Aktayeva Alimbubi
Aktayeva Alimbubi has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Akky Kubigenova
S. Seifullin Kazakh Agrotechnical research University
2 shared publications - Rozamgul Niyazova
Department of Artificial Intelligence Technologies, L.N. Gumilyov Eurasian National University, Astana 010008, Kazakhstan
2 shared publications - Aidyn Daurenova
Abay Myrzakhmetov Kokshetau University
1 shared publication - Aigerim Ismukanova
Kokshetau University named after Sh. Ualikhanov
1 shared publication - Altynbek Sharipbay
L.N. Gumilyov Eurasian National University
1 shared publication - Bibigul Razakhova
L.N. Gumilyov Eurasian National University
1 shared publication
Latest Publications
- 1 December 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (6) , 5532-5555
Intelligent educational question–answer systems for consultation and assessment: methods, challenges, and prospects
Automated assessment of open-ended responses is challenging in multilingual and low-resource educational settings because annotated corpora and language-specific semantic resources are limited. Educational question–answer systems often separate psychometric modelling from natural language processing (NLP), restricting the integration of ability estimation and semantic interpretation. This study developed and evaluated an interpretable hybrid framework that combines three-parameter item response theory (IRT) adaptive testing with contextual semantic evaluation using language embeddings and cosine similarity. The framework integrates adaptive item selection, response interpretation, ability estimation, and diagnostic feedback. KazQAD, a Kazakh question-answer dataset comprising over 12,000 annotated pairs, was developed to support this study. An evaluation involving 350 undergraduates compared fixed-form computer-based testing (CBT), standalone IRT-based adaptive testing, and the hybrid framework. Among the three approaches, the hybrid framework showed the strongest correlation with expert assessment (r=0.91), the lowest mean standard error of ability estimation (SE=0.08), and the shortest average assessment duration (23 minutes vs 42 minutes for fixed-form CBT), a 45.2% reduction. These findings support integrating psychometrically calibrated estimation with semantic interpretation within a unified adaptive workflow for Kazakh-language assessment. However, this study did not directly benchmark contemporary transformer-based semantic graders, and the findings remain specific to the evaluated conditions and do not establish universal superiority.
- 1 December 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (6) , 5532-5555
Intelligent educational question–answer systems for consultation and assessment: methods, challenges, and prospects
Automated assessment of open-ended responses is challenging in multilingual and low-resource educational settings because annotated corpora and language-specific semantic resources are limited. Educational question–answer systems often separate psychometric modelling from natural language processing (NLP), restricting the integration of ability estimation and semantic interpretation. This study developed and evaluated an interpretable hybrid framework that combines three-parameter item response theory (IRT) adaptive testing with contextual semantic evaluation using language embeddings and cosine similarity. The framework integrates adaptive item selection, response interpretation, ability estimation, and diagnostic feedback. KazQAD, a Kazakh question-answer dataset comprising over 12,000 annotated pairs, was developed to support this study. An evaluation involving 350 undergraduates compared fixed-form computer-based testing (CBT), standalone IRT-based adaptive testing, and the hybrid framework. Among the three approaches, the hybrid framework showed the strongest correlation with expert assessment (r=0.91), the lowest mean standard error of ability estimation (SE=0.08), and the shortest average assessment duration (23 minutes vs 42 minutes for fixed-form CBT), a 45.2% reduction. These findings support integrating psychometrically calibrated estimation with semantic interpretation within a unified adaptive workflow for Kazakh-language assessment. However, this study did not directly benchmark contemporary transformer-based semantic graders, and the findings remain specific to the evaluated conditions and do not establish universal superiority.
- Open Access
- 16 March 2025
- Published by Innovative Research Publishing in International Journal of Innovative Research and Scientific Studies
- Vol. 8 (3) , 2413-2430
Development of a smart textbook in informatics with interactive learning support and Kazakh language integration based on artificial intelligence technologies
This article presents a project for developing interactive models of an educational resource for determining the semantic proximity between the ontology of knowledge extracted from a knowledge base based on a given question and the ontology generated from a student's answer in computer science. A general methodology for developing software has been proposed. This methodology will form the basis for the automated creation of smart textbooks on computer science in the Kazakh language using ontological models and thesauri. These educational resource models are suitable for any type of educational process (Blended Learning Technology (BLT), full-time, part-time). For example, the article describes an online smart textbook that will adapt to the student's individual learning path by providing personalized text, audio, and video materials, asking questions, and evaluating answers with an indication of percentage accuracy. A pedagogical experiment has been conducted to assess the students' performance. The online smart textbook will adapt to the student's learning style by providing personalized text, audio, and video materials. It will also ask questions and evaluate answers with an indication of percentage accuracy. In addition, completed assignments were analyzed to assess students' progress using static digital materials and standard computer testing systems for a dynamic, intelligent learning environment and knowledge assessment. The results show that the proposed methodology has great potential for increasing student engagement in studying the formalization and processing of the grammar of the Kazakh language using production rules and, based on them, developing a grammar processor, creating ontologies, thesauri, and knowledge bases on the content of “Computer Science”.
- 16 March 2025
- Published by Innovative Research Publishing in International Journal of Innovative Research and Scientific Studies
- Vol. 8 (3) , 2413-2430
Open AccessDevelopment of a smart textbook in informatics with interactive learning support and Kazakh language integration based on artificial intelligence technologies
This article presents a project for developing interactive models of an educational resource for determining the semantic proximity between the ontology of knowledge extracted from a knowledge base based on a given question and the ontology generated from a student's answer in computer science. A general methodology for developing software has been proposed. This methodology will form the basis for the automated creation of smart textbooks on computer science in the Kazakh language using ontological models and thesauri. These educational resource models are suitable for any type of educational process (Blended Learning Technology (BLT), full-time, part-time). For example, the article describes an online smart textbook that will adapt to the student's individual learning path by providing personalized text, audio, and video materials, asking questions, and evaluating answers with an indication of percentage accuracy. A pedagogical experiment has been conducted to assess the students' performance. The online smart textbook will adapt to the student's learning style by providing personalized text, audio, and video materials. It will also ask questions and evaluate answers with an indication of percentage accuracy. In addition, completed assignments were analyzed to assess students' progress using static digital materials and standard computer testing systems for a dynamic, intelligent learning environment and knowledge assessment. The results show that the proposed methodology has great potential for increasing student engagement in studying the formalization and processing of the grammar of the Kazakh language using production rules and, based on them, developing a grammar processor, creating ontologies, thesauri, and knowledge bases on the content of “Computer Science”.
- Open Access
- 28 June 2024
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (2 (129)) , 69-82
Development of quantum computing algorithm of technology for monitoring learning results
The present publication considers implementing an online control proctoring system, with the possibility of using methods and models of pattern recognition using algorithmic quantum computing to conduct online exams. The study's object is the protection method within infrastructure proctoring systems in education. The study aims to create a security system for proctoring technology infrastructure in education. The article proposes an alternative approach to building protection systems with an effective recognition model using algorithmic quantum computing in proctoring platforms. This study addresses these issues and proposes a novel approach to generating a random cryptographic key using multimodal biometric technology. A presented quantum algorithm method for computer simulation of the data processing quantum principles allows studying and analysing how the created model for transforming a classical image into a quantum state works. This method also shows the possibilities of quantum information theory in interpreting classical problems or how to optimise the same, taking into account the development of methods for the functioning of models and algorithms for quantum computing, data protection and security of online video communications in a proctoring system in an educational environment. The novelty of this research is expressed primarily in the constant updating and addition of authentication systems using quantum computing in various aspects, including the proctoring system in the educational environment. Also, scientific novelty is associated with insufficient similar research in the information space. The practical significance is due to the need in the current situation to attract attention to existing problems in structuring the infrastructure of a monitoring system within planning and coordinating the protection, thereby enhancing learning outcomes by eliminating security flaws using a quantum computing algorithm for pattern recognition
- 28 June 2024
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (2 (129)) , 69-82
Open AccessDevelopment of quantum computing algorithm of technology for monitoring learning results
The present publication considers implementing an online control proctoring system, with the possibility of using methods and models of pattern recognition using algorithmic quantum computing to conduct online exams. The study's object is the protection method within infrastructure proctoring systems in education. The study aims to create a security system for proctoring technology infrastructure in education. The article proposes an alternative approach to building protection systems with an effective recognition model using algorithmic quantum computing in proctoring platforms. This study addresses these issues and proposes a novel approach to generating a random cryptographic key using multimodal biometric technology. A presented quantum algorithm method for computer simulation of the data processing quantum principles allows studying and analysing how the created model for transforming a classical image into a quantum state works. This method also shows the possibilities of quantum information theory in interpreting classical problems or how to optimise the same, taking into account the development of methods for the functioning of models and algorithms for quantum computing, data protection and security of online video communications in a proctoring system in an educational environment. The novelty of this research is expressed primarily in the constant updating and addition of authentication systems using quantum computing in various aspects, including the proctoring system in the educational environment. Also, scientific novelty is associated with insufficient similar research in the information space. The practical significance is due to the need in the current situation to attract attention to existing problems in structuring the infrastructure of a monitoring system within planning and coordinating the protection, thereby enhancing learning outcomes by eliminating security flaws using a quantum computing algorithm for pattern recognition