Abstract
The article presents a system for the classification of Kazakh language documents based on subject areas, employing techniques such as tokenization, stemming, and term-matching. The system, named “Kazakh Language Document Classifier by Subject Area,” targets documents in education, employment, and medicine, aiming to address the challenges of document management and information retrieval in multilingual settings. The process begins with document preprocessing, including morphological analysis of Kazakh text, followed by the automatic identification of keywords using N-grams, TF-IDF, and syntactic tags. By leveraging databases of subject-specific terms, the system organizes documents into relevant categories, enhancing retrieval efficiency. The implementation also integrates the Apache POI library for handling MS Office Word documents. The classifier's accuracy is evaluated, showing initial success in categorizing documents. Further development aims to improve accuracy through data expansion and the establishment of classification thresholds, contributing to advancements in natural language processing for Kazakh. This system holds promise for educational applications and cross-disciplinary document analysis.