Educational Data Research Articles

ARCS 모형 적용 온라인 기반 여성건강간호학 수업이 간호대학생의 학습동기, 자기주도학습 준비도 및 학업적 자기효능감에 미치는 효과

Objectives The purpose of this study was tried to provide basic data for future nursing education by identifying the effects of nursing student's learning motivation, self-directed learning readiness, academic self-efficacy in online-based class with the ARCS model. Methods In order to achieve this study was designed quasi-experimental study with a one group pre-test and post-test design. The subjects of this study were collected using an online questionnaire for two-year nursing students located in U city, and 138 students participated in the final. Data were analyzed using descriptive statistics, paired t-test with the IBM SPSS 22.0 program. Results The results of this study showed that learning motivation (t=-6.87, p<.001), self-directed learning readiness (t=-5.42, p<.001) and academic self-efficacy (t=-6.78, p<.001) increased statistically significantly after the online-based women's health nursing class with the ARCS model. Conclusions Through the results of this study, it was confirmed that online-based women’s health nursing class with the ARCS model was effective in improving the learning motivation, self-directed learning readiness and academic self-efficacy of nursing students. Therefore, online-based class with the ARCS model can be learning strategy that can improve that learning effect of nursing student’s major theory subject.

Using R for Multivariate Meta-analysis on Educational Psychology Data: A Method Study

Using R for Multivariate Meta-analysis on Educational Psychology Data: A Method Study

Research of Integration of Innovations of Artificial Intelligence in Modern Educational Technologies

The purpose of this article is devoted to the significance of the innovative use of artificial intelligence in modern education, the authors, based on an analysis of the literature, came to the conclusion that artificial intelligence can be used not only as a teaching tool, but also through the classroom, the media and others traditional learning aids. Artificial intelligence has powerful algorithms that can help educators better understand learning focus and break down educational content from multiple angles to help students quickly integrate and update course content. The article discusses the main applications of artificial intelligence in education as analysis criteria, as well as intelligent tutoring, educational data analysis, personalized learning paths, and virtual classroom creation as an innovative integrated classroom design. After discussion and analysis, the authors believe that artificial intelligence has great potential for innovation in teaching methodology and technology, it can enrich teacher teaching methods and improve teaching technology. By integrating traditional teaching methods and advanced artificial intelligence algorithms, artificial intelligence cannot only help teachers improve the effectiveness of teaching, but also to analyze the content of classes and optimize the choice of teaching sequence.

Examining career and technical education (CTE) pathways in historically Black colleges and universities (HBCUs)

Career and technical education (CTE) is considered a key academic pathway for sustainable careers in several high-growth industries. However, African–American employees are underrepresented in these industries. Historically Black colleges and universities (HBCUs) may represent invaluable options to address this inequality. Our analysis of the Integrated Postsecondary Education Data System (IPEDS) suggests that HBCUs provide fewer CTE options than a matched sample of non-HBCUs. The most commonly available CTE programs appear in less than one-quarter of HBCUs, and nearly one-quarter of CTE industries are unrepresented. Although some programs are well-positioned to address African–American employee underrepresentation, others are completely absent. Findings connecting HBCU CTE programs to occupations with high projected growth or living wage salaries are also mixed. Overall, these results may be informative for academic policymakers, administrators, and students.

Using machine learning to predict student science achievement based on science curriculum type in TIMSS 2019

ABSTRACT Most educational systems use either an integrated or a separated science curriculum. However, it is unclear which of these science curricula benefits students more author and existing research provides insufficient information about the implementation details of the curriculum employed. Therefore, this study compares the effects of two science curricula on students’ science literacy, drawing on socio-ecological theory and employing educational data mining techniques. Results from Grade 8 Science students in 44 countries sampled in the Trends in International Mathematics and Science Study (TIMSS) 2019 showed that (1) the integrated curricula benefitted students marginally more than the separated curricula; (2) curriculum type was not essential in directly predicting students’ academic performance; and (3) random forest outperformed linear regression, lasso regression, decision trees, and neural networks in predicting student science achievement. This study advances our understanding of the predictors of student science performance, demonstrates that machine learning techniques can be applied successfully to examine curriculum effects, and provides directions for implementing integrated science curricula.

Academic library expenditures and graduation rates: evidence from four-year colleges and universities in the US

ABSTRACT In the midst of financial challenges, colleges and universities in the United States have significantly cut funding for their academic libraries in the name of enhancing efficiency. Using longitudinal data from the Integrated Postsecondary Education Data System (IPEDS) on 1,325 four-year colleges and universities, this study finds that total academic library expenditure is positively associated with student graduation rates, net of a wide range of institutional and student-related characteristics. Such findings are evident for total graduation rates as well as graduation rates for students of different racial/ethnic backgrounds. In particular, the positive association between academic library expenditures and graduation rate is most consistently evident for Black students who attend predominantly White institutions (PWIs). The findings reinforce the important role that academic libraries can play for students and shed light on the need for institutions to consider the educational consequences of reducing funding for academic libraries.

How to mitigate the risks of deployment of artificial intelligence in medicine?

The aim of this study is to examine the risks associated with the use of artificial intelligence (AI) in medicine and to offer policy suggestions to reduce these risks and optimize the benefits of AI technology. AI is a multifaceted technology. If harnessed effectively, it has the capacity to significantly impact the future of humanity in the field of health, as well as in several other areas. However, the rapid spread of this technology also raises significant ethical, legal, and social issues. This study examines the potential dangers of AI integration in medicine by reviewing current scientific work and exploring strategies to mitigate these risks. Biases in data sets for AI systems can lead to inequities in health care. Educational data that is narrowly represented based on a demographic group can lead to biased results from AI systems for those who do not belong to that group. In addition, the concepts of explainability and accountability in AI systems could create challenges for healthcare professionals in understanding and evaluating AI-generated diagnoses or treatment recommendations. This could jeopardize patient safety and lead to the selection of inappropriate treatments. Ensuring the security of personal health information will be critical as AI systems become more widespread. Therefore, improving patient privacy and security protocols for AI systems is imperative. The report offers suggestions for reducing the risks associated with the increasing use of AI systems in the medical sector. These include increasing AI literacy, implementing a participatory society-in-the-loop management strategy, and creating ongoing education and auditing systems. Integrating ethical principles and cultural values into the design of AI systems can help reduce healthcare disparities and improve patient care. Implementing these recommendations will ensure the efficient and equitable use of AI systems in medicine, improve the quality of healthcare services, and ensure patient safety.

Estimating lead-attributable mortality burden by socioeconomic status in the USA.

This study aimed to estimate population-level and state-level lead-attributable mortality burdens stratified by socioeconomic status (SES) class in the USA. Based on the National Health and Nutrition Examination Survey (NHANES), we constructed individual-level SES scores from income, employment, education and insurance data. We assessed the association between the blood lead levels (BLL) and all-cause mortality by Cox regression in the NHANES cohort (n = 31 311, 4467 deaths). With estimated hazard ratios (HR) and prevalences of medium (2-5 μg/dL) and high (≥ 5 μg/dL) BLL, we computed SES-stratified population-attributable fractions (PAFs) of all-cause mortality from lead exposure across 1999-2019. We additionally conducted a systematic review to estimate the lead-attributable mortality burden at state-level. The HR for every 2-fold increase in the BLL decreased from 1.23 (1.10-1.38) for the lowest SES class to 1.05 (0.90-1.23) for the highest SES class. Across all SES quintiles, medium BLL exhibited a greater mortality burden. Individuals with lower SES had higher lead-attributable burdens, and such disparities haver persisted over the past two decades. In 2017-19, annually 67 000 (32 000-112 000) deaths in the USA were attributable to lead exposure, with 18 000 (2000-41 000) of these deaths occurring in the lowest SES class. Substantial disparities in the state-level mortality burden attributable to lead exposure were also highlighted. These findings suggested that disparities in lead-attributable mortality burden persisted within US adults, due to heterogeneities in the effect sizes of lead exposure as well as in the BLL among different SES classes.

Multisensory Extended Reality Applications Offer Benefits for Volumetric Biomedical Image Analysis in Research and Medicine.

3D data from high-resolution volumetric imaging is a central resource for diagnosis and treatment in modern medicine. While the fast development of AI enhances imaging and analysis, commonly used visualization methods lag far behind. Recent research used extended reality (XR) for perceiving 3D images with visual depth perception and touch but used restrictive haptic devices. While unrestricted touch benefits volumetric data examination, implementing natural haptic interaction with XR is challenging. The research question is whether a multisensory XR application with intuitive haptic interaction adds value and should be pursued. In a study, 24 experts for biomedical images in research and medicine explored 3D medical shapes with 3 applications: a multisensory virtual reality (VR) prototype using haptic gloves, a simple VR prototype using controllers, and a standard PC application. Results of standardized questionnaires showed no significant differences between all application types regarding usability and no significant difference between both VR applications regarding presence. Participants agreed to statements that VR visualizations provide better depth information, using the hands instead of controllers simplifies data exploration, the multisensory VR prototype allows intuitive data exploration, and it is beneficial over traditional data examination methods. While most participants mentioned manual interaction as the best aspect, they also found it the most improvable. We conclude that a multisensory XR application with improved manual interaction adds value for volumetric biomedical data examination. We will proceed with our open-source research project ISH3DE(Intuitive Stereoptic Haptic 3D Data Exploration) to serve medical education, therapeutic decisions, surgery preparations, or research data analysis.

Educational Data Clustering in Secondary School Sensor-Based Engineering Courses Using Active Learning Approaches

The authors investigated the impact of active learning STEM and STEAM approaches on secondary school students’ general engineering knowledge, intrinsic relevance, and creativity. Three out-of-school sensor-based courses were held successively. Every sensor-based course involved the final project development. A structured questionnaire was administered to 379 students and consisted of two critical factors: creativity and intrinsic relevance. The third factor was dedicated to the students’ engineering learning outcomes. Two factors were addressed to secondary school students, while the third factor was addressed to the tutors’ observations of the students’ general sensor-based knowledge. Clustering validation analysis quantified the obtained results and justified the significant differences in all estimated factors for different educational modes. Moreover, the study showcases the value of the arts in sensor-based learning-by-doing courses when tackling complex issues like engineering topics. The authors suggest that broader research be undertaken, involving a larger sample, a greater scale, and a diversity of factors.

Learning analytics: A comparison of western, educated, industrialized, rich, and democratic (WEIRD) and non-WEIRD research

We examined how Learning Analytics literature represents participants from diverse societies by comparing the studies published with samples from WEIRD (Western, Industrialized, Rich, Democratic) nations versus non-WEIRD nations. By analyzing the Learning Analytics studies published during 2015-2019 (N = 360), we found that most of the studies were on WEIRD samples, with at least 58 percent of the total studies on WEIRD samples. Through keyword analysis, we found that the studies on WEIRD samples’ research topics focused on self-regulated learning and feedback received in learning environments. The studies on non-WEIRD samples focused on the collaborative and social nature of learning. Our investigation of the analysis tools used for the studies suggested the limitations of some software in analyzing languages in diverse countries. Our analysis of theoretical frameworks revealed that most studies on both WEIRD and non-WEIRD samples did not identify a theoretical framework. The studies on WEIRD and non-WEIRD samples convey the similarities of Learning Analytics and Educational Data Mining. We conclude by discussing the importance of integrating multifaceted elements of the participant samples, including cultural values, societal values, and geographic areas, and present recommendations on ways to promote inclusion and diversity in Learning Analytics research.

Meta-path structured graph pre-training for improving knowledge tracing in intelligent tutoring

Knowledge tracing (KT) aims to predict students’ future performance by tracking their learning behaviors in intelligent tutoring systems (ITS). In KT, three main types of entities are involved: students, exercises, and knowledge concepts. Graph structures provide an effective framework for establishing relationships between different entities. However, existing KT methods have neglected complex connections and implicit relational features, thus facing challenges in capturing high-order information in educational data. To this end, this paper proposes MPSG, a Meta-Path Structured Graph method designed to harness high-order information between entities to pre-train informative exercise embeddings for improving KT. Technically, structured by different meta-paths, four relation graphs are derived to establish implicit cross-entity relationships. On each graph, the surrounding neighbors of each node are then obtained through an intimacy-based sampling strategy. Subsequently, during the representation learning stage, node features under different meta-path views are generated and then aggregated to obtain the final exercise embeddings. The learned embeddings are optimized through three auxiliary tasks, anchored within a self-supervised learning paradigm. Extensive experiments across four public datasets demonstrate that our method can significantly enhance the predictive performance of downstream KT models.

Assessing the Racial and Ethnic Diversity of Physician Assistant/Associate Program Graduates from 2010 to 2012 and 2019 to 2021.

To assess the racial/ethnic diversity of graduates of US Physician Assistant/Associate (PA) programs compared with the diversity of the populations from which they draw students and to assess diversity changes over time among PA graduates. We calculated proportion of Black or Hispanic PA graduates nationally and by school between 2010 to 2012 and 2019 to 2021 using the Integrated Postsecondary Education Data System (IPEDS) and compared it with the diversity of the 20 to 35-year-old population using the American Community Survey. We created benchmark populations for each school based on whether the school was public or private, with in-state/out-of-state proportions provided by the Physician Assistant Education Association. A diversity index (DI) was calculated for each program. A DI of 0.5 means that the representation of Black/Hispanic graduates is half their representation in the benchmark population. Although the numbers of Black/Hispanic graduates increased from 2010 to 2012 to 2019 to 2021, the percentage of Black graduates decreased. Nationally, the DI for Black graduates decreased from 0.28 to 0.23 and the Hispanic DI increased from 0.28 to 0.37 between 2010 to 2012 and 2019 to 2021. Among 213 PA programs included in the 2019 to 2021 dataset, 5 schools had a DI >1.0 for Black graduates and 7 schools had a DI >1.0 for Hispanic graduates. Using the IPEDS data, we found that Black and Hispanic graduates are underrepresented among PA program graduates. The PA education community needs to develop new strategies for diversifying the profession consistent with the new US Supreme Court decision banning race-conscious admissions.

EDUCATIONAL DATA MINING AND LEARNING ANALYTICS: TEXT GENERATORS USAGE EFFECT ON STUDENTS’ GRADES

Today, various types of data are constantly growing, so they can be used for different purposes. In this investigation, educational data has been analyzed to determine the influence of assessment on student knowledge. The newly collected dataset has been prepared and statistically analyzed. The dataset consists of open-question answers collected on one study subject during the midterm exam at Vilnius Gediminas Technical University. The results of the statistical analysis have shown that by using the text generators, students obtained higher grades by paraphrasing the answers to the questions in good quality. Furthermore, research has shown which types of questions are more difficult for students to answer without additional material and using text generation tools. It can be useful for lecturers planning course assessment tasks.

The Googlization of the classroom: Is the UK effective in protecting children's data and rights?

There has been an explosion in uses of educational technology (EdTech) to support schools’ teaching, learning, assessment and administration. This article asks whether UK EdTech and data protection policies protect children's rights at school. It adopts a children's rights framework to explore how EdTech impacts children's rights to education, privacy and freedom from economic exploitation, taking Google Classroom as a case study. The research methods integrate legal research, interviews with UK data protection experts and education professionals working at various levels from national to local, and a socio-technical investigation of the flow of children's data through Google Classroom. The findings show that Google Classroom undermines children's privacy and data protection, potentially infringing children's other rights. However, they also show that regulation has impacted on Google's policy and practice. Specifically, we trace how various governments’ deployment of a range of legal arguments has enabled them to regulate Google's relationship with schools to improve its treatment of children's data. Although the UK government has not brought such actions, the data flow investigation shows that Google has also improved its protection of children's data in UK schools as a result of these international actions. Nonetheless, multiple problems remain, due both to Google's non-compliance with data protection regulations and schools’ practices of using Google Classroom. We conclude with a blueprint for the rights-respecting treatment of children's education data that identifies needed actions for the UK Department for Education, data protection authority, and industry, to mitigate against harmful practices and better support schools.

Staff disability data in UK higher education: Evidence from EDI reports

ObjectivesTo explore how higher education institutions (HEIs) make transparent the data they collect on staff disability, and how this relates to existing equality, diversity and inclusion (EDI) charters.DesignDescriptive cross-sector quantitative...

Study on the Connotation and Application of Multimodal Teaching Mode in Foreign Language Teaching

Amidst the rapid evolution of educational informationization, learning data, and teaching models are constantly updated and iterated. As a product of the information age, multimodal teaching is widely used in today's teaching practice. However, shortcomings still persist in multimodal teaching within foreign language education, requiring further enhancement and utilization. This study examines the impact and significance of educational informatization on multimodal teaching, aiming to propose reformative strategies. Delving into the essence and application of multimodal teaching in foreign language education opens up a wealth of possibilities for enhancing the learning experience and ensuring effective communication skills development. This research aims to summarize the practice of multimodal teaching in the field of foreign language education, shedding light on its impact on instructional innovation principles and the integration of foreign language education with information technology. Additionally, given the challenges in the application of multimodal teaching mode, this study puts forward some suggestions for reference. This research recommends bolstering the use of multimedia devices and online resources to drive reform and innovation in multimodal teaching practices, offering valuable insights for advancing education, especially in second language acquisition and information technology applications.

A Comparison of Bias Mitigation Techniques for Educational Classification Tasks Using Supervised Machine Learning

Machine learning (ML) has become integral in educational decision-making through technologies such as learning analytics and educational data mining. However, the adoption of machine learning-driven tools without scrutiny risks perpetuating biases. Despite ongoing efforts to tackle fairness issues, their application to educational datasets remains limited. To address the mentioned gap in the literature, this research evaluates the effectiveness of four bias mitigation techniques in an educational dataset aiming at predicting students’ dropout rate. The overarching research question is: “How effective are the techniques of reweighting, resampling, and Reject Option-based Classification (ROC) pivoting in mitigating the predictive bias associated with high school dropout rates in the HSLS:09 dataset?" The effectiveness of these techniques was assessed based on performance metrics including false positive rate (FPR), accuracy, and F1 score. The study focused on the biological sex of students as the protected attribute. The reweighting technique was found to be ineffective, showing results identical to the baseline condition. Both uniform and preferential resampling techniques significantly reduced predictive bias, especially in the FPR metric but at the cost of reduced accuracy and F1 scores. The ROC pivot technique marginally reduced predictive bias while maintaining the original performance of the classifier, emerging as the optimal method for the HSLS:09 dataset. This research extends the understanding of bias mitigation in educational contexts, demonstrating practical applications of various techniques and providing insights for educators and policymakers. By focusing on an educational dataset, it contributes novel insights beyond the commonly studied datasets, highlighting the importance of context-specific approaches in bias mitigation.

Data Mining Of Educational Data In Government Distance Learning

Data Mining Of Educational Data In Government Distance Learning

Investigating positive reading trajectories among children who experienced out-of-home care

BackgroundChildren who experience out-of-home care (OOHC) often have low academic achievement which subsequently negatively affects their adult life outcomes, yet a smaller proportion succeed in spite of adversity. Scant research has examined the trajectories of children who achieve well in school and factors associated with positive educational outcomes. Objectives(1) Describe the reading trajectories from Year 3 to Year 7 of school of children who experienced OOHC, with a focus on higher achievement and improving trajectories. (2) Identify child, carer and placement characteristics plus supports and services associated with positive reading trajectories among children who have experienced OOHC. Participants and settingThe study included 325 children from the Pathways of Care Longitudinal Study (POCLS) in New South Wales, Australia. MethodsThe POCLS is a prospective cohort study including linked survey data and administrative child protection and education data. Group based trajectory modeling (GBTM) was used to identify and describe common trajectories of reading achievement. Multinomial logistic regression was used to identify factors associated with different reading trajectories. ResultsGBTM revealed three reading trajectories among non-Aboriginal children, and two among Aboriginal children. A high achieving group (12% of non-Aboriginal children) were the only trajectory group to maintain their level of achievement across the study. Improving achievement was rare, while falling behind over time was common across achievement levels. ConclusionsResults point to the need for early intervention supporting school readiness and catch-up growth, with ongoing interventions for children who experience OOHC to prevent declining student outcomes across achievement levels and extend talented students.