Talk · International Conference on Computer Science and Engineering · September 17, 2025
Explainable Artificial Intelligence Methods in Text Classification of Machine Learning Models for Tatar Language
Fail Mubarakovich Gafarov, Viliuza R. Gafarova, Madehur M. Ayupov
Abstract
Text classification involves assigning predefined labels to textual data. While traditional machine learning models (e.g., Random Forest, Logistic Regression) and deep learning architectures (e.g., RNNs, Transformers, BERT) are effective, their complexity often renders them opaque "black boxes," limiting interpretability—especially in low-resource languages like Tatar. This paper presents an explainable AI framework for explanation text classification task for Tatar language, combining five ML models (Random Forest, KNN, Decision Tree, Logistic Regression, Gradient Boosting) with a fine-tuned BERT-based classifier. To enhance transparency of trained text classification models we integrated Explainable AI (XAI) techniques—LIME, SHAP, and Integrated Gradients. These methods allow to generate human-readable explanations for each prediction. The main objective of this paper is to show how machine learning-based natural language processing methods enhanced by Explainable AI methods can be applied in NLP tasks for Tatar language.
More by Fail Gafarov
- Predicting Changes in Personality Behavior Under the Influence of an InterlocutorRussian Digital Libraries Journal · 2026
- RNN-Based Approach to Cognitive Architecture of Subject Behavior in Digital EnvironmentInternational Conference on Computer Science and Engineering · 2026
- Cross-Model Analysis of Token-Level Explanations in Tatar Text ClassificationUral Symposium on Biomedical Engineering, Radioelectronics and Information Technology · 2026
- СРАВНИТЕЛЬНЫЙ АНАЛИЗ МОДЕЛЕЙ АРХИТЕКТУРЫ TRANSFORMER В ЗАДАЧЕ УПРОЩЕНИЯ ТЕКСТАВысшая школа: научные исследования · 2025
