Defense of the dissertation of Mukhiyadin Ainur for the degree of Doctor of Philosophy (PhD) in the educational program «8D06103 - Information systems»
L.N. Gumilyov Eurasian National University, a dissertation defense for the degree of Doctor of Philosophy (PhD) by Mukhiyadin Ainur on the topic «Developing the model of social institutions behavior in a pandemic based on the analysis of global data on COVID-19» in the educational program «8D06103 – Information systems».
The dissertation was carried out at the Department of «Information Systems education department» of L.N. Gumilyov Eurasian National University.
The language of defense is kazakh
Official reviewers:
Sadirmekova Zhanna Bakirbayevna – Doctor of Philosophy (PhD), Associate Professor of M.Kh. Dulati Taraz Regional University (Taraz, Republic of Kazakhstan);
Kaibasova Dinara Zhenisbekovna – Doctor of Philosophy (PhD), Associate Professor of the Department of "Computer Engineering" of Astana IT University (Astana, Republic of Kazakhstan).
Temporary members of the Dissertation Council:
Barakhnin Vladimir – Doctor of Technical Sciences, Professor, Leading Researcher at the Federal Research Center for Information and Computing Technologies (FITZ IVT) (Novosibirsk, Russian Federation);
Didar Edilkhan – Doctor of Philosophy (PhD), Head of Smart City, Associate Professor (Astana, Republic of Kazakhstan);
Erimbetova Aigerim Sembekovna – Doctor of Philosophy (PhD), Candidate of Technical Sciences, Associate Professor, Leading Researcher of the Institute of Information and Computing Technologies of the Ministry of Education and Science of the Republic of Kazakhstan (Almaty, Republic of Kazakhstan).
Scientific consultants:
Mukasheva Manargul Umirzakovna – Candidate of Pedagogical Sciences, Professor, Leading Researcher of the Center for the Development of Digitalization of Education, Y. Altynsarin National Academy of Education (Astana, Kazakhstan);
Moiseeva Lyudmila Vladimirovna – Doctor of Pedagogical Sciences, Professor, Ural State Pedagogical University (Yekaterinburg, Russian Federation).
The defense will take place on April 03, 2025, at 10:00 AM in the Dissertation Council for the training direction «8D061 – Information and communication technologies» in the educational program «8D06103 – Information systems» of L.N. Gumilyov Eurasian National University. Conducting a meeting of the dissertation council in a mixed (offline and online) format.
Link: https://surl.li/tazpox
Address: Astana, st. K.Satpayeva, 2, room. 302.
Abstract (English): dissertation for the Degree of Doctor of Philosophy (PhD) in the educational program 8D06103 – "Information systems". Mukhiyadin Ainur "Developing the model of social institutions behavior in a pandemic based on the analysis of global data on COVID-19" Relevance of the research topic. The COVID-19 pandemic has demonstrated the importance of using global data to understand and assess the impact of crises on various aspects of public life, including education, healthcare, and social behavior. Kazakhstan, like many other countries, lacks tools and methodologies for processing and analyzing big data. Despite the significant amount of data collected during the pandemic, existing tools and methods in Kazakhstan are often insufficient for the full analysis and use of this data. This limits the ability to deeply understand these processes and develop effective strategies to respond to current challenges. Social surveys and other types of global data play a crucial role in collecting information about the state of social institutions and their response to the pandemic. They provide unique opportunities to analyze and assess the impact of the pandemic on different populations. However, in order to fully utilize this data, it is necessary to use modern methods of processing and analyzing big data. In addition, the pandemic has revealed the need to develop new approaches and strategies for managing educational processes in conditions of global crises. Distance learning has become an integral part of the educational process, and its quality is directly related to the effective use of data for monitoring and analysis. The use of machine learning and big data analysis methods will significantly improve the quality of distance learning and increase the adaptability of education systems to future challenges. It is also worth noting that the integration of modern technologies and methods of data analysis into social research will contribute not only to achieving more accurate and reliable results, but also to the development of the scientific base and an increase in the level of confidence in research results. This is especially true in times of crisis, when accurate and timely information can play a crucial role in making strategic decisions and developing measures to mitigate the pandemic. The purpose and scientific results of the dissertation research. The purpose of the research is to develop and implement a hybrid Machine Learning model for assessing the quality of distance learning based on social survey data and other sources. This model is aimed at optimizing the analysis of big data and improving the management of educational processes in crisis situations, which will allow to increase the quality and accessibility of education. This goal served as the basis for identifying and formulating the following main tasks, which will serve as the basis for the successful implementation of the study and achieving the set scientific results: ˗ Study the impact of epidemiological and natural factors on the life values and behavior of students, as well as analyze the territorial distribution of data on the behavior of schools and students during distance learning; ˗ Assess the effectiveness of data collection and processing methods used in studying the behavior of social institutions and develop a model for conducting statistical analysis of data in order to study the behavior of these institutions; ˗ Create and implement a hybrid machine learning model to assess the quality of distance learning, as well as automate the process of providing survey results related to the quality of education. Scientific novelty: The scientific novelty of the results obtained during the study is as follows: 1. A comprehensive analysis of the impact of the Covid-19 pandemic on the life values and behavior of students, as well as an assessment of the territorial distribution of data by schools, was carried out. 2. A model for analyzing survey data aimed at studying the behavior of social institutions has been developed. The process includes the analysis of surveys, the formation and collection of data, their subsequent processing and visualization of the results, which facilitates understanding of changes in educational organizations. 3. A hybrid model for assessing the quality of distance learning, combining statistical analysis methods (PCA), text processing methods (TF-IDF, Word2Vec), which allows for a deep analysis of the impact of the pandemic on educational processes and the adaptation of teaching methods, has been developed. The object of research of the dissertation work is information systems and data processing algorithms used to analyze the quality of distance learning and the behavior of social institutions in the context of a global crisis. The subject of research of the dissertation work is the methodology for using machine learning methods and models to analyze big data related to assessing the quality of distance learning and monitoring the behavior of social institutions. Research methodology and methods. Research methods. The basis of the methodology is the use of modern machine learning algorithms and big data analysis methods to predict student performance and assess the effectiveness of educational systems. The following methods are used in the study: 1. Incorporating various classification and regression methods, such as random forests, fuzzy logic, k-means clustering, naive Bayesian approach, decision trees, support vector machines, artificial neural networks, and the k-nearest neighbors algorithm. These methods allow for in-depth analysis of data and making accurate predictions about the risk of academic failure of students based on various characteristics and learning outcomes. 2. Using ensemble methods that combine predictions from several machine learning algorithms to improve the accuracy and reliability of predictions. This approach helps to overcome the limitations of individual algorithms and achieve generalized and reliable results. 3. Using large-scale data processing and analysis methods, including synchronous and asynchronous learning logs. This allows us to take into account a wide range of data collected from various sources and samples, which is important for a comprehensive assessment of the progress and effectiveness of education systems. 4. Use statistical methods to assess the significance and reliability of data, as well as to test hypotheses and evaluate the effectiveness of the proposed models and algorithms. 5. Use data visualization tools to visually display the results and predictions of the analysis, which contributes to a better understanding and interpretation of the data. This methodology allows us to conduct comprehensive studies of student behavior and the effectiveness of educational processes, as well as to make recommendations for improving education systems based on objective and quantitative data. The theoretical significance of the research is the development and justification of new approaches to analyzing and forecasting educational processes in the context of the COVID-19 pandemic. The work uses an integrated approach that includes statistical analysis methods (PCA), text processing methods (TF-IDF, Word2Vec) and machine learning algorithms. These methods provide high accuracy and reliability of the results, which contribute to a deep understanding of the data and the identification of key factors affecting educational processes. The practical significance of the research is confirmed by the development and implementation of an automated information system for collecting and analyzing data on the quality of distance learning. This system automates the process of providing survey results and increases the efficiency of educational process management. The results obtained have been successfully implemented in educational practice, which confirms their applicability and value for improving the quality of education in times of crisis. Implementation of results. The results of the work were implemented at the L.N. Gumilyov Eurasian National University (Astana) and the I. Altynsarin National Academy of Education (Astana). Approbation of the results of the dissertation. The main results of the dissertation and the results of the research were presented and discussed at the following international, republican scientific and practical conferences: 2 articles in international publications with a non-zero impact factor included in the Scopus database: 1. Mukhiyadin A., Makhazhanova, U., Serikbayeva, S., Kassekeyeva, A., Muratova, G., Karauylbayev, S., ... & Kenzhebay, A., Application of information technologies and methods for processing big data to the management of the educational process during the pandemic //Journal of Theoretical and Applied Information Technology. – 2023. – Т. 101. – №. 2. – С. 458-470. (Quartile - Q3, percentile - 30) 2. Mukasheva, M., Mukhiyadin, A., Makhazhanova, U., & Serikbayeva, S., The Behaviour of the Ensemble Learning Model in Analysing Educational Data on COVID-19 //International Journal of Information and Education Technology. – 2023. – Т. 13. – №. 12. (Quartile - Q3, percentile - 33) In the publications recommended by the Ministry of Science and Higher Education of the Republic of Kazakhstan – 4 articles: 1. Мұхиядин, А., Мукашева, М., Махажанова, У., Муханова, А., & Ламашева, Ж., Программалық құралдар көмегімен экстремалды қашықтықтан оқытудың оқушыларға әсерін зерттеу //Известия НАН РК. Серия физико-математическая. – 2023. – №. 4. – с. 209-223. 2. Мухиядин А., Махажанова, У., Мукашева, М., & Муханова, А., Информационные технологии как средство анализа экспериментальных данных при экстренном дистанционном обучении //Известия НАН РК. Серия физико-математическая. – 2023. – №. 1. – С. 170-190. 3. Мұхиядин, А. Ұ., Махажанова, У. Т., Алимагамбетова, А. З., Муханова, А. А., & Акмолдина, А. И., Машиналық оқыту әдістерін пайдалана отырып, оқушылардың білім алуға ынтасын болжау: Қазақстандағы білім беру деректерін талдау // Известия НАН РК. Серия физико-математическая. – 2024. – №. 4. – С. 204–217. 4. Мұхиядин А.Ұ., Махажанова У.Т., Баегизова А.С., Доумчариева Ж.Е., Муханова А.А., ПРИМЕНЕНИЕ АНСАМБЛЕВЫХ МЕТОДОВ МАШИННОГО ОБУЧЕНИЯ ДЛЯ АНАЛИЗА ОБРАЗОВАТЕЛЬНЫХ ДАННЫХ В УСЛОВИЯХ ПАНДЕМИИ COVID-19 //Вестник КазАТК. – 2024. – Т. 135. – №. 6. – С. 192-202. 6 articles in the materials of international conferences of far abroad and the Republic of Kazakhstan: 1. Мұхиядин А. Ұ., Мукашева М. У., Байбурин А. М. ВЛИЯНИЕ COVID-19 НА ДЕЯТЕЛЬНОСТЬ СОЦИАЛЬНЫХ ИНСТИТУТОВ: ОБРАЗОВАНИЕ В ШКОЛЕ //Образование 2030. Дорожная карта. – 2021. – С. 262-268. 2. Мухиядин А. Ұ., Ерсултанова А. С. Влияние дистанционного обучения на учителей средних школ в период пандемии COVID-19 в Республике Казахстан //КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИ: СОЦИАЛЬНО-ЭКОНОМИЧЕСКИЕ И ИНФОРМАЦИОННЫЕ АСПЕКТЫ. – 2022. – С. 199-203. 3. Ерсултанова А. С., Мұхиядин А. Ұ. ПАНДЕМИЯ КЕЗЕҢІНДЕ ИНФОРМАТИКАНЫ ОҚЫТУДАҒЫ ИНКЛЮЗИВТІ БІЛІМ БЕРУ МӘСЕЛЕЛЕРІ //The XIII International Science Conference «Perspectives of development of science and practice», December 14–17, 2021, Prague, Czech Republic. 626 p. – 2021. – С. 348. 4. Мухиядин А. У., Ерсултанова А. С. Проблемы инклюзивного образования Республики Казахстан в период пандемии Covid-19 //Современные проблемы образования в области физической культуры, безопасности жизнедеятельности и биологии. – 2022. – С. 217-222. 5. Мұхиядин А.Ұ., Мукашева М.У. COVID-19 бойынша ашық ақпарат көздері туралы //Инновациялық зерттеулердің тиімділігін арттырудың модельдері мен әдістері: халықаралық ғылыми конф. материалдары. – Қарағанды: «Bilim Innovations Group» орталығы, 2020. – 229 б. – Б. 127. 6. Мұхиядин А.Ұ., Ерсултанова А.С. Covid-19 пандемиясы кезінде мұғалімдердің қашықтықтан оқытуға көзқарасы: акт қолдану арқылы сауалнама нәтижелерін талдау //«Сейтқасымов оқулары – 2022»: Халықаралық ғылыми-тәжірибелік конференция материалдары. – Нұр-Сұлтан: «Esil University» БПО, 2022. – Б. 315-319. The scope and structure of the dissertation. The dissertation research work consists of an introduction, a main chapter consisting of 3 sections, a list of 163 references, a conclusion and 1 appendix. The main volume of the work consists of 115 pages, including 41 figures and 14 tables. The introduction substantiates the relevance of the topic and indicates the main directions of the work. Currently, it is important to assess the quality of the distance learning system and its impact on the educational process. The COVID-19 pandemic that has swept the world has contributed to the widespread use of distance learning and has determined the relevance of studying the effectiveness of this learning system. The results obtained in the process of assessing the quality of distance learning play an important role in improving the education system and introducing new methodologies. The main directions of the research are the analysis of changes in student behavior due to distance learning, the study of the actions of social institutions, as well as the use of machine learning methods to evaluate these processes. These directions provide a comprehensive description of the research topic and reveal its relevance. The first section is devoted to the analysis of the impact of external factors on students' life values and behavior. This section considers the impact of epidemiological situations and natural disasters on students' values. In particular, issues such as a decrease in students' interest in education, increased psychological pressure, as well as changes in the level of participation in the educational process during the pandemic were considered. The study took into account the regional characteristics of the respondents and analyzed their experiences in the educational process comparatively. The territorial analysis examined the levels of adaptation of urban and rural schoolchildren to distance learning. While urban schools have high access to the Internet, psychological problems are common, while in rural areas one of the main difficulties was the lack of resources. These analyses were carried out by monitoring the behavior of secondary school students during distance learning. The second section considers the issues of data analysis and the study of the behavior of social institutions. Here, the statistical analysis methods used to process data obtained through surveys are described. The statistical significance of the criteria aimed at studying the actions of social institutions was assessed. For this, the factor analysis method was used, which determined the interrelationships of various factors and the level of influence of the data. The study developed a model describing the behavior of social institutions. This model allowed us to assess the interaction of epidemiological and social factors. In addition, the principal components method (PCA) was used to increase the efficiency of data grouping and classification. As a result of these methods, the quality of data analysis improved and the reliability of the results obtained increased. The third section is devoted to the development and implementation of a hybrid machine learning model for assessing the quality of distance learning. This section considers the processing of big data, the creation of a hybrid machine learning model, and the automated presentation of survey results using the example of survey results. By combining the TF-IDF, Word2Vec, and PCA methods, the efficiency of data classification increased. In addition, the distance learning quality assessment system was automated. This system accelerated the processing of survey results and allowed for real-time analysis of the data obtained. Thus, the process of assessing the quality of distance learning was optimized and the scope of the system expanded. The results of the study were based on the results obtained in all sections. Recommendations were made to improve the effectiveness of the distance learning system in the context of the pandemic. New methods and models were introduced in the study of the behavior of social institutions. In addition, the scientific and practical value of the results obtained was noted. At the end of the work, the literature and additional materials used in the study are presented. These materials demonstrate the complexity of the study and confirm its practical significance. The author expresses special gratitude to the scientific advisor, Professor Mukasheva Manargul Umirzakovna, Senior Research Fellow of the National Academy of Education named after Y. Altynsarin, for setting interesting tasks and providing useful advice on their solution. In addition, the author expresses gratitude to the foreign scientific advisor, Doctor of Pedagogical Sciences of the Russian Pedagogical University, Professor Moiseeva Lyudmila Vladimirovna, for her sincere and selfless help, comprehensive support, professionalism, interest in work, and invaluable comments. In addition, the teachers of the Department of "Information Systems" Makhazhanova N.T., Abdikerimova G.B., Muhanova A.A. and I would like to thank the members of the scientific seminar of the Eurasian National University for discussing the results. The author also expresses his gratitude to the Y. Altynsarin National Academy of Education for its assistance in conducting scientific research.
'/%3e%3cpath%20fill-rule='evenodd'%20clip-rule='evenodd'%20d='M17.5427%2012.684C17.1383%2011.7889%2016.7126%2011.771%2016.3278%2011.7553C16.0132%2011.7419%2015.6529%2011.7427%2015.2932%2011.7427C14.9333%2011.7427%2014.3483%2011.8774%2013.8537%2012.4152C13.3587%2012.9531%2011.9639%2014.2533%2011.9639%2016.8978C11.9639%2019.5426%2013.8987%2022.098%2014.1684%2022.4569C14.4383%2022.8153%2017.9033%2028.4156%2023.3907%2030.5701C27.9513%2032.3606%2028.8793%2032.0045%2029.8692%2031.9149C30.8591%2031.8253%2033.0633%2030.6149%2033.5133%2029.3597C33.9632%2028.1048%2033.9632%2027.0291%2033.8282%2026.8043C33.6932%2026.5803%2033.3333%2026.4459%2032.7933%2026.1771C32.2534%2025.9083%2029.5992%2024.6078%2029.1043%2024.4286C28.6093%2024.2494%2028.2494%2024.1598%2027.8894%2024.6979C27.5295%2025.2355%2026.4954%2026.4459%2026.1804%2026.8043C25.8655%2027.1635%2025.5505%2027.2083%2025.0105%2026.9395C24.4706%2026.6699%2022.7318%2026.1029%2020.6691%2024.2717C19.0641%2022.8472%2017.9806%2021.0877%2017.6656%2020.5496C17.3506%2020.012%2017.6318%2019.7209%2017.9027%2019.4529C18.1451%2019.2121%2018.4426%2018.8254%2018.7126%2018.5116C18.982%2018.1977%2019.072%2017.9737%2019.252%2017.6153C19.4319%2017.2564%2019.342%2016.9425%2019.207%2016.6737C19.072%2016.405%2018.0228%2013.7468%2017.5427%2012.684Z'%20fill='white'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_181_11959'%20x1='22.8525'%20y1='42.8177'%20x2='22.8525'%20y2='0.921701'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%2320B038'/%3e%3cstop%20offset='1'%20stop-color='%2360D66A'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
