Sapura Sattarova

This paper presents a baseline study on automatic Uzbek text classification. Uzbek is a morphologically rich and low-resource language, which makes reliable preprocessing and evaluation challenging. The approach integrates Term Frequency–Inverse Document Frequency (TF–IDF) representation with three conventional methods: linear regression (LR), k-Nearest Neighbors (k-NN), and cosine similarity (CS, implemented as a 1-NN retrieval model). The objective is to categorize school learning materials by grade level (grades 5–11) to support improved alignment between curricular texts and students’ intellectual development. A balanced dataset of Uzbek school textbooks across different subjects was constructed, preprocessed with standard NLP tools, and converted into TF–IDF vectors. Experimental results on the internal test set of 70 files show that LR achieved 92.9% accuracy (precision = 0.94, recall = 0.93, F1 = 0.93), while CS performed comparably with 91.4% accuracy (precision = 0.92, recall = 0.91, F1 = 0.92). In contrast, k-NN obtained only 28.6% accuracy, confirming its weakness in high-dimensional sparse feature spaces. External evaluation on seven Uzbek literary works further demonstrated that LR and CS yielded consistent and interpretable grade-level mappings, whereas k-NN results were unstable. Overall, the findings establish reliable baselines for Uzbek educational text classification and highlight the potential of extending beyond lexical overlap toward semantically richer models in future work.

This paper presents an approach to automatic Uzbek text classification. Uzbek language is a morphologically rich and low-resource language. The approach integrates Term Frequency–Inverse Document Frequency (TF-IDF) representation with conventional machine learning and similarity-based approaches. The aim is to categorize learning materials at the school grade level to support improved alignment of materials and student learning outcomes. In order to carry out the research, a dataset of 5th-11th grade school textbooks in different subjects was collected. The texts were preprocessed using standard natural language processing (NLP) tools and were transformed into TF-IDF vectors. These were used to train three common classification models: Logistic Regression (LR), k-Nearest Neighbors (k-NN), and Cosine Similarity (CS).Each new input text is compared with the grade-level textbook corpus, and the grade with the highest similarity is selected. It provides an estimate of the appropriate intellectual level for the material. The experimental findings indicate that Logistic Regression achieved 82% accuracy, and Cosine Similarity performed slightly better at 85.7%. Conversely, the k-NN method achieved only 22% accuracy, indicating its low applicability for Uzbek text classification. Overall, the proposed approach demonstrates practical value for pedagogical purposes and potential applicability to wider document analysis issues.

The selection of relevant literature for middle school students is crucial for enhancing their intellectual growth and fostering their interest in reading. This study presents a neural network-based natural language processing approach for optimizing literary selection. Texts from the “School Literature Corpus,” derived from Uzbek school literature textbooks, were preprocessed and represented as embeddings using the transformer model all-MiniLM-L6-v2. By applying cosine similarity, literary works were aligned with the intellectual and vocabulary levels of specific grades, enabling personalized and context-aware recommendations. The results demonstrate that this method yields more meaningful literature recommendations, enriching curricula and fostering critical thinking, literacy, and a lifelong love of reading. This approach provides educators and institutions with learning materials tailored to the intellectual potential of their students, supporting the development of knowledgeable, curious, and intellectually gifted learners. Furthermore, it ensures continuous improvement in educational quality and contributes to the advancement of society's future.

The issue of creating an educational corpus suitable for the intellectual potential of primary school students is one of the important tasks for improving the quality of education. If students read textbooks and educational literature that are not suitable for their age and intellectual capacity, they will not understand this information well and will not be able to fully master the necessary educational material. As a result, their interest in education decreases. Therefore, students should be provided with appropriate learning materials for their age and intellectual ability. With the help of the corpus for determining the intellectual potential of primary school students, it is possible to apply educational materials suitable for the intellectual potential of students to the educational process. This increases students’ interest in learning and calls them to learn more. This article considers the issue of creating a corpus for determining the intellectual potential of primary school students based on school textbooks. The educational corpus was created based on 35 primary school textbooks approved by the Ministry of Preschool and School Education of the Republic of Uzbekistan. The problem was completely solved based on primary school textbooks based on the Uzbek language.

Основная цель педагогики – воспитать молодое поколение зрелыми, знающими и всесторонне развитыми личностями. В связи с этим одной из главных задач системы образования является: формирование культуры чтения среди молодежи, обеспечение ее учебниками и произведениями искусства, соответствующими ее возрасту и интеллектуальному потенциалу. Но только если юные читатели будут читать книги, соответствующие их интеллектуальному потенциалу и учитывающие их возрастные особенности, их знания, духовность, мировоззрение и другие положительные стороны будут развиваться. Если учащиеся будут читать произведения, не соответствующие их возможностям, они не смогут полностью усвоить содержание прочитанного произведения, и информация в книге будет их «утяжелять». В результате у читателя может угаснуть желание читать. Читателям не следует выбирать литературу, которая поверхностна по содержанию, несовместима с нашей национальной духовностью и ценностями, нравственными нормами и способна оказать негативное влияние на образование молодежи. Поэтому необходимо создать систему рекомендации произведений, соответствующую интеллектуальному потенциалу читателей. В данной статье рассматривается применение метода подобия Жаккара для создания подходящих списков чтения для старшеклассников. Для этого на основе учебников литературы высокого класса создается корпус и этот корпус сравнивается с литературными произведениями. Книги с наибольшим результатом сходства рекомендуются к прочтению. Проблема была успешно решена на основе учебников литературы для учащихся 5-11 классов и произведений искусства на узбекском языке.