recognition, are used to analyze and process large volumes of text data efficiently. Text similarity measures, like cosine similarity, are particularly useful for evaluating how closely literary works align with the intended educational objectives. By comparing the semantic content of different texts, cosine similarity helps in selecting works that are not only relevant but also suitable for the students' level of understanding.
Educational Benefits: The establishment of a literature corpus tailored to 5th-grade students offers significant educational benefits. For students, engaging with texts that are carefully chosen based on their intellectual abilities helps in developing critical reading and analytical skills. It also fosters a love for reading by introducing them to a variety of literary genres and styles, which can enhance their overall educational experience. For teachers, this corpus provides a structured framework for curriculum planning and instruction. It allows educators to easily access and incorporate appropriate literary works into their teaching materials, ensuring that the content is both relevant and pedagogically sound.
Benefits for Teachers and Students: For educators, the corpus simplifies the process of selecting appropriate reading materials, reducing the time and effort required to curate content manually. It also supports differentiated instruction by offering a range of texts that cater to varying levels of ability within the classroom. This can lead to more effective teaching strategies and better student outcomes. For students, the benefits are multifaceted. Exposure to a diverse array of texts can broaden their literary horizons and enhance their language skills. Additionally, engaging with texts that are aligned with their cognitive development ensures that they are challenged appropriately without being overwhelmed. This alignment helps in building a solid foundation for future academic success and fosters a lifelong appreciation for literature.
Using Text Similarity for Selection: The application of text similarity measures, such as cosine similarity, plays a critical role in refining the selection process within the corpus. By quantifying the similarity between texts, educators can ensure that the literary works included are not only relevant but also complement one another in terms of content and complexity. This methodological approach allows for a more precise and targeted selection of texts, enhancing the overall quality of the literature corpus and its alignment with educational objectives.
In conclusion, the creation of a literature corpus tailored to 5th-grade students represents a significant advancement in educational practice. By leveraging NLP tools and techniques, educators can develop a resource that supports effective curriculum planning and enhances the reading experience for students. The benefits of this approach extend beyond the classroom, contributing to the development of critical reading skills, vocabulary enrichment, and a lifelong passion for literature. The incorporation of text similarity measures ensures that the selected literary works are both appropriate and enriching, reinforcing the importance of a well-structured and thoughtfully curated literature corpus in the educational process.
FUTURE WORK
Future work will focus on expanding the literature corpus to cover grades 5 through 9, addressing the diverse needs of students across these educational stages. This expansion will involve curating age-appropriate texts and integrating advanced NLP techniques to analyze text complexity and thematic relevance. By aligning the corpus with curriculum standards and developing supplementary educational resources such as lesson plans and activity guides, we aim to enhance teaching and learning experiences. Additionally, improvements to the digital platform will include features for better usability and personalized recommendations. Evaluating the impact on student engagement and academic performance will guide further refinements, ensuring the corpus effectively supports educational goals and fosters a love of reading.
REFERENCES
1. Vodicka, Felix. "The Concretization of the Literary Work". The Prague School: Selected Writings, 1929-1946, edited by Peter Steiner, New York, USA: University of Texas Press, 1982, pp. 103-134. https://doi.org/10.7560/780439-008
2. Niyozmetova Roza Khasanovna. (2023). SELECTION OF WORKS BASED ON NEW UZBEK LITERATURE: PROBLEMS AND SOLUTIONS. World Bulletin of Social Sciences, 22, 170-173.
3. Abdurakhmonova N. et al. Uzbek electronic corpus as a tool for linguistic analysis //Компьютерная обработка тюркских языков. TURKLANG 2022. - 2022. - С. 231-240.
4. Vosiljonov, Azizbek. "Basic Theoretical Principles of Corpus Linguistics." Academicia Globe, vol. 3, no. 02, 2022, pp. 173-175, doi:10.17605/OSF.IO/36RWP.
5. Can E. F. et al. Automatic categorization of ottoman literary texts by poet and time period //Computer and Information Sciences II: 26th International Symposium on Computer and Information Sciences. - Springer London, 2012. - С. 51-57.
6. Say B. et al. Development of a corpus and a treebank for present-day written Turkish //Proceedings of the eleventh international conference of Turkish linguistics. - Eastern Mediterranean University, 2002. - С. 183-192
7. Akanova, A. et al. "Development of the Algorithm of Keyword Search in the Kazakh Language Text Corpus." 2019.
a. Madatov, D. J. Khujamov, and B. R. Boltayev, "Creating of the Uzbek WordNet based on Turkish WordNet," in AIP Conference Proceedings, 2022. doi: 10.1063/5.0089532.
8. K. Madatov, S. Bekchanov, and J. Vicic, "Dataset of stopwords extracted from Uzbek texts," Data Brief, vol. 43, 2022, doi: 10.1016/j.dib.2022.108351
9. Madatov, K. A., and Sattarova, S. "Creation of a Corpus for Determining the Intellectual Potential of Primary School Students." 2024 IEEE 25th International Conference of Young Professionals in Electron Devices and Materials (EDM), Altai, Russian Federation, 2024, pp. 2420-2423. doi:10.1109/EDM61683.2024.10615103
10. Abjalova, M., Adali, E., Iskandarov, O. "Educational Corpus of the Uzbek Language and Its Opportunities." 2023 8th International Conference on Computer Science and Engineering (UBMK), IEEE, 2023, pp. 590-594.
11. Madatov, K., Bekchanov, S., and Vicic, J. "Accuracy of the Uzbek Stop Words Detection: A Case Study on 'School Corpus.'" CEUR Workshop Proceedings, 2022.
12. Salaev, U., Kuriyozov, E., and Gómez-Rodríguez, C. "A Machine Transliteration Tool Between Uzbek Alphabets." CEUR Workshop Proceedings, vol. 3315, 2022, pp. 42-50.
13. Madatov, K. A., and Bekchanov, S. K. "The Algorithm of Uzbek Text Summarizer." 2024 IEEE 25th International Conference of Young Professionals in Electron Devices and Materials (EDM), Altai, Russian Federation, 2024, pp. 2430-2433. doi:10.1109/EDM61683.2024.10615191
14. Sharipov, M., Mattiev, J., Sobirov, J., and Baltayev, R. "Creating a Morphological and Syntactic Tagged Corpus for the Uzbek Language." CEUR Workshop Proceedings, vol. 3315, 2022, pp. 93-98.
15. Мадатов Х., Саттарова С. Using the Jaccard similarity method for recommendation system of books //Общество и инновации. - 2024. - Т. 5. - №. 1. - С. 59-69
16. Sattarova S. Advancing natural language processing in uzbek: challenges and solutions: Advancing natural language processing in uzbek: challenges and solutions //MODERN PROBLEMS AND PROSPECTS OF APPLIED MATHEMATICS. - 2024. - Т. 1. - №. 01.
17. Khodjinazarovna B. F., Kamaliddinovich S. A., Beknazarovna S. S. Visualizing the solar system using python and its importance in education //International journal of advanced research in education, technology and management. - 2023. - Т. 2. - №. 6.
18. Sattarova S. B., Bekchanova F. X., Shermetov A. K. Terminologik lug'at yaratish texnologiyasi va uning ta'lim tizimidagi ahamiyati //Academic research in educational sciences. - 2023. - Т. 4. - №. 5. - С. 422-434.
19. Beknazarovna S. THE IMPORTANCE OF ELECTRONIC CATALOGS IN THE DEVELOPMENT OF READING CULTURE //ILM SARCHASHMALARI (2). - 2024. - С. 193-197.
20. Madatov X. A., Sattarova S. B. YOSHLARDA KITOBXONLIK MADANIYATINI RIVOJLANTIRISHNING ASOSIY OMILLARI //Educational Research in Universal Sciences. - 2023. - Т. 2. - №. 17. - С. 1017-1025
21. Madatov, Khabibulla, and Sapura Sattarova. "Vectorization of Uzbek Texts Using the TF-IDF Vectorizer Method." O'zMU XABARLARI, vol. 11, 2023, pp. 177-180. ISSN 2181-7324.
