Search Results (87)

Student dropout prediction remains critical in higher education, where timely identification enables effective interventions. Learning Management Systems (LMSs) capture rich temporal data reflecting student behavioral evolution, yet existing approaches underutilize this sequential information. Traditional machine learning methods aggregate behavioral data into static features, discarding dynamic patterns that distinguish successful from at-risk students. While Long Short-Term Memory (LSTM) networks model sequences, they assume discrete time steps and struggle with irregular LMS observation intervals. To address these limitations, we introduce Completion-aware Risk Neural Ordinary Differential Equations (CR-NODE), integrating continuous-time dynamics with completion-focused features for early dropout prediction. CR-NODE employs Neural ODEs to model student behavioral evolution through continuous differential equations, naturally accommodating irregular observation patterns. Additionally, we engineer three completion-focused features: completion rate, early warning score, and engagement variability, derived from root cause analysis. Evaluated on Canvas LMS data from 100,878 enrollments across 89,734 temporal sequences, CR-NODE achieves Macro F1 of 0.8747, significantly outperforming LSTM (0.8123), Extreme Gradient Boosting (XGBoost) (0.8300), and basic Neural ODE (0.8682). McNemar’s test confirms statistical significance ($p<0.0001$). Cross-dataset validation on the Open University Learning Analytics Dataset (OULAD) demonstrates generalizability, achieving 84.44% accuracy versus state-of-the-art LSTM (83.41%). To support transparent decision-making, SHapley Additive exPlanations (SHAP) analysis reveals completion patterns as the primary prediction drivers. Full article

Based on the 2030 Agenda for Sustainable Development, which emphasizes inclusion and equality of education for all, the number of university students with special educational needs (SEN) is increasing worldwide. Universities are increasingly faced with the demand for inclusive education. This study aimed to investigate the attitudes of university teachers towards educational inclusion and the implementation of accommodations for students with SEN according to their gender, academic discipline and professional training. Through standardized questionnaires, we surveyed 117 university teachers at five faculties. We ascertained that university teachers have positive attitudes towards the inclusion of students with SEN and the implementation of accommodations in their study programs. The statistically significant more sympathetic attitudes towards educational inclusion and provision of academic accommodations were found among female teachers. University teachers in natural sciences study programs had significantly more negative attitudes towards the ability of students with SEN succeeding academically than teachers in social sciences programs. Those who did not receive professional training were statistically significantly more likely to agree with the contention that students with SEN hinder educational work in the classroom and could not succeed academically. The study revealed the importance of sustainable professional training for university teachers in teaching students with SEN. Full article

Problem-based learning (PBL) has been recognized for enhancing student motivation and key competencies. However, its integration with emerging topics such as ESG (Environmental, Social, and Governance) in general education remains underexplored. This study implemented a PBL-based instructional design in a general education course titled “Organizational Greenhouse Gas Inventory and Net-Zero Transition,” integrating practical tasks and ESG case studies to enhance students’ sustainability literacy and core competencies. Pre- and post-course assessments were conducted using the University Career and Competency Assessment Network (UCAN) questionnaire, analyzed through paired sample t tests and Wilcoxon signed rank tests. Results showed significant improvements in the innovation and communication aspects, with upward trends observed in other domains. Students also demonstrated strong engagement and learning motivation through tasks such as carbon footprint estimation, data integration, and field-based assessments. The findings support the feasibility of embedding ESG and PBL frameworks in general education. Future course iterations will consider differentiated instructional design and the incorporation of qualitative methods to accommodate diverse student backgrounds and enhance learning outcomes, contributing to the advancement of sustainability education in higher education. Full article

Analyses of student mobility are typically conducted in an urban environment and are informed by socio-demographic or trip attributes. The prevailing focus is on individual modes of transport, different groups of commuters travelling to campus, students’ behavioural perceptions, and the totality of student trips. This paper starts with the identification of the determinants of student mobility that have received insufficient research attention. Utilising surveys, the study captures the mobility patterns of a sample of 1014 students and calculates their carbon footprint (CF; in kg/academic year) to assess whether the factors neglected in previous studies influence differences in the actual environmental load of student commuting. A regression analysis is employed to ascertain the significance of these factors as predictors of sustainable student mobility. This study exclusively focuses on the group of student commuters to campus and analyses the trips associated with compulsory activities at a suburban campus that is distant from the university centre and student facilities, which changes the mobility context in terms of commuting options. The under-researched factors identified in this research have not yet been quantified as CF. The findings confirm that only some of the factors neglected in previous research are statistically significant predictors of the local environmental load of student mobility. Specifically, variables such as student employment, frequency of class attendance, and propensity for ride-sharing could be utilised to forecast and regulate students’ mobility towards more sustainable patterns. However, all of the under-researched factors (including household size, region of origin (i.e., past experiences), residing at term-time accommodation while studying, and the availability of a family car) have an influence on the differences in CF magnitude in the studied campus. Full article

Rental accommodations near European university campuses keep rising in price, while listings remain scattered and opaque. This paper proposes a solution that overcomes these issues by integrating real-time open listing ingestion, zone-level geospatial enrichment, and a reinforcement-learning recommender into one streamlined analysis pipeline. On demand, the system updates price statistics for most districts in Timișoara and returns five budget-safe offers in a short amount of time. By combining adaptive ranking with new spatial metrics, it significantly cuts search time and removes irrelevant offers in pilot trials. Moreover, this implementation is fully open-data, open-source, and free, designed specifically for students to ensure accessibility, transparency, and cost efficiency. Full article

In almost all institutional discourses about universities, students are mentioned. Universities are defined as dynamic areas that pave the way for students to acquire and develop scientifically based professional skills. Students are also given importance in explanations about creating a sustainable university. However, their contributions have been neglected in the development of this idea. Based on this inspiration, this study aims to examine the kind of expansions the university reality constructed by university students with their cognitive patterns can provide to the idea of creating a sustainable university. To achieve this aim, firstly, the university reality constructed by students enrolled in an associate degree program at a university, with their cognitive patterns, is explained through metaphors. Accordingly, open-ended questions were asked to 200 university students who were in the process of experiencing university life and volunteered to participate in the study. The answers received were evaluated through descriptive analysis and content analysis. As a result of the research, it was seen that 119 metaphors were produced, and these metaphors could be divided into seven categories with the titles of university as a structure that expresses, develops, and enlightens university reality; university as a structure that reaches goals; university as a social life area that accommodates differences and offers diversity; university as a structure that limits; university as a structure that challenges; university as a structure that liberates; and university as a structure that provides security and peace. Then, it was discussed how university students’ explanations about university reality would benefit the establishment of a sustainable university. While this study provides insights into university students’ perspectives on the university, it also contributes to strengthening and expanding the existing idea of a sustainable university. Full article

Background: Attention-deficit/hyperactivity disorder (ADHD) is a chronic neurodevelopmental disorder that continues into adulthood and is linked to significant academic, occupational, and psychological challenges. Medical students may be at heightened risk due to the cognitive and emotional demands of their training. However, regional data on adult ADHD symptoms in this population, particularly in northern Saudi Arabia, remain limited. Objective: to estimate the prevalence of probable adult ADHD symptoms among medical students at the University of Tabuk and to examine the associated sociodemographic, academic, and health-related factors. Methods: A cross-sectional, web-based survey was conducted between 15 May and 5 June 2025 among randomly selected Saudi medical students (years 2–6) at the University of Tabuk. The validated Arabic version of the WHO Adult ADHD Self-Report Scale (ASRS-v1.1) was used to screen for probable ADHD. A positive screen was defined as ≥4 flagged items. Descriptive and bivariate analyses were performed using SPSS v29. Results: Of the 219 respondents (60.3% male; mean age: 21.6 years), 23.3% screened positive for probable adult ADHD. Symptom frequency peaked in the third (40.0%) and fourth (35.6%) academic years and was lowest among sixth-year students (11.4%) (p = 0.012). A strong association was observed between positive ADHD screening and self-reported psychiatric disorders (p < 0.001). No statistically significant associations were found for gender, income, GPA, marital status, or academic phase. Conclusions: Nearly one in four medical students at the University of Tabuk exhibited symptoms suggestive of adult ADHD, a prevalence markedly higher than global estimates and consistent with regional trends. The association with psychiatric morbidity and the mid-programme peak suggests a need for proactive screening, mental health support, and academic accommodations. Universities can translate these findings into practice by instituting routine ADHD screening, offering flexible assessment accommodations, embedding peer-mentoring programmes, and strengthening on-campus mental-health referral pathways. Full article

This paper examines the impacts of AI-powered assistive technologies (AIATs) on the academic success of higher education university students with visual impairments. As digital learning contexts become progressively more prevalent in higher education institutions, it is critical to understand how these technologies foster the academic success of university students with blindness or low vision. Based on the Unified Theory of Acceptance and Use of Technology (UTAUT) model, the study conducted a quantitative research approach and collected data from 390 visually impaired students who were enrolled in different universities across Saudi Arabia (SA). Employing Partial Least Squares Structural Equation Modeling (PLS-SEM), the paper tested the influences of four UTAUT dimensions—Performance Expectancy (PE), Effort Expectancy (EE), Social Influence (SI), and Facilitating Conditions (FC)—on Academic Performance (AP), while also evaluating the mediating role of Behavioral Intention (BI). The results revealed a significant positive relationship between the implementation of AI-based assistive tools and students’ academic success. Particularly, BI emerged as a key mediator in these intersections. The results indicated that PE (β = 0.137, R² = 0.745), SI (β = 0.070, R² = 0.745), and BI (β = 0.792, R² = 0.745) significantly affected AP. In contrast, EE (β = −0.041, R² = 0.745) and FC (β = −0.004, R² = 0.745) did not have a significant effect on AP. Concerning predictors of BI, PE (β = 0.412, R² = 0.317), SI (β = 0.462, R² = 0.317), and EE (β = 0.139, R² = 0.317) were all positively associated with BI. However, FC had a significant negative association with BI (β = −0.194, R² = 0.317). Additionally, the analysis revealed that EE, SI, and PE can all indirectly enhance Academic Performance by influencing BI. The findings provide practical insights for higher education policymakers, higher education administrators, and AI designers, emphasizing the need to improve the accessibility and usability of sustainable and long-term assistive technologies to better accommodate learners with visual impairments in higher education contexts. 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

Background: Rural communities in the United States experience significant barriers in accessing healthcare, including inadequate numbers of providers and local healthcare facilities. These barriers are exacerbated during seasons with high rates of respiratory diseases when rural clinics and providers may be overwhelmed. When mild, many of these respiratory diseases may be managed effectively in alternate settings, including community pharmacies. Investigators interviewed pharmacists in Washington State to explore the capacity of pharmacists and pharmacies to provide test-to-treat services for COVID-19, influenza, and strep throat. Methods: A qualitative study design was used to conduct key informant interviews with pharmacists who precepted student pharmacists from a local university. Twenty interviews were conducted, transcribed, and qualitatively evaluated to identify themes. The 5 A’s of Access were utilized as a theoretical framework. This framework describes five domains of access, including affordability, availability, accessibility, accommodation, and acceptability. Results: Qualitative analysis identified several themes that described the benefits of offering test-to-treat services in rural communities, such as reducing geographical barriers to accessing care, reducing wait times for patients, and reducing the number of patients seeking higher levels of care for basic treatments. Barriers to offering test-to-treat services identified by pharmacist participants included difficulties with receiving payment for services, challenges with adequate staffing, and the lack of awareness among many people in rural communities that pharmacies offer test-to-treat services. Conclusions: Rural communities experience challenges with the limited capacity of healthcare providers to meet the needs of patients in their communities. The results of this qualitative analysis may be useful to pharmacists in U.S. states where collaborative drug therapy agreements or collaborative practice agreements allow the provision of test-to-treat services. By providing test-to-treat services, pharmacists can increase access to care for rural patients and alleviate the burden of offering these services from other healthcare providers. Full article

The aim of the paper is to identify energy inefficiencies and to propose energy-saving solutions to reduce the carbon footprint of the structures, considering Building Information Modelling—Existing Conditions Model as an enabling tool. The initiative underscores the role of Building Information Modelling—Existing Conditions Model in facilitating data-driven strategies for improving energy efficiency, highlighting its potential to transform the infrastructure and built environment into a paradigm of responsible energy consumption. In this context, the paper presents a comprehensive assessment of the thermal performance of student accommodations using advanced technologies, such as Unmanned Aerial Systems and Terrestrial Laser Scanners equipped with thermal cameras. The findings illustrate potential areas for improvements in thermal efficiency, offering a roadmap for targeted interventions to enhance the energy performance of buildings. The results of the study not only advance the green campus at Politehnica University Timisoara (Romania), but also serve as an educational model that demonstrates the integration of technology to promote sustainability in the built environment. Full article

In China, educators are encouraged by administrators to assume instructional and language strategies to align with their students’ needs so as to enhance classroom communicative effectiveness, with students’ perceptions of teachers’ behavior being a salient factor in this process. This study, based on communication accommodation theory, examines how students’ perceptions of teachers’ behaviors influence reports of positive classroom outcomes. Using structural equation modeling, we analyzed responses from a sample of 422 university students in Shanghai. The results showed that the students’ perceptions of teachers’ communication accommodation behaviors, such as verbal and nonverbal tactics, teaching content, and emotional support behaviors, significantly and positively impacted students’ learning effectiveness, teacher credibility, and communication satisfaction. Furthermore, teacher credibility partially mediated the relationship between perceptions of accommodation and learner effectiveness. The findings offer practical insights for educators by suggesting that strategic adaptions of communication accommodations behaviors can promote students’ learning outcomes. Full article

This paper describes large, fine-grained, intentionally inclusive, research-based cognitive models called learning maps. Learning maps are the product of an intensive research synthesis process to develop formal learning models that better reflect the diversity of how learners can learn and be assessed on academic content. Students begin at different places and learn at different rates, and they may have cognitive disabilities or may face a variety of barriers that pose challenges when learning content. Learning maps provide numerous starting points and pathways by which students can acquire and demonstrate knowledge, skills, and understandings. Our work in developing learning maps relies on principles of Universal Design for Learning (UDL), which provides a foundation of flexibility and inclusivity to accommodate students with a wide range of cognitive, linguistic, physical, and sensory profiles. In this paper, we describe learning map design, development, and both qualitative and quantitative methods for the evaluation of map structure. In addition, we offer reflections on our experiences with implementing learning maps as the cognitive architecture for assessments and educational interventions through our work on a variety of projects. With examples from these projects, we describe evidence that shows how learning maps can be useful tools for improving instruction and assessment for all learners. We identify areas where further research and inquiry could prove fruitful and conclude with a discussion of potential areas of extension and offer suggestions for the ongoing refinement of learning maps. Full article

Attention deficit hyperactivity disorder (ADHD) is a neurological disorder generally experienced as challenging, as it impacts multiple aspects of an individual’s life. There is a significant gap in the literature surrounding ADHD in adults, including experiences of stigma and social inclusion from the perspective of people with ADHD. This study aimed to explore perceptions and experiences of social inclusion and stigma amongst a sample of university students with ADHD living in Ireland. Nine semi-structured interviews were conducted with seven participants (four men and three women), including two follow-up interviews. The participants were all university students with an official diagnosis of ADHD. Data from the interviews were analysed using the descriptive and interpretive method of Constant Comparison Analysis. In total, sixteen categories (themes) were extracted and classified into five overarching domains: informational access, access to healthcare, attitudinal access, social inclusion, and academic accommodations. The findings indicated that ADHD adversely affects university students’ experience of social inclusion. Barriers to effective healthcare, negative attitudes towards ADHD, and misinformation/lack of information were all highlighted as risk factors for feelings of social exclusion. Universities should include students with disabilities when designing policies and provide accommodations to support them. Additionally, greater awareness and informational access is imperative to improving social inclusion for people with ADHD. Full article

This study aimed to improve cloud network management skills through the Microsoft Azure AI Platform and to raise awareness of green technology among postgraduate STEM students at the Faculty of Education, Minia University. An e-learning environment was developed using the Chamilo system, which included interactive tools, educational resources, and assessment methods. The study employed Kuhlmann’s instructional design model and the general ADDIE model, following detailed procedures that aligned with the study’s objectives. Both experimental and quasi-experimental designs were used with a sample of 60 students. The measurement tools included a cognitive achievement test for cloud network management skills with AI platforms, an observation checklist for using the Azure AI platform, and a scale for green technology awareness. The results indicated enhancements in cloud network management skills using the Azure AI platform and an increase in green technology awareness among the participants. The study recommended designing learning environments that accommodate various learning styles and integrating AI platforms with green technology to support sustainable development goals. Full article