Search Results (119)

Academic performance in adolescence is influenced by both cognitive capacity and physiological factors such as sleepiness. However, the interaction between these dimensions remains understudied. This pilot study examined whether daytime sleepiness moderates the relationship between working memory and academic achievement in a sample of 601 schoolchildren aged 11 to 17 years. Participants completed a digital visuospatial working memory task and self-reported their daytime sleepiness using the Pediatric Daytime Sleepiness Scale (PDSS). Academic performance was assessed through official grades in Mathematics, Language, and Literature. Regression analyses showed that working memory (total score and average reaction time) and daytime sleepiness were independent predictors of academic performance. These findings support our hypotheses that cognitive and physiological factors each contribute to school success. However, no significant moderation effects were found in the full sample. Subgroup analyses revealed that working memory predicted academic outcomes only among students with normal sleepiness levels, whereas in high-sleepiness students, cognitive predictors lost significance and PDSS scores emerged as the dominant predictor. These results suggest that elevated daytime sleepiness can undermine the positive impact of working memory on academic performance. The findings highlight the importance of assessing both cognitive skills and physiological readiness when evaluating students. They also suggest that sleep-focused interventions may improve learning outcomes, especially during adolescence. Full article

This article discusses the development of a course maturity model, aimed at improving and aligning academic courses with labor market demands. The model, named Ten Tools for Improving Course (TTIC), is a continuous, cyclic, multi-component structure designed to assess and enhance course quality and effectiveness. Maturity models for the university environment are typically based on very specific, isolated domains, ignoring other key areas of university organizations. Moreover, existing university maturity models generally do not provide directions for activities and practices that enable assessment of the achieved level with the aim of fostering continuous improvement. The present study addresses these limitations by focusing on the “Algorithmization and Programming of Solutions” course at Riga Technical University, utilizing statistical data to predict student performance and reduce dropout rates. By using TTIC, the authors aim to enhance educational quality and develop professional competencies. The model evaluates various factors influencing student success, including content alignment, teaching methods, feedback, and adaptability. The paper highlights the use of statistical analysis to predict student performance and offers strategies for course enhancement. Full article

In the rapid digital era, artificial intelligence (AI) tools have progressively arisen to shape the education environment. In this context, large language models (LLMs) (i.e., ChatGPT vs. 4.0 and Gemini vs. 2.5) have emerged as powerful applications for academic inclusion. This paper investigated how using and trusting LLMs can impact the academic success and quality of life (QoL) of visually impaired university students. Quantitative research was conducted, obtaining data from 385 visually impaired university students through a structured survey design. Partial Least Squares Structural Equation Modelling (PLS-SEM) was implemented to test the study hypotheses. The findings revealed that trust in LLMs can significantly predict LLM usage, which in turn can improve QoL. While LLM usage failed to directly support the academic success of disabled students, but its impact was mediated through QoL, suggesting that enhancements in well-being can contribute to higher academic success. The results highlighted the importance of promoting trust in AI applications, along with developing an accessible, inclusive, and student-centred digital environment. The study offers practical contributions for educators and policymakers, shedding light on the importance of LLM applications for both the QoL and academic success of visually impaired university students. Full article

This study investigates the effectiveness of integrating explicit learning-strategy instruction into gatekeeper mathematics courses to foster a math growth mindset, self-regulated learning (SRL), and improved academic performance among underrepresented minority students. The intervention was implemented across four key courses—College Algebra I/II and Calculus I/II—and incorporated evidence-based cognitive, metacognitive, and behavioral learning strategies through course materials, class discussions, and reflective assignments. Grounded in a conceptual framework linking learning-strategy instruction, growth mindset, SRL, and performance—while accounting for students’ social identities—the study explores both direct and indirect effects of the intervention. Using an explanatory sequential mixed-methods design, we first collected quantitative data via pre- and post-surveys/tests and analyzed performance outcomes, followed by qualitative focus groups to contextualize the findings. Results showed no significant effects of the intervention on growth mindset or SRL, nor evidence of mediation through these constructs. The direct effect of the intervention on performance was negative, though baseline mindset, SRL, and pre-course preparedness strongly predicted outcomes. No moderation effects were detected by student identities. The findings suggest that while explicit learning-strategy instruction may not independently shift mindset or SRL in the short term, pre-existing differences in these areas are consequential for performance. Qualitative findings provided further context for understanding how students engaged with the strategies and how instructor implementation shaped outcomes. These insights inform how learning strategies might be more effectively embedded in introductory math to support success and equity in STEM pathways, particularly in post-COVID educational contexts. Full article

Digital transformation (DT) has become one of the most significant trends in higher education institutions (HEIs) in both EU and non-EU countries. Using Information and Communication Technologies (ICTs) to reinvent higher education is contingent upon several factors, including an institution’s development stage regarding the application and strategic integration of ICTs across its key activities and processes. In the extant literature, multiple frameworks of ICT development (maturity) paths have been developed. However, there is a lack of empirical studies on how well those models predict the DT success, and which of their dimensions are most relevant. In this paper, we use a research instrument, adapted from the HigherDecision research project, to capture the subjective assessments of academics and students at three public higher education institutions in Bosnia and Herzegovina and Croatia. Using seven dimensions of the DT construct, prescribed by the HigherDecision framework, we examine their contribution to the subjectively evaluated success of each HEI’s DT initiative and identify the most impactful dimension(s). Our results show that the digital infrastructure and academic teaching and learning are perceived as critical drivers of DT in the academic sector. Provided that the University of Mostar, as a mid-sized public university located in Bosnia and Herzegovina, currently represents one of the DT leaders in the Western Balkans (WB) region, we discuss implications for scaling its good practices in smaller HEIs across the region. Full article

In most Western societies, intelligence testing has evolved beyond simple measures of language and numerical abilities. Although these measures are valuable in predicting academic achievement and career success, it is widely recognized that modern intelligence assessments offer a more comprehensive view of intellectual aptitude. Unfortunately, in Caribbean Small Island Developing States, like Barbados, despite ongoing efforts towards educational reform and an increasing body of research and related theories advocating for inclusive approaches to understanding and nurturing students’ intellectual development, the education system remains heavily influenced by traditional conceptualizations of intelligence that present a somewhat narrow view of students’ aptitudes. This perspective appears to consider students’ performance on high-stakes examinations measuring numerical and language abilities as perhaps the most indicative markers of intelligence. Building on the work of renowned educational theorists such as Sternberg, Renzulli, and Gardner, and drawing from literature on traditional and contemporary measures of intelligence, this opinion paper examines the implications of deconstructing and redefining traditional views of intelligence within the Barbadian educational context. The value of conventional measures and the potential challenges and limitations associated with transitioning to contemporary intelligence assessments are acknowledged, and the pedagogical and assessment implications at primary and secondary school levels are discussed. Full article

This study investigates the feasibility of using wearable technology and machine learning algorithms to predict academic performance based on physiological signals. It also examines the correlation between stress levels, reflected in the collected physiological data, and academic outcomes. To this aim, six key physiological signals, including skin conductance, heart rate, skin temperature, electrodermal activity, blood volume pulse, inter-beat interval, and accelerometer were recorded during three examination sessions using a wearable device. A novel pipeline, comprising data preprocessing and feature engineering, is proposed to prepare the collected data for training machine learning algorithms. We evaluated five machine learning models, including Random Forest, Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), Categorical Boosted (CatBoost), and Gradient-Boosting Machine (GBM), to predict the exam outcomes. The Synthetic Minority Oversampling Technique (SMOTE), followed by hyperparameter tuning and dimensionality reduction, are implemented to optimise model performance and address issues like class imbalance and overfitting. The results obtained by our study demonstrate that physiological signals can effectively predict stress and its impact on academic performance, offering potential for real-time monitoring systems that support student well-being and academic success. Full article

Student success is a multifaceted outcome influenced by academic, behavioral, contextual, and socio-environmental factors. With the growing availability of educational data, machine learning (ML) offers promising tools to model complex, nonlinear relationships that go beyond traditional statistical methods. However, the lack of interpretability in many ML models remains a major obstacle for practical adoption in educational contexts. In this study, we apply explainable artificial intelligence (XAI) techniques—specifically SHAP (SHapley Additive exPlanations)—to analyze a synthetic dataset simulating diverse student profiles. Using LightGBM, we identify variables such as hours studied, attendance, and parental involvement as influential in predicting exam performance. While the results are not generalizable due to the artificial nature of the data, this study reframes its purpose as a methodological exploration rather than a claim of real-world actionable insights. Our findings demonstrate how interpretable ML can be used to build transparent analytic pipelines in education, setting the stage for future research using empirical datasets and real student data. Full article

The use of learning success prediction models is increasingly becoming a part of practice in educational institutions. While recent studies have primarily focused on the development of predictive models, the issue of their temporal stability remains underrepresented in the literature. This issue is critical as model drift can significantly reduce the effectiveness of Learning Analytics applications in real-world educational contexts. This study aims to identify effective approaches for assessing the degradation of predictive models in Learning Analytics and to explore retraining strategies to address model drift. We assess model drift in deployed academic success prediction models using statistical analysis, machine learning, and Explainable Artificial Intelligence. The findings indicate that students’ Digital Profile data are relatively stable, and models trained on these data exhibit minimal model drift, which can be effectively mitigated through regular retraining on more recent data. In contrast, Digital Footprint data from the LMS show moderate levels of data drift, and the models trained on them significantly degrade over time. The most effective strategy for mitigating model degradation involved training a more conservative model and excluding features that exhibited SHAP loss drift. However, this approach did not yield substantial improvements in model performance. Full article

Unanticipated interplay among digital access, institutional prestige, and support systems shapes academic outcomes in higher education. Survey responses from 387 undergraduates in Taiwan and Vietnam—two markets that experienced 80–130 percent growth in mobile broadband penetration between 2015 and 2023—reveal that greater university resource intensity is associated with higher course grades, whereas Reputation Capital and National Context factors unexpectedly correlate with lower performance. Moreover, while individual motivation robustly predicts achievement, a strong future orientation (long-term mindset) is linked to modest declines in grades, perhaps reflecting difficulties in balancing forward-looking goals with the demands of fast-paced, digitally mediated coursework. These counter-intuitive findings underscore the intricate dynamics of student success in technology-saturated learning environments and suggest that effective use of institutional resources and digital platforms requires targeted interventions—such as training in digital self-regulation and curricular designs that mitigate the downsides of prestige and pervasive connectivity—to optimize academic performance. Full article

This study examines how emotional intelligence and frustration intolerance influence academic performance in university students, drawing on the Job Demands–Resources model—which frames academic success as a balance between psychological demands (such as frustration intolerance) and personal resources (like emotional intelligence)—and Self-Determination Theory, which explains how motivation and self-regulation contribute to adaptation and persistence in challenging contexts. A sample of 630 undergraduates across various disciplines completed validated measures of emotional intelligence, frustration intolerance, academic burnout, academic engagement, and grade point average. Structural equation modeling analyzed relationships among these variables. The results showed that emotional intelligence positively predicted academic performance both directly and indirectly by increasing engagement and reducing burnout. Conversely, frustration intolerance negatively affected academic performance through increased burnout and decreased engagement. The model explained 24 percent of the variance in academic performance. These findings indicate that academic achievement depends on managing the balance between psychological demands and personal resources. Frustration intolerance acts as a psychological demand increasing vulnerability to exhaustion and disengagement, while emotional intelligence serves as a personal resource supporting self-regulation, motivation, and persistence. This highlights the importance of fostering emotional skills and frustration tolerance in higher education to help students cope better with academic challenges and improve performance. Full article

The role of emotional intelligence (EI) in the academic context has been steadily established, together with its impact on students’ academic achievement, well-being, and professional success. Therefore, this study examined the development of a key EI ability—emotional understanding—throughout secondary school and explored its impact on students’ academic achievement (maternal language and mathematics) at the end of this cycle, using the Vocabulary of Emotions Test. A total of 222 students were followed over the entire 3-year secondary cycle, using a three-wave longitudinal design spanning from 10th to 12th grade. At the first wave, participants were aged between 14 and 18 years (M = 15.4; SD = 0.63), with 58.6% being female. Overall, the results of Latent Growth Curve modeling indicated that students’ emotional understanding increased over the secondary school cycle. While student’s gender predicted the emotional understanding change patterns throughout secondary school, student’s GPA in 10th grade did not. Moreover, the initial levels of ability-based emotional understanding predicted students’ achievement in maternal language at the end of the cycle. Our findings offer valuable insights into how EI skills can contribute to academic endeavors in late adolescence and will explore their impact on educational settings. Full article

Artificial intelligence (AI) has found applications across diverse sectors in recent years, significantly enhancing operational efficiencies and user experiences. Educational data mining (EDM) has emerged as a pivotal AI application to transform educational environments by optimizing learning processes and identifying at-risk students. This study leverages EDM within a Moroccan university (Hassan First, University Settat, Morocco) context to augment educational quality and improve learning. We introduce a novel “Hybrid approach” that synthesizes students’ historical academic records and their in-class behavioral data, provided by instructors, to predict student performance in initial coding courses. Utilizing a range of machine learning (ML) algorithms, our research applies multi-classification, data augmentation, and binary classification techniques to evaluate student outcomes effectively. The key performance metrics, accuracy, precision, recall, and F1-score, are calculated to assess the efficacy of classification. Our results highlight the long short-term memory (LSTM) algorithm’s robustness achieving the highest accuracy of 94% and an F1-score of 0.87 along with a support vector machine (SVM), indicating high efficacy in predicting student success at the onset of learning coding. Furthermore, the study proposes a comprehensive framework that can be integrated into learning management systems (LMSs) to accommodate generational shifts in student populations, evolving university pedagogies, and varied teaching methodologies. This framework aims to support educational institutions in adapting to changing educational dynamics while ensuring high-quality, tailored learning experiences for students. Full article

Understanding how students’ online homework behaviors relate to their academic success is increasingly important, especially in elementary education where such research is still emerging. In this study, we examined three years of online homework data from fourth-grade students enrolled in an after-school math program. Our goal was to see whether certain behaviors—like how soon students started their homework, how many times they tried to solve problems, or whether they uploaded their written work—could help explain differences in homework completion and test performance. We used multiple regression analyses and found that some habits, such as beginning homework soon after class and regularly attending lessons, were consistently linked to better homework scores across all curriculum levels. Test performance, however, was harder to predict and showed fewer consistent patterns. These findings suggest that teaching and encouraging specific online study behaviors may help support younger students’ academic growth in digital learning environments. Full article

While static conscientiousness is known to predict academic success, personality can be particularly dynamic during adolescence. This study adopted a unique change-oriented perspective to examine the longitudinal relationship between within-person changes in conscientiousness and changes in academic performance among Chinese high school students, while also exploring the moderating role of changes in parental academic expectations. Four waves of longitudinal data were collected from 453 students (265 males, Mage = 15.42, SD = 0.76), with each wave spaced 6 months apart. Results indicated that the changes in conscientiousness (T2-T1) predicted the changes in academic performance (T4-T3) through the changes in academic engagement (T3-T2). However, the moderating effect of changes in parental academic expectations on the relationship between changes in conscientiousness and academic engagement was not significant. These findings go beyond static trait approaches by illustrating how dynamic changes in personality relate to evolving academic outcomes via engagement during the crucial high school years. The study highlights the importance of a dynamic perspective on personality, particularly within the developmental context of adolescence, and offers implications for interventions targeting both student traits and parental support in the Chinese educational context. Full article