Bimoldina Zharkyn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bimoldina Zharkyn has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Aigul Skakova
Nur-Mubarak University
1 shared publication Al-Farabi Kazakh National University
1 shared publication- Bilimzhankyzy Nazerke
Turan University
1 shared publication - Gulnar Astaubayeva
Narxoz University
1 shared publication I. Tereikovski
1 shared publication- Kalamkas Bagitova
Атырауский университет имени Х. Досмухамедова, Атырау, Казахстан
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by D. Serikbayev East Kazakhstan Technical University in EKTU Journal of Information and Communication Sciences
- Vol. 1 (3) , 43
THE DEVELOPMENT OF ARTIFICIAL INTELLIGENCE IN KAZAKHSTAN AND THE USE OF BIG DATA TECHNOLOGIES TO ANALYZE THE "DIGITAL FAMILY MAP" IN ORDER TO IMPROVE THE EFFICIENCY OF PUBLIC SERVICES
Thearticle examinesthe developmentof artificialintelligence andbig datatechnologies inthe Republicof Kazakhstanwithin theframework ofthe digitaltransformation ofpublic administration. The relevanceof thestudy isdetermined bythe needto enhancethe targetingof socialpolicy andto improvethe efficiencyof publicservice deliverythrough theanalysis oflarge-scalesocio-demographicdata sets. The aimof theresearch isto assessthe potentialof applyingintelligent algorithmsand bigdata processingtools inthe analysisof theDigital FamilyMap asa componentof thestate informationinfrastructure. Thestudy employssystemic andinstitutional analysis, a comparativeapproach, andelements ofapplied dataanalytics. Thefindings identifykey directionsfor integratingintelligent technologiesinto publicdecision-makingprocesses andsubstantiate theiradvantages interms offorecasting accuracyand resourceoptimization. Thescientific noveltylies inthe comprehensiveassessment ofintegrating intelligentdata analysistechnologies intothe socialsphere, whilethe practicalsignificance isreflected inthe potentialto improvemechanisms fordelivering publicservices.
- 30 September 2026
- Published by D. Serikbayev East Kazakhstan Technical University in EKTU Journal of Information and Communication Sciences
- Vol. 1 (3) , 43
Open AccessTHE DEVELOPMENT OF ARTIFICIAL INTELLIGENCE IN KAZAKHSTAN AND THE USE OF BIG DATA TECHNOLOGIES TO ANALYZE THE "DIGITAL FAMILY MAP" IN ORDER TO IMPROVE THE EFFICIENCY OF PUBLIC SERVICES
Thearticle examinesthe developmentof artificialintelligence andbig datatechnologies inthe Republicof Kazakhstanwithin theframework ofthe digitaltransformation ofpublic administration. The relevanceof thestudy isdetermined bythe needto enhancethe targetingof socialpolicy andto improvethe efficiencyof publicservice deliverythrough theanalysis oflarge-scalesocio-demographicdata sets. The aimof theresearch isto assessthe potentialof applyingintelligent algorithmsand bigdata processingtools inthe analysisof theDigital FamilyMap asa componentof thestate informationinfrastructure. Thestudy employssystemic andinstitutional analysis, a comparativeapproach, andelements ofapplied dataanalytics. Thefindings identifykey directionsfor integratingintelligent technologiesinto publicdecision-makingprocesses andsubstantiate theiradvantages interms offorecasting accuracyand resourceoptimization. Thescientific noveltylies inthe comprehensiveassessment ofintegrating intelligentdata analysistechnologies intothe socialsphere, whilethe practicalsignificance isreflected inthe potentialto improvemechanisms fordelivering publicservices.
- 30 June 2025
- Published by National Engineering Academy of the Republic of Kazakhstan in Bulletin of the National Engineering Academy of the Republic of Kazakhstan
- Vol. 96 (2) , 9-21
Modeling the processes of identifying political extremism in social networks
The fight against extremism in social networks on the internet can be classified as one of the most important, mandatory and difficult tasks, but one that has a solution. The development of effective systems and models for the detection and Prevention of political extremism is the basis for ensuring security and stability in the country. Accordingly, it requires conducting scientific research in this area, thereby implementing an effective and timely set of measures aimed at identifying, preventing and suppressing any manifestations of extremism. A number of machine learning models have been studied. Measures for their implementation and careful evaluation were carried out. Machine learning models allow a comprehensive comparison of their performance in this area. Conducting this analysis contributed to the identification of the most effective methods, achieving an optimal balance between accuracy, efficiency and practicality. Machine learning models a comparative analysis of the methods of LSTM, TF-IDF and KNN showed their features and limitations in determining extremism in textual content. LSTM has shown high performance with consistent data, while TF-IDF has shown good performance in producing features, while KNN has proven effective for simple classification tasks. This assessment gave a clear idea of their suitability for various aspects of the problem and helped to choose the most optimal approach.
- 30 June 2025
- Published by National Engineering Academy of the Republic of Kazakhstan in Bulletin of the National Engineering Academy of the Republic of Kazakhstan
- Vol. 96 (2) , 9-21
Modeling the processes of identifying political extremism in social networks
The fight against extremism in social networks on the internet can be classified as one of the most important, mandatory and difficult tasks, but one that has a solution. The development of effective systems and models for the detection and Prevention of political extremism is the basis for ensuring security and stability in the country. Accordingly, it requires conducting scientific research in this area, thereby implementing an effective and timely set of measures aimed at identifying, preventing and suppressing any manifestations of extremism. A number of machine learning models have been studied. Measures for their implementation and careful evaluation were carried out. Machine learning models allow a comprehensive comparison of their performance in this area. Conducting this analysis contributed to the identification of the most effective methods, achieving an optimal balance between accuracy, efficiency and practicality. Machine learning models a comparative analysis of the methods of LSTM, TF-IDF and KNN showed their features and limitations in determining extremism in textual content. LSTM has shown high performance with consistent data, while TF-IDF has shown good performance in producing features, while KNN has proven effective for simple classification tasks. This assessment gave a clear idea of their suitability for various aspects of the problem and helped to choose the most optimal approach.