Educational Data Research Articles

A Systematic Review of Postgraduate Programmes Concerning Ethical Imperatives of Data Privacy in Sustainable Educational Data Analytics

This systematic review, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, investigated the intersection of data privacy, postgraduate educational data analytics (EDA), and sustainability. Existing literature focuses on general privacy concerns in EDA, neglecting the specific data collected and related risks in postgraduate programmes. This review addresses this gap by identifying data types used by higher education institutions in postgraduate initiatives and evaluating the adequacy of current ethical frameworks, particularly for sustainability goals. Recognising the lack of established best practices for balancing data utility and privacy, the review analyses privacy-preserving techniques. Through identifying key data types collected in postgraduate initiatives, evaluating existing ethical frameworks, and exploring privacy-preserving educational data analytics techniques, this study provided practical guidance for higher education institutions to navigate the challenges of balancing data utility and student privacy. The results suggest that higher education institutions can achieve sustainable data use by adopting a comprehensive approach that incorporates best practices, emerging technologies, and continuous monitoring to safeguard student privacy while leveraging the benefits of educational data analytics for achieving the Sustainable Development Goals.

Penerapan Algoritma Naïve Bayes Untuk Analisis Pengaruh Faktor Pendidikan Terhadap Peningkatan Kesehatan Masyarakat

Health and Education are the main capital in realizing the nation's progress. Because quality and productive human resources are those who have a good level of health. People who have low education usually cannot receive current information about health, they prefer traditional health care such as going to a shaman or healer rather than going to the doctor. The aim of this research is to determine the influence of educational factors on public health. Data obtained through surveys and data collection carried out in the Sustainable Development Goals (SDGs) program or what we can interpret as sustainable development goals. 4429 data were obtained which included: economic data, health data, poverty data, gender data, education data and environmental data. The data obtained is used by researchers as attributes or variables to support decision making. This research uses a classification method with the Naïve Bayes algorithm with the accuracy value as the final value of the research. Data processing uses Rapid Miner software. From the test results it turns out to have an accuracy rate of 65.19%. Testing was carried out using k-fold validation, starting from k-fold validation 2 to 10. And the highest accuracy value was found at k-fold 6

Transforming Education with Blockchain Technology: Enhancing Security, Transparency, and Credential Verification

Blockchain technology has emerged as a powerful tool for enhancing transparency, security, efficiency, and inclusivity in record-keeping, credentialing, and educational transactions in the digital age. This paper aims to highlight the potential benefits and challenges of integrating blockchain technology into educational environments, emphasizing security, transparency, and credential verification as key areas of focus. Blockchain technology offers transformative potential in the field of education, particularly in credential and certification processes, providing secure, transparent, and globally accessible solutions for verifying academic achievements and professional skills. As blockchain technology continues to evolve, further advancements and case studies specific to enhancing privacy in educational processes are expected to emerge, addressing the unique challenges and regulatory requirements associated with handling sensitive educational data. Further R&D in blockchain technology within the education sector holds promise for addressing existing challenges, unlocking new opportunities, and advancing the capabilities of educational institutions worldwide.

The Impact of Implementing Blockchain Technology in Learning on Data Security and Integrity

The application of blockchain technology in learning has great potential to improve data security and integrity. Because blockchain is a decentralized technology that uses block chains to record and secure transactions in a transparent and permanent manner, it offers an excellent solution to address security and data integrity issues. This research was conducted with the aim of improving the security and integrity of student data. Student data can be stored in a distributed manner with blockchain. No one can change or delete it without their permission. This goal also includes increasing transparency and accountability of the learning process to ensure that the data used in the learning process is accurate data. The method used in this research is a quantitative method. This method is a way of collecting numerical data that can be tested. Data was collected through distributing questionnaires addressed to students. Furthermore, the data that has been collected from the results of distributing the questionnaire will be accessible in Excel format which can then be processed using SPSS. From this research carried out, researchers can obtain research results that blockchain technology is used to protect educational data by locking the learning history of the learning management system (LMS), so that assessments can be carried out effectively and allow all parties involved to access and verify information safely while ensuring data integrity and validity. Based on the results of this research, it can be concluded that the application of blockchain technology can help improve the security and integrity of student data, such as academic, financial and personal data, in the learning context. By using blockchain, students have complete control over their data and ensure that bad people cannot misuse or access it. Apart from that, blockchain technology can also increase transparency and accountability in the classroom.

The effect of academic outcomes, equity, and student demographics on parental preferences for schools: evidence from a survey experiment

Abstract How does competition for school resources, along with racial and socioeconomic biases, shape parental preferences for schools? In this article, I investigate how school attributes affect preferences and choice, which sheds light on the processes that maintain school segregation. To do so, I conduct a survey experiment that explores parental preferences and the tradeoffs inherent in the process of school selection using school profiles that resemble those available on widely used education data platforms. I find that parents hold the strongest positive preferences for learning opportunities and overall school achievement compared to other attributes, including school racial and socioeconomic composition. Additionally, though parents prefer schools that have higher equity rankings, highly equitable schools are less desirable to parents than schools with more status and learning opportunities. However, parents also hold independent racial and socioeconomic preferences and —on average—avoid schools with more students of color and low-income students. Furthermore, results suggest they are largely unwilling to make tradeoffs that would result in schools with higher fractions of students of color or low-income students. Taken together, this study links prior studies on the segregating effects of educational data with literatures on school segregation by illustrating the specific dimensions that drive school choice.

Proposals for Incorporating the Reversal in Single-Case ABAB Designs Data Analysis

One of the commonly used single-case experimental designs (SCEDs) in education research is the ABAB design, commonly referred to as reversal design. This design is applicable when the studied behavior is reversible (i.e., reverses to baseline levels when the intervention is withdrawn) and it allows for a within-unit replication of the “basic effect”, that is, a comparison between two adjacent conditions (with and without an active intervention). Methodologically, one of its strengths is to provide three phase change moments to demonstrate experimental control. However, the withdrawal of the intervention (i.e., the comparison between the first intervention phase and the second baseline phase) has not received sufficient attention in the SCED literature. The aim of the current text is to propose quantifications that enable using the information from the withdrawal. Specifically, the quantifications allow for assessing the degree to which withdrawing the intervention leads to initial baseline levels as well as incorporating the reversal in an overall effect size. The proposals are illustrated with several real educational science data sets, including both within-unit analysis and replication of the ABAB design across units, and representing different degrees of reversal of the target behavior when the intervention is withdrawn.

Oceania in the Desert: A QuantCrit Analysis of the (Under)Counting of Native Hawaiian and Pacific Islander Students at an AANAPISI-HSI

Most education research uses the National Center for Education Statistics (NCES) Integrated Postsecondary Education Data System (IPEDS), often leaving the logic undergirding the IPEDS racial classification system (i.e., categorization and counting) unquestioned. Framed by Quantitative Critical Race Theory (QuantCrit) principles, this research demonstrates how the NCES IPEDS racial classification misrepresents and undercounts students. Specifically, we show how IPEDS guidance around racial classification misrepresents the number of Asian American, Native Hawaiian, and Pacific Islander (AA&NHPI) undergraduates, with particular attention to NHPI students, at a single institution. We show the ways in which IPEDS logic leads to undercounting, namely that, based on the NCES IPEDS racial classification system, most undergraduates identifying as NHPI are classified as Two or More Races and Hispanic or Latino. A similar pattern of suppression is found to varying degrees for students identifying as American Indian or Alaska Native, Asian, and Black or African American. Our findings complicate the taken-for-granted nature of IPEDS racial classification and have implications for serving racially minoritized student groups and for institutions that may qualify as enrollment-based Minority-Serving Institutions.

Construction and Innovative Exploration of Personalized Learning Systems in the Context of Educational Data Mining

This study examines the current research on educational data mining, educational learning support services, personalized learning services, and personalized learning paths in education. The authors aim to integrate personalized learning concepts into traditional support services by drawing on the latest theoretical and practical research. Using multimodal data fusion techniques, the study conduct exploratory analyses on various data types, including learner academic performance, psychological assessments, learning behavior, and physiological information. This leads to the construction of a personalized education learning support service model. The model focuses on objectives such as monitoring learning behavior, identifying preferences, recognizing abilities, optimizing paths, and recommending resources. The goal is to provide learners with sustained support services throughout the personalized learning process, addressing individual needs, fostering enthusiasm, and maintaining long-term motivation.

The Impact of Statistics and Probability on Educational Artificial Intelligence

Artificial intelligence has transformed e-learning by enabling personalized and efficient teaching. This manuscript analyzes the importance of statistics and probability in educational AI. Statistical methodologies improve decision-making, personalize learning, and optimize educational outcomes. Challenges such as data privacy and ethics are addressed. Case studies demonstrate the practical applications of AI in diverse educational contexts. Future directions suggest a need for robust research to further understand and implement AI-driven educational strategies. The findings underscore the critical role of data-driven approaches in shaping the future of education. Statistics and probability are not only foundational to the development of AI but also essential for analyzing vast amounts of educational data. They allow for the creation of predictive models that can identify student needs and adapt instructional methods accordingly. This adaptability enhances the learning experience by providing targeted support and resources to students, thereby improving their academic performance. Ethical considerations are fundamental when using AI to handle educational data. Protecting student data with privacy and security is crucial to maintaining trust in AI applications. This manuscript examines how educators and policymakers can collaborate to create guidelines that safeguard student information while utilizing data to enhance education. Integrating statistics and probability into educational AI significantly impacts and improves e-learning. Educators can enhance learning by employing data-driven strategies that provide personalized and effective teaching. This approach not only benefits individual learners but also contributes to the overall advancement of educational practices. Embracing these data-driven methodologies is essential for the continued evolution of teaching and learning in the digital age.

A Framework for Cleaning Streaming Data in Healthcare: A Context and User-Supported Approach

Nowadays, ubiquitous technology makes life easier, especially devices that use the internet (IoT). IoT devices have been used to generate data in various domains, including healthcare, industry, and education. However, there are often problems with this generated data such as missing values, duplication, and data errors, which can significantly affect data analysis results and lead to inaccurate decision making. Enhancing the quality of real-time data streams has become a challenging task as it is crucial for better decisions. In this paper, we propose a framework to improve the quality of a real-time data stream by considering different aspects, including context-awareness. The proposed framework tackles several issues in the data stream, including duplicated data, missing values, and outliers to improve data quality. The proposed framework also provides recommendations on appropriate data cleaning techniques to the user to help improve data quality in real time. Also, the data quality assessment is included in the proposed framework to provide insight to the user about the data stream quality for better decisions. We present a prototype to examine the concept of the proposed framework. We use a dataset that is collected in healthcare and process these data using a case study. The effectiveness of the proposed framework is verified by the ability to detect and repair stream data quality issues in selected context and to provide a recommended context and data cleaning techniques to the expert for better decision making in providing healthcare advice to the patient. We evaluate our proposed framework by comparing the proposed framework against previous works.

Public Policies, Sustainable Purchases and Family Farming in Brazil – 2013 a 2023

Objectives: to characterize and analyze the public policies and sustainable purchases that contribute to reducing environmental impacts and promote the development of family farming. In order to address the general objective of the research, the following specific objectives were carried out: 1) Contextualize family farming in Brazil; 2) Present and analyze the following public policies focused on family farming: Low Carbon Agriculture - ABC Plan, National Program for Strengthening Family Farming - PRONAF, Food Acquisition Program - PAA and National School Feeding Program - PNAE and 3) discuss the process of sustainable bidding and family farming. Methodology and data sources: the methodology used to achieve the study's objectives was tabular and graphical analysis of secondary data. The data sources were collected from the Ministry of Agrarian Development and Family Farming (MDA), the Central Bank of Brazil (BCB) through the Rural Credit Matrix, the National Supply Company (CONAB), the National Fund for Educational Development (FNDE) and data from the National Secretariat for Rural Social and Productive Inclusion (SEISP) through the Secretariat for Evaluation, Information Management and Single Registry (SAGICAD) platform. In addition, exploratory research was carried out using a bibliographic survey to support the results found. The period of analysis was from 2013 to 2023. Results: It is important to consider that the public policies mentioned above contribute to aligning economic, social and environmental aspects. Based on the evidence obtained, the programs proved to be effective in their aim of supporting family farming. Therefore, in order to continue their actions, it is recommended that the main characteristics of their design be maintained, which have been fundamental to achieving their results and, above all, that resources for their actions be expanded and guaranteed.

РОЗВИТОК КРИТИЧНОГО МИСЛЕННЯ МАЙБУТНІХ ВЧИТЕЛІВ ІНФОРМАТИКИ ТА МАТЕМАТИКИ З ВИКОРИСТАННЯМ ЗАСОБІВ ШТУЧНОГО ІНТЕЛЕКТУ

The article examines the problems of developing critical thinking of future teachers of computer science and mathematics using artificial intelligence tools. The experience of domestic and foreign researchers regarding the use of artificial intelligence in education for the development of critical thinking, in particular, the United States of America, the Republic of Poland, and the Republic of Slovenia, was analyzed. The necessary components of critical thinking are defined: the use of logical thinking to analyze problems, make decisions and solve problems; obtaining, interpreting and using knowledge/facts/data in the process of solving problems; demonstration (manifestations) of creativity and non-standard thinking. In order to investigate the specifics of the application of critical thinking skills by future teachers of computer science and mathematics when working with artificial intelligence systems, a survey was conducted. The "Klochko Questionnaire: Peculiarities of using critical thinking skills by future teachers of computer science and mathematics when working with artificial intelligence systems" was created. The possibilities of using artificial intelligence tools in education have been clarified, in particular: analysis of educational data, creation of educational content, professional development, adaptive learning, and others.The results of the study showed that 92.2% of respondents use or plan to use artificial intelligence tools in the educational process. The vast majority of students studying to become computer science and mathematics teachers actively use artificial intelligence to solve various problems, applying critical thinking and developing their critical thinking skills. The development of critical thinking skills of future computer science and mathematics teachers is a necessary condition for their academic success, personal and professional development, competitiveness, preparation for future challenges, solving new problems, teaching students to think critically. The implementation of artificial intelligence tools for the development of critical thinking in future teachers may have certain risks, such as excessive trust in artificial intelligence and the reduction of the role of one's own experience, intuition, etc. It is important to note that the field of using artificial intelligence technologies in education is just beginning to develop and needs additional research, however, it has great potential for the development of critical thinking of future teachers.

Factors associated with care partner identification and education among hospitalized persons living with dementia

ObjectiveCare partners of persons living with dementia (PLWD) often feel unprepared to care for their loved ones. Improving PLWD care partner identification and education during hospital stays can improve preparedness. This retrospective EHR study investigated PLWD characteristics that may relate to care partner identification, education, and teaching methods during hospital stays. MethodsEncounters from a Midwestern academic healthcare system were used. Patients were over 18, had a documented dementia diagnosis, were admitted to the hospital for at least 24 h, and had information documented in care partner or education data fields (N = 7982). Logistic regressions assessed patient's demographics, care partner identification and education. Chi-square tests compared education teaching methods and patient discharge location. ResultsPLWD's who were unmarried, discharged to other care facilities, or received the diagnosis “degeneration of nervous system due to alcohol” were associated with lacking care partner identification. Care partners of unmarried PLWDs or those with the diagnosis “Alzheimer's disease, unspecified” received less education. Multiple teaching methods were associated with discharge location. ConclusionMultiple characteristics were related to PLWD care partner identification and education differences during hospital stays. InnovationNovel analyses highlight need for a protocol to systematically prepare dementia care partners.

A Mendelian randomization study: Years of education and nonalcoholic fatty liver disease.

Though years of education have been connected to nonalcoholic fatty liver disease (NAFLD), the exact mechanism underlying this linkage is still unknown. To investigate the causal association between years of education and NAFLD, we will use a 2-sample Mendelian randomization (MR) technique. : Genome-wide association studies data on years of education (n = 766,345) and genome-wide association studies data on nonaffiliated mental illness (n = 778,614) were screened for genetic variations as instrumental variables in the Mr-Base database. MR-Egger regression, weighted median, and inverse variance weighted were used in the MR analysis. Years of education (odds ratio = 0.63; 95% confidence interval: 0.47-0.79; P = 1.28 × 10-8) might be protective against the development of NAFLD. Among the sensitivity analyses were the following: the MR-Egger intercept test revealed P > .05, suggesting that there was no horizontal pleiotropy in the MR analysis and that the inverse variance weighted results were trustworthy; the Cochran Q test revealed P > .05, suggesting that there was no heterogeneity between the 2 samples; Funnel plot results demonstrated that there was no bias in the link between the measure of variability and the impact size. Leave-1-out analysis results demonstrated that no 1 single nucleotide polymorphism had a significant effect on the study's results, showing that the MR results were stable. This study has investigated the connection between years of education and NAFLD, offering novel suggestions for NAFLD treatment and prevention.

Educational Debt and Income Among Pharmacists and Other Health Professionals

ObjectiveGiven the substantial increases in student educational loan debt in recent years, the objective was to assess trends in educational debt-to-income ratios for graduates of pharmacy, medicine, dentistry, optometry, and veterinary medicine programs in the United States in the 2017–2022 period. MethodsA retrospective analysis of 2017–2022 data for educational debt and income for select health professions was conducted. Annual income data were collected from the American Community Survey, and educational debt data were collected from health professions organizations. Educational debt-to-income ratios for each health profession were calculated, as was the mean change per year in debt-to-income ratio. ResultsWith the exception of medicine, educational debt consistently exceeded income across the selected health professions in the 2017–2022 period. Debt-to-income ratios of pharmacists and the remaining health professionals decreased on average per year between 2017 and 2022. Physicians had the lowest debt-to-income ratios and dentists had the highest debt-to-income ratios in the study period. ConclusionDebt-to-income ratios fell below the 2017 levels for the health professions of interest, suggesting that average growth in income outpaced that of debt for the study period. Regardless, debt remains high and may influence health care professionals’ postgraduate training and career decisions, and in turn affect access to health care. Therefore, a call to action is proposed to address educational debt burden. Several strategies are suggested, including federal policy changes, implementing tuition reductions or minimal increases, facilitating financial aid options, and reducing underlying costs of health professions programs.

This Is Going on Your Permanent Record: A Legal Analysis of Educational Data in the Cloud

This Is Going on Your Permanent Record: A Legal Analysis of Educational Data in the Cloud

ПРИМЕНЕНИЕ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА ДЛЯ ИЗМЕРЕНИЯ УСПЕВАЕМОСТИ УЧАЩИХСЯ

This article explores the application of artificial intelligence (AI) for measuring student performance. It examines the potential of AI for automated assessment, educational data analysis, personalized feedback, and integration into educational platforms. Special attention is given to advanced AI systems, such as Claude by Anthropic, and their potential in personalizing learning, providing feedback, and processing big data. The ethical considerations and challenges of implementing AI in education are discussed, emphasizing the importance of a responsible and student-centered approach. The paper also delves into future directions for research and development in AI for education, including the advancement of adaptive learning, support for 21st-century skills, and integration with other cutting-edge technologies. Additionally, it addresses the implications of AI on educational equity and accessibility. The conclusion highlights AI's potential to transform the educational landscape and the importance of a balanced approach to its implementation, ensuring that it benefits all learners while addressing potential risks and ethical concerns.

Uncovering insights from big data: change point detection of classroom engagement

Expectations of big data across various fields, including education, are increasing. However, uncovering valuable insights from big data is like locating a needle in a haystack, and it is difficult for teachers to use educational big data on their own. This study aimed to understand changes in student participation rates during classes and teachers’ teaching styles by analyzing educational big data. In the analysis, data from 120 students and two mathematics class teachers at a public junior high school in Japan were used. We applied the pruned exact linear time (PELT) algorithm to automatically identify significant changes in student participation during class. Based on the information obtained, we analyzed the interaction logs of teachers’ e-book readers and clarified the relationship between student participation rates and teacher behavior patterns. Change point detection using the PELT algorithm showed a high F1-score of 0.7929, indicating good overall performance. We also investigated whether there was a relationship between class differences and teachers’ actions and found a statistically significant difference. The results provide clues for improving student learning engagement and teachers’ teaching styles, and they are expected to improve the quality of education by automatically identifying notable cases from educational big data. However, further research is required to improve data analysis methods, such as adjusting the parameters of algorithms based on the situation.

A Comparison of Demographic Diversity Between Orthopaedic Surgery Residents and ACGME Foot and Ankle Fellows From 2007 to 2022.

Academic medicine emphasizes the need to recruit a diverse workforce in graduate medical education. Orthopaedic surgery residency has demonstrated efforts to model program compositions with evolving US demographics. However, it remains unclear whether orthopaedic fellowships, particularly foot and ankle, also reflect these efforts. Using the publicly available Accreditation Council for Graduate Medical Education (ACGME) Data Resource Book, a census of the gender and racial/ethnic identities of orthopaedic foot and ankle fellows, as well as active orthopaedic surgery residents, were compiled from 2007 to 2022. Linear trend analysis was conducted to evaluate the trends of orthopaedic residents and foot and ankle fellows, with a Pearson correlation for comparison. Prior analysis demonstrated no significant change in sex and ethnic diversity of fellows from 2006 to 2015. The majority of foot and ankle fellows were White (31%-69%) and male (63%-88%). Linear analysis demonstrated growing diversity in female and non-White active orthopaedic surgery residents. Similarly, there was an increasing number of female foot and ankle fellows (0%-38%) reflective of the trend in orthopaedic residency (12%-20%); however, there was no significant change among racial/ethnic identities. Pearson correlation analysis between the trend of orthopaedic residency residents and foot and ankle fellows suggests moderate correlation among female, Asian, and "Unknown" racial/ethnic categories. The proportion of foot and ankle female fellows in ACGME-accredited fellowships has matched or exceeded the percentage of female orthopaedic residents. Despite increased diversity of orthopaedic surgery residents over the past 2 decades, ACGME-accredited foot and ankle fellowships do not yet reflect similar trends among racial/ethnic minorities. Level III, retrospective cohort study.

Machine learning based education data mining through student session streams

Recently, significant growth in using online-based learning stream (i.e., elearning systems) have been seen due to pandemic such as COVID-19. Forecasting student performance has become a major task as an institution is focusing on improving the quality of education and students' performance. Data mining (DM) employing machine learning (ML) techniques have been employed in the e-learning platform for analyzing student session streams and predicting academic performance with good effects. A recent, study shows ML-based methodologies exhibit when data is imbalanced. In addressing ensemble learning by combining multiple ML algorithms for choosing the best model according to data. However, the existing ensemblebased model does not incorporate feature importance into the student performance prediction model. Thus, exhibits poor performance, especially for multi-label classification. In addressing this, this paper presents an improved ensemble learning mechanism by modifying the XGBoost algorithm, namely modified XGBoost (MXGB). The MXGB incorporates an effective cross-validation scheme that learns correlation among features more efficiently. The experiment outcome shows the proposed MXGBabased student performance prediction model achieves much better prediction accuracy contrary to the state-of-art ensemble-based student performance prediction model.