Frontiers in Education: Digital Learning Innovations

This study examines the prediction accuracy of ensemble machine learning models by comparing local and global precision, recall, and accuracy for multiclass grading of engineering students. It also investigates the performance of various machine learning models in predicting the multiclass grading outcomes for these students. The primary goal is to address challenges in multiclass data preparation and evaluate the best machine learning models using both micro and macro accuracy metrics derived from baseline comparisons. The results highlight a significant comparative analysis of prediction accuracy across different algorithms, emphasizing the importance of employing multiple receiver operating characteristic curves, areas under the curves, and a one-vs-rest classification approach when target features are represented as letter grades. The algorithms examined include decision trees, K-nearest neighbors, random forests, support vector machines, XGBoost, gradient boosting, and bagging. Gradient boosting achieves the highest global accuracy for macro predictions at 67%. It is followed by random forests at 64%, bagging at 65%, K-nearest neighbors at 60%, XGBoost at 60%, decision trees at 55%, and support vector machines at 59%. When considering micro prediction accuracy at the individual student level, support vector machines, random forests, and XGBoost closely align with true student grades, with accuracies of 19, 22, and 33%, respectively, at baseline. Notably, these models accurately predict the C grade with 97% precision, whereas predicting the A grade proves more challenging, with an accuracy of only 66%. These findings are further corroborated by precision-recall error plots. The grid search for random forest algorithms achieved a score of 79% when optimally tuned; however, the training accuracy was 99%. The results have implications for both students and educational institutions, helping identify areas for improvement and recognizing high achievers, which ultimately contributes to enhanced academic outcomes for engineering students.

Artificial intelligence (AI) has become a key factor in higher education, revolutionizing both teaching methods and student learning. This study aimed to identify the perceptions of university students and professors on the use of AI in academic education. A descriptive study with a quantitative approach was conducted using the deductive method and a Likert scale questionnaire. The results revealed a predominantly low perception of AI in university teaching, with 71.5% of students and 73.1% of professors expressing skepticism about its application. Additionally, 59% of students and 65.9% of professors evaluated the impact of AI on the learning process unfavorably, indicating concerns about its effectiveness in enhancing education. Ethical and privacy considerations showed a contrast, with 84% of students displaying high confidence while 73.2% of professors maintaining moderate trust. These findings highlight a perception gap and a lack of confidence in assessing the impact of AI, emphasizing the urgent need for training programs, comprehensive policies, and evaluation methodologies. Addressing these concerns is crucial for harnessing AI’s potential in higher education and preparing students and professors for an increasingly digitized academic environment.

Anthropology, in its various branches, explores human evolution and behavior in both biological and social contexts. The development of the prefrontal cortex, which occurs significantly during childhood and adolescence, is closely linked to the formation of executive functions and the establishment of the basis for future behavior. In this context, the social and educational environment, ranging from family to school, plays a crucial role in shaping the aspirations and vocations of young people. Reading, especially in the early stages of development, presents itself as a powerful tool that can foster interest in science and medicine. This article explores how the interaction between physical anthropology, child cognitive development, and literature can contribute to cultivating scientific vocations through children’s narratives. The aim of this research is to encourage medical vocation in children, combining reading and physical anthropology by introducing historical characters, such as the “Roman legionaries” who inhabited Caesaraugusta (Zaragoza, Spain) in the 2nd century A.D., through a motor story aimed at schoolchildren. This approach is used as a scientific transfer tool to generate greater interest in the medical and anthropological field among children. As a result of this proposal, a book entitled “Maripi: the scientific gladiator” has been created and edited, which will be implemented in the early childhood education classroom after its publication. This book will not only narrate the experiences and the context of the Roman legionaries, but it is also designed to capture the attention of children and stimulate their curiosity about medicine. From this work it is concluded that reading at early ages can be a facilitating element for science, in this case physical anthropology, to contribute to enhance medical vocations in the youngest and also as a resource for transferring scientific knowledge to the youngest.

The integration of digital technologies into education represents a significant evolution in the pedagogical landscape, with the potential to enhance accessibility, engagement, and personalization in learning. This review synthesizes current trends, challenges, and innovations within digital learning, emphasizing the impact of artificial intelligence (AI), virtual reality (VR), and online platforms on student achievement. It highlights the importance of addressing technical, pedagogical, and socioeconomic challenges to ensure equitable access to technology. Successful initiatives like the Open University illustrate digital learning's potential to improve educational outcomes. The review also anticipates future directions, including the expanding role of AI, VR, mobile learning, and blockchain in education. It concludes with strategic recommendations for educators and policymakers to adopt best practices, prioritize infrastructure development, and focus on continuous professional development to leverage the benefits of digital learning. As education enters an era of digital transformation, a collaborative approach among stakeholders will be essential in creating an inclusive and effective learning environment for the future.

IntroductionDespite the increase of three-dimensional (3D) technological integration into academia, little consideration has been given to the emotional responses of students to such pedagogy. Both pleasant (high valence/sentiment) and unpleasant (low valence/sentiment) emotions influence the cognitive processes involved in learning, and emotional sentiment can be exemplified by particular emoji.MethodsA survey with 10 facial emoji stratified into three categories (positive, neutral, and negative sentiment) was administered to students completing a human anatomy course with 3D visualization technology (3DVT) and augmented reality (AR) integration. The survey was administered before and after each class session (technology-based learning sessions, non-technology-based learning sessions, and examination sessions) to measure student emotional sentiment. Pre- and post-course questionnaires were also administered to clarify reactions to the technology.ResultsResults indicated that students reported positive and neutral emotions nearly exclusively, although students reported a reduction in emotional sentiment after technology-based learning sessions as compared to after non-technology-based learning sessions (Z = −2.557, p = 0.011). Lower emotional sentiment was associated with the examination sessions as compared to either of the learning session types, and students reported an increase in emotional sentiment after the examination sessions as compared to before the examination sessions (Z = −2.066, p = 0.039).DiscussionThe present study revealed that the 3D technologies elicited primarily neutral or positive emotions, and that the integration of an emoji survey can aid instructors in monitoring student emotional responses to pedagogical interventions.

Success in school is closely linked to students’ ability to regulate their own learning. In mathematics, self-regulated learning (SRL) strategies can help students become more independent and proactive in their learning. However, there is limited research on how students can be effectively supported in developing and applying these strategies, especially for younger students. The purpose of this study is to evaluate the impact of a self-instructional SRL material. The material is designed in collaboration between researchers and teachers, and integrated into regular mathematics instruction. Specifically, we examine whether the use of the SRL material varies across schools and student groups. A quasi-experimental research design with pre- and post-tests was employed, involving 258 students in grades 5 and 6 from five different schools over the course of one semester. Data was collected through structured surveys measuring student engagement with the material, along with performance tracking before and after the intervention. The findings indicate that co-developing SRL materials with teachers, and embedding them in regular instruction, has clear advantages. The findings also show that while the material was used equally across genders and performance levels, variations remain due to school culture, socio-economic factors, and individual teacher influence. Notably, lower-performing students showed greater progress compared to high-performers, and girls engaged more actively with SRL strategies than boys. These findings have important implications for the design and implementation of SRL interventions. While integrating SRL support within everyday teaching fosters engagement, additional measures may be needed to address persistent disparities between schools and student groups.

Learning academic subjects in English can evoke a range of emotions among university students. For some students, learning a new language represents a valuable opportunity to expand their perspectives and communicate with people from diverse cultural backgrounds. For others, the language barrier can be an obstacle to understanding and expressing themselves, which can lead to feelings of lack of confidence. In this study, we are interested in the emotions that students may experience when they are in class learning subjects through English Medium Instruction (EMI). For this purpose, an Achievement Emotions Questionnaire with Likert-type questions was used. It includes items about their degree of confidence, anxiety, motivation or emotions when learning through EMI. The sample consisted of 231 students in the bilingual Primary Education program and in the Foreign Languages Approach Program of the University of Extremadura (PALEx). The results show significant differences between men and women in the case of shame, emotion experienced more by women than by men. However, the average number of women who feel positive emotions such as hope, enjoyment and pride is higher than that of men although the fact that they are unable to meet their expectations leads them to suffer from anxiety or disappointment to a greater extent than men. Nevertheless, men present a higher average in the emotions of anger and boredom. The results also show that the self-perceived level of English is relevant for experiencing positive emotions: the higher the level, the more enjoyable the English classes are and the more hope for success.

AimThe aim of the research is to identify and to analyse the possibilities of early school leaving support and predictive factors related to emotional and learning support and classroom organization.MethodsBased on the Teaching through Interactions Framework, the study analyses the socio-emotional and methodological factors of early school leaving – emotional and learning support and classroom organization. In the analysis of theoretical scientific literature, a Systematic Review has been carried out, where the scientific articles included in internationally cited databases Web of Science, Scopus and Ebsco have been analysed by key words. Correlation and regression analysis in the SPSS environment of the program for processing quantitative data has been performed in a correlative study.ResultsThe findings of the correlation analysis show that there are statistically significant negative correlations between early school leaving and emotional and learning support, as well as classroom organization. The selected six articles are mostly focused on the emotional support provision. As a result of the regression analysis, the most significant factor predicting early school leaving has been identified - the lack of emotional support.ConclusionScientific articles included in the WoS, Scopus and Ebsco databases do not use a holistic approach to preventing early school leaving. The lower the emotional, classroom organization and instructional support, the higher the risk of early school leaving. Teacher’s empathy and sensitivity to the academic, socio-emotional and developmental needs of individual students and the whole class are the most important predictors of early school leaving.

In higher education, lecturers experience difficulties motivating their students. Within the scope of this project, learning outcomes are intended to be enhanced by an innovative teaching and learning method: digital educational escape games. Exploring the design of digital escape games as a modern and constructivist approach to enhance teaching and learning in STEM (science, technology, engineering, mathematics) higher education, this paper outlines evidence-based research based on semi-structured expert interviews and qualitative content analysis. Experts’ insights into these thematic areas provide valuable perspectives on how digital escape games can effectively contribute to the teaching and learning experience in STEM disciplines. The results show expert opinions regarding key didactic aspects like the integration of educational content and learning processes into game design. It was found that the didactic and educational aspects of a game are inextricably linked and cannot be separated. In order to create an effective educational game, it is essential to establish the learning objective as the foundation for the game’s narrative. In addition to the consensus on the integration of didactics and games, there were also aspects on which educators and learners held opposing views. Hence, controversially discussed game design elements need to be subject of further research.

This systematic review, conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, evaluates the efficacy of emerging digital technologies—namely virtual reality (VR), augmented reality (AR), and adaptive learning technologies (ALT)—in enhancing vocabulary acquisition within English as a second language (ESL) education. By addressing a notable gap in the literature, this review explores how these technologies mitigate common learning challenges and improve educational outcomes. Through a critical analysis of recent empirical studies across diverse educational stages, it synthesizes findings to assess their impact on vocabulary retention and overall academic performance. The results indicate that these technologies enhance vocabulary acquisition and increase student motivation and engagement, significantly impacting educational practices and policymaking. This review highlights the transformative potential of VR, AR, and ALT in ESL education by providing immersive and personalized learning experiences that address traditional barriers in language acquisition.

The paper takes the evolution of China’s aesthetic education policy as its entry point to elucidate the intrinsic driving forces behind the development of aesthetic education. Political ideology, labor, and moral education are often interwoven, and these aims have simultaneously provided an opportunity for new media art to engage with aesthetic education. Under the policy support of the Ministry of Education’s new round of aesthetic education immersion initiatives, new media art has undertaken a series of reforms, innovations, and experiments—employing interactive and immersive methods—to enhance and expand aesthetic experiences. Due to the alignment of certain concepts with those in traditional philosophy, it has garnered institutional favor. Research indicates that new media art-based aesthetic education possesses notable advantages in cultivating imagination, creativity, and other capacities in the digital age; however, despite its rapid development propelled by policy momentum, it still faces challenges such as a shortage of qualified educators and a narrow understanding of aesthetic education—issues that may paradoxically give rise to a dilemma rooted in deeper systemic contradictions.

Due to the rapidly improving capability of large language models such as Generative Pre-trained Transformer models (GPT), artificial intelligence (AI) based tools have entered use in education at scale. However, empirical data are largely lacking on the effects of AI tools on learning. Here, we determine the impact of four GPT-based tools on college-aged participants’ reading comprehension of standardized American College Test (ACT)-derived passages using a randomized cross-over online study (n = 195). The four tools studied were AI-generated summaries, AI-generated outlines, a question-and-answer tutor chatbot, and a Socratic discussion chatbot. Consistent with our pre-registered hypotheses, we found a differential effect of AI tools as a function of baseline reading comprehension ability. AI tools significantly improved comprehension in lower performing participants and significantly worsened comprehension in higher performing participants. With respect to specific tools, low performers were most benefited by the Socratic chatbot while high performers were worsened most by the summary tool. These findings suggest that while AI tools have massive potential to enhance learning, blanket implementation may cause unintended harm to higher-performing students, calling for caution and further empirical study by developers and educators.

Artificial intelligence is revolutionizing industries including institutions of higher learning as it enhances teaching and learning processes, streamline administrative tasks and drive innovations. Despite the unprecedented opportunities, AI tools if not used correctly, can be challenging in education institutions. The purpose of this study was to comprehensively review the AI innovations, opportunities and challenges associated with the use of AI in higher Education of learning. A systematic literature review methodology was adopted and used to locate and select existing studies, analyze and synthesize the evidence to arrive at clear conclusion about the current debate in the area of study. Following the PRISMA, the study analyzed a total of 54 documents that met the inclusion and exclusion criteria set for selection of the documents. The review unveiled many opportunities including enhanced research capabilities, automation of administrative tasks among others. Artificial Intelligence tools are found to refine and streamline the administrative tasks in different units in higher institutions of learning. The challenges include ethical concerns, integrity issues and data fabrication issues. With the challenges notwithstanding, the benefits of Artificial Intelligence cannot be over emphasized. Artificial intelligence remains a powerful tool for research, automation of administrative tasked, personalized learning, inclusivity and accessibility of educational content for all. Emphasis should be put in regulatory frameworks detailing how such tools can be used while maintaining the level of ethical standards required.

IntroductionDigital technologies are widely integrated with teaching and learning, and examining these technological interventions in the classrooms has become an active research area. Existing reviews are often constrained, relying on qualitative methods like meta-analysis, scoping review, or systematic review, which tend to cover a limited number of studies. We conducted a bibliometric analysis of 1,128 articles published between 2014 and 2023 from the Web of Science database to provide a comprehensive overview of this field.MethodsThis study used Biblioshiny and VOSviewer tools to perform performance analysis and scientific mapping. In this study, performance analysis was performed, including descriptive statistics, publication trends, and identification of key actors. Furthermore, scientific mapping has also been done to visualize the prevalent structural aspects and hot research topics to observe the evolving dynamics over the past 10 years.ResultsThe findings indicate a significant rise in publications over the past decade, with an annual growth of 21.5 per cent. We identified prolific authors, institutions, journals, countries, articles, and keywords that encapsulate the domain of digital technologies in the classrooms. The prospective challenges were also identified, including a need for a more technology-driven culture, limited teacher assistance, user interface design issues, proper training, and a technological divide.DiscussionThe findings could encourage the use of digital technologies in the classrooms and offer insights for policymakers to (re)allocate resources. Furthermore, this work is valuable for informing scholars and practitioners about the current state of research, helping them to identify and focus on trending topics when deciding which areas to explore.

The landscape of higher education is continuously evolving, with online learning emerging as a prominent educational modality. This cross-sectional study, conducted at the Holy Spirit University of Kaslik (USEK) in Lebanon from January to October 2023, aimed to assess Lebanese students’ perceptions regarding the effectiveness of online learning as a mode of education and to develop strategies and recommendations for enhancing online learning in Lebanon. Using a convenience-sampling method, we collected 309 responses, focusing on educators’ preparedness, student satisfaction, adaptability in online learning, and preferences for future learning modalities. The results highlighted a pressing demand for innovative course design strategies that promote engagement and interactivity, with 41.4% of respondents expressing this need. Additionally, 34.6% of learners emphasized the need for accessible technical support. Furthermore, 38.8% of participants underscored the necessity of comprehensive training programs for educators and learners in navigating online learning environments effectively. Moreover, the preference for online or hybrid learning models (55%) emphasized the importance of flexibility while preserving the value of in-person interactions. The study also highlighted the potential of educational advances to further enhance online learning environments. These technologies could provide opportunities for personalized learning experiences, tailoring course content, delivery methods, and assessments to meet the diverse needs of students, thus fostering a more adaptable and inclusive learning ecosystem. These insights are crucial for refining online education strategies and addressing the evolving needs of students in Lebanon.

Education is one of the many sectors in which augmented reality has been successfully implemented. To determine how Augmented Reality (AR) supports education, this bibliometric study analyzes 1734 articles extracted from the Scopus database between 2010 and mid-2023. The study aimed to determine patterns in productivity, authorship and collaboration patterns, publications, citation structures, general research tendencies, and bibliographic coupling. Biblioshiny and VOSviewer were employed in this investigation. The outcomes of the study indicate an ongoing trend of increasing publication counts or more contributions since 2016, and still a trending topic studies on interactive learning environments and AR in education and knowledge constitute niche areas, while epidemiology, science education, and mobile augmented reality are important research topics that were underdeveloped and indicate a relationship that is both emerging and declining, based on a thematic analysis of the papers. Furthermore, the outcomes demonstrate that the USA, Spain, and the United Kingdom have the strongest global cooperation despite the USA writing more articles. To offer an ideal road map for scholars who would like to carry out research in this area, this paper also looks at the trendsetting in augmented reality in education.

The effective integration of Generative Artificial Intelligence (GenAI) into educational practices holds promise for enhancing teaching and learning processes. Examining faculty acceptance and use of GenAI implementation can provide valuable insights into the conditions necessary for its successful application. This study consisted of a survey to measure the acceptance and use of GenAI in the educational practice of 208 faculty members at a private university in Mexico. The survey instrument used integrates elements of the Technology Acceptance Model (TAM) and the Theory of Reasoned Action (TRA). The original questionnaire was translated into Spanish and validated by experts to ensure reliability and validity in the new context. Overall, acceptance dimensions obtained middle-high results. Behavioral intention obtained the highest values whereas Subjective norm obtained the lowest values. Significant differences in GenAI acceptance regarding faculty disciplines and sociodemographics were not identified. Also, faculty GenAI acceptance is positively moderate correlated with faculty GenAI use to produce text. The identified acceptance level among faculty toward the use of GenAI in educational environments leads to expect a promising future for its integration into teaching and learning practices. In addition, further research on GenAI integration for student use and the impact of faculty training on the effective use of GenAI in educational settings are encouraged.

IntroductionInclusive digital education is a growing field that aims to provide equitable learning opportunities for all students, including those with special educational needs (SEN). This study investigates the effectiveness of three pedagogical methods - problem/project-based learning (PBL), cooperative learning (CL), and service learning (SL) - in promoting inclusive digital education.MethodsWe adopted a quantitative approach, collecting data through a structured questionnaire administered to nine media education and pedagogy experts from Italy and Austria.ResultsResults showed that PBL, CL, and SL are generally effective but require differentiated implementation approaches to maximize inclusivity. Practical implementation in the inclusive context of PBL requires promoting student reflection and self-assessment adapted to students’ individual needs; in CL, group projects supported by digital collaboration tools (e.g., Google Docs) facilitate structured dialogue, peer collaboration, and shared responsibility, thereby increasing engagement; in SL, linking learning to real-world practice and designing experiences that reflect students’ abilities and interests emerge as crucial, especially for students with SEN.DiscussionThe implications of these findings suggest that educators should adopt flexible and adaptive strategies to successfully implement PBL, CL, and SL to ensure that they meet the diverse needs of students in digital environments. Limitations of the study and recommendations for future investigations are discussed to further develop this area of research.