30 August 2025 in Science for Education Today
KUKazan Federal University
Introduction. The article presents the results of a study on generating high-quality educational content in mathematical literacy for 5th-grade students using generative AI. The problem stems from the lack of adaptive assignments that meet educational standards and the limitations of AI (hallucinations, non-reproducibility). The aim of the study is to develop, test, and evaluate the effectiveness of an original prompt-engineering strategy for generating pedagogically relevant and age-appropriate math problems. Materials and Methods. The study employs systemic and activity-based approaches. Methods include analysis of AI applications in education, experimental task generation using a hybrid prompt-engineering strategy (Few-Shot Learning + Chain-of-Thought + Role Prompting) based on ChatGPT-4o, expert evaluation (10 mathematics teachers with ≥12 years of experience), and statistical data processing (Cohen’s κ, mean values µ). Verification involved generating tasks in a new context (airports) and assessing them based on adequacy, student-appropriateness, and complexity criteria. Results. Key findings demonstrate the successful implementation of the strategy, enabling the generation of structurally consistent tasks (κ = 0.82). The critical role of Chain-of-Thought prompting in creating multi-step problems is emphasized. The authors highlight the dual functionality of tasks (learning and assessment). The experiment confirmed high expert ratings for adequacy (µ = 4.81), format compliance (µ = 4.77), and descriptive completeness (µ = 4.82). A limitation in terminology complexity for some tasks was identified. Conclusions. The study concludes that the combined prompt-engineering strategy is highly effective for generating standards-aligned tasks and has strong potential for integration into digital learning platforms. Further optimization of linguistic adaptation and the development of a validation pipeline are required for implementation.
26 December 2018 in Cypriot Journal of Educational Sciences
The aim of the study was to develop the web-based teaching course for use in the process of ICT learning by the Tatar-speaking students. We developed the training materials in computer science, based on Wikia, and conducted educational experiment on their usage. The first-year students of Higher School of Tatar Philology and Intercultural Communication of Kazan Federal University took part in the experiment. They were divided into two groups. The experimental group consisted of 25 trainees, control group included 25 students. The educational experiment was carried out during one semester of the academic year 2015/16 and 2016/17. In teaching of the subject “Computer science” (36 hours) the technology CLIL and Web 2.0-based training materials were used in the experimental group. Computer science teaching in the control group was provided in Russian, by means of traditional methods. The students were tested at the final stage of educational experiment. Processing of the results with the help of statistical methods led to the conclusion that the positive changes in the experimental group were due to CLIL-assisted training, using teaching materials, developed on the basis of Web 2.0 technologies. Keywords: Web 2.0, the Tatar language, the Russian language, adoptive language, learning content, Wiki.
15 December 2024 in Russian language studies
Implemented within text analytics as one of the strategic directions of modern Russian linguistics, the research focuses on the linguistic profiling of educational and artistic texts. The identified genre features contribute to software systems development and big language data processing. The study is aimed at revealing the ranges of linguistic parameters which differentiate educational (secondary) and artistic (primary) texts. The study was based on 72 biographies from textbooks on Russian as a foreign language and 90 excerpts from adventure stories. The genres were chosen for the contrastive study for the following reasons: (1) a high degree of narrativity and actions; (2) functional differences, namely, informative function of biography and entertaining function of adventure stories. The research corpus comprised 120932 words. Two data processing tools were used in the study: (1) the linguistic parameters were calculated using RuLingva platform, (2) STATISTIKA program was used to identify statistically significant differences between the two genres. The revealed genre-specific parameters include global and local overlaps of nouns and arguments, nouns in prepositional and genitive cases, past and present verb forms. Global and local overlaps of nouns and arguments were found to contribute to high cohesion of biographies, because the nomination of each next event in the person's life in connected with the previous one. The genitive case prevails in biographies due to the use of nominative word combinations. The research perspective is seen in the typology of genres based on linguistic profiling of official and personal biographies, on the one hand, and adventure novels, on the other hand. An important aspect of further research in the studied area is the installation of meaning matrices in the RuLingva text profiler to automate text linguistic profiling.
30 December 2025 in Science for Education Today
Introduction. Modern education faces a contradiction between the active integration of generative artificial intelligence and its underexplored potential for providing evaluative feedback in development students’ mathematical literacy. The purpose of the article is to identify the potential of using a generative language model as a teacher’s tool for generating expert-level evaluative feedback when assessing open-ended mathematical problems Materials and Methods. The research is based on systemic-activity, criteria-oriented, and comparative approaches. Methods employed included theoretical analysis of scholarly literature, criteria-based assessment combined with prompt engineering techniques, as well as quantitative and qualitative analysis to determine the agreement between the evaluative feedback generated by the language model and that provided by a human expert. The sample consisted of 51 students Results. The research experimentally confirmed the feasibility of using generative artificial intelligence for providing evaluative feedback in mathematics education. An effective strategy for automating the assessment of open-ended mathematical problems was developed and substantiated, based on criteria-based assessment and prompt engineering techniques using GigaChat Pro language model. Empirical data revealed a moderate agreement between the evaluative feedback generated by GigaChat Pro and that provided by an expert teacher: accuracy reached 73%, Cohen’s coefficient (k) was 0,57, and the semantic similarity of textual comments (BertScore F1) was 0,614.