Authors:
Juan José Victoria Maldonado, Santiago Alonso García, Alejandro Martínez Menendez, Manuel Enrique Lorenzo Martín
Abstract:
The growing relevance of Artificial Intelligence (AI) in education necessitates a better understanding of its acceptance among future educators. This study investigates the factors influencing pre-service teachers’ intention to use AI, employing the UTAUT2 model extended with sociodemographic moderators. A cross-sectional quantitative design was applied to a sample of 908 undergraduate students from Early Childhood and Primary Education programs in Andalusia, Spain. Structural equation modeling results reveal that performance expectancy, effort expectancy, and habitual use are significant predictors of behavioral intention toward AI use. In contrast, the proposed moderating effects of gender and academic year were found to be non-significant. Findings highlight the pivotal role of habitual engagement with AI while questioning the effectiveness of current curricular approaches in promoting its pedagogical use, as academic progression showed no moderating influence. The study emphasizes the need for targeted training and curricular updates to foster meaningful AI integration in teacher education.
+ Info
Authors:
Antonio Carlos Bento, José Reinaldo Silva, Marcos Ribeiro Pereira Barretto, Sérgio Camacho-León, Elsa Yolanda Torres-Torres
Abstract:
This paper examines the pedagogical impact of Artificial Intelligence-assisted tools in a university software construction course. Through a 10-week case study with 25 engineering students, the study captures qualitative insights into how students interact with AI tools, the challenges they face, and the learning strategies that emerge. While students reported perceived time savings, the core contribution lies in understanding the educational implications, both positive and challenging of integrating AI into project-based learning environments. The findings reveal that Artificial Intelligence tools enhance prototyping and debugging skills but require structured integration to mitigate over-reliance. The study contributes a framework for balancing Artificial Intelligence use with traditional pedagogy, supporting Sustainable Development Goals 4’s goal of equitable education, while the opinion survey carried out with students shows a result of 96% satisfaction with the use of assisted artificial intelligence tools during the development of the project during the studies.
+ Info
Authors:
Rodolfo Alan Martínez Rodríguez, José Manuel Valencia-Moreno, Olivia Denisse Mejía Victoria, Alma Alejandra Soberano Serrano
Abstract:
Academic performance prediction remains a critical challenge in Latin American higher education, where institutional heterogeneity and limited data availability constrain the effectiveness of traditional analytical approaches. While supervised machine learning models often achieve high predictive accuracy, they typically lack interpretability and fail to capture latent student profiles required for actionable educational interventions. This study proposes a unified and interpretable hybrid framework that integrates predictive modeling and clustering within a single analytical pipeline. The approach simultaneously estimates academic risk and identifies student profiles using a real-world dataset of 386 first-year students from a Mexican public university. The results demonstrate that, while individual supervised models achieved strong predictive performance (AUC up to 0.84), the primary contribution of the proposed approach lies in its integrative capacity. The hybrid pipeline achieved competitive performance (AUC = 0.85; F1-score = 0.76) and enabled cross-paradigm validation between predictive and clustering outputs ( $\kappa = 0.70$ ), providing evidence of structural consistency in student risk patterns. Beyond predictive accuracy, the framework links probabilistic predictions with behavioral profiles and anomaly detection, enabling the identification of heterogeneous at-risk groups and supporting targeted pedagogical interventions. These findings demonstrate the potential of hybrid learning analytics approaches to bridge the gap between predictive performance and actionable educational insights, offering a scalable and interpretable solution for early-warning systems in resource-constrained higher education environments.
+ Info
Authors:
Manuel A. Perales-Esteve, Samuel Yanes Luis, Alfredo Pérez Vega-Leal
Abstract:
This paper describes an instructional experience in a core course of an Electronic, Robotic and Mechatronic Engineering degree, where students were encouraged to address socially relevant needs through their project work. While no formal collaboration with community partners was established, the initiative introduced elements inspired by Service-Learning within a Project-Based Learning framework. Results from four academic years, including student survey data, indicate that linking projects to familiar real-life contexts fosters modest improvements in motivation and perceived relevance of course content. The study discusses the potential of this socially oriented approach as a transitional step toward the future integration of authentic Service-Learning practices in engineering curricula.
+ Info
Authors:
Salwa Mrayhi, Mohamed Koutheair Khribi, Mohamed Jemni
Abstract:
Massive Open Online Courses (MOOCs) broaden access to learning, but inclusivity remains uneven when accessibility and personalization are treated as peripheral rather than foundational design requirements. This PRISMA 2020-aligned systematic review (2018–2025) examines how accessibility by design and Adaptive and Personalized Technologies for Learning (APTeL) are implemented in MOOCs and how they relate to learner outcomes (access, engagement, persistence, achievement). Fifty-six empirical studies met the inclusion criteria by addressing WCAG- or ARIA-based accessibility and/or APTeL mechanisms such as learner modeling, recommender systems, adaptive sequencing, and adaptive feedback. Across this corpus, media-level accessibility was most common, with captions and transcripts reported in 68% of studies, alternative formats (for example, alt text and audio description) in 46%, and assistive technology checks in 34%, while explicit WCAG or ARIA citation (29%) and explicit UDL alignment (21%) were comparatively limited. Personalization efforts centered on learner modeling (54%), recommender systems (41%), adaptive sequencing (36%), and adaptive feedback (30%). Outcome reporting favored engagement proxies (75%) over achievement (38%) and persistence or retention (32%), and only 11% of studies disaggregated outcomes by disability. The clearest benefits appeared when accessible and operable interaction pathways were co-designed with APTeL adaptations explicitly mapped to learning objectives, UDL checkpoints, and assessment strategies. However, heterogeneous conformance reporting, limited assistive technology validation, sparse UDL mapping, and weak outcome validity reduce interpretability and restrict causal claims about impact on learning and persistence. The review specifies design and practice implications for accessibility-aligned APTeL in MOOCs, identifies methodological and ethical gaps that constrain generalizability and equity inferences, and proposes priorities for platform policy and rigorous, disability-aware evaluation frameworks.
+ Info
Authors:
Dennis Bolaños, Christian Caizaluisa, Daniel Zapata-Hidalgo, David Loza-Matovelle
Abstract:
This study presents the design and implementation of a collaborative robot (cobot) intended as an educational tool for robotics within the STEM framework. The cobot integrates direct and inverse kinematics for motion control and joint-level mechanical impedance modulation. It also features a user-friendly interface with a digital twin. The prototype was fabricated using additive manufacturing and optimized via CAD/CAE tools. It achieved a positioning accuracy of ±6.19 mm, which was validated under ISO 9283 standards. The digital twin serves not only as a technical support tool but also as a teaching resource, providing immediate visualization of robot states and motion. This helps learners connect kinematic and control concepts with observable behavior. The system supports autonomous “Learning” and “Reproduce” functions, bridging the gap between theoretical concepts and practical applications. These modes enable repeatable experimentation, allowing students to record and reproduce trajectories and to contrast the physical execution with its synchronized virtual representation. This reinforces understanding through guided trial and improvement. The Cobot involves learners in fundamental STEM disciplines, including computer programming, engineering design principles, mathematical concepts, and systems-oriented thinking. The collaborative robot has significant potential as an effective pedagogical platform that promotes interdisciplinary education and practical problem-solving in robotics. Finally, statistical analysis confirmed the normality of the data and the reliability of the performance data, further supporting its value in learning environments.
+ Info
Authors:
Adriana Dapena, Paula M. Castro, Lucas Alonso de San Segundo, Óscar Fresnedo
Abstract:
The Final Degree Project (FDP) represents the culmination of higher education studies and marks a key transition from academic training to professional practice. This paper aims to analyze the integration of sustainability, ethics, and gender perspectives in the design, development, and evaluation of FDPs, in alignment with the principles of the European Higher Education Area (EHEA). These dimensions are essential for fostering transversal competences that prepare students to address complex social and professional challenges. We propose a general framework for addressing these cross-cutting aspects throughout the different stages of the FDP process. This involves embedding them in course guides, applying them during project development, and integrating them into the final evaluation criteria. Additionally, we present two case studies that illustrate the current state of integration of these dimensions in real FDP contexts. The analysis reveals that, while some sustainability, ethical, and gender-related aspects are already considered, their implementation remains partial and inconsistent. This highlights the need for clearer guidelines, structured methodologies, and greater institutional support to ensure their effective incorporation.
+ Info
Authors:
Adriana L. Iniguez-Carrillo, Laura S. Gaytán-Lugo
Abstract:
The rapid advancement of Automatic Speech Recognition and Artificial Intelligence has enabled the development of Intelligent Personal Assistants (IPA) that facilitate natural, voice-based interactions with computational systems. This work presents the creation and evaluation of “Smart Tutor,” an IPA designed to assist engineering students at Universidad de Guadalajara with academic and administrative inquiries. The Tutor aims to offer an intuitive, human-like interaction experience to streamline information acquisition. Usability was evaluated using the SOVO instrument, focusing on effectiveness, efficiency, and user satisfaction. Initial and refined iterations of the prototype demonstrated improvements in user understanding and response times. The findings highlight the potential benefits of voice-based assistants in educational contexts, particularly in reducing administrative burdens and enhancing the learning experience.
+ Info
Authors:
Ginna Viviana Leytón-Yela, Hector Mora, Jesus Insuasti, John Barco-Jimenez
Abstract:
This article presents a comparative analysis of automatic error classification in Python programming tasks involving loops, with a focus on machine learning approaches for identifying error types. Three experiments were conducted: the first evaluated traditional machine learning algorithms; the second explored alternative kernel functions in SVM and MLP algorithms; and the third involved two multi-input deep learning models. Following the CRISP-DM methodology, we compiled a dataset of 3000 looped programming tasks, each including a problem description in English, a Python solution, and a classification based on state errors formulated by Gries theory (initial S, final E, state transformation T, and their combinations, totaling seven labels). In preprocessing, the code was partitioned using its AST to align it with Gries states, and both the problem descriptions and code snippets were embedded with Bert, Code-bert, and Graph-code-bert. Ablations were performed to approximate the optimal solutions for each algorithm as closely as possible. The results showed that traditional machine learning algorithms achieved up to 90% accuracy and an MCC of 83%, while alternative kernels marginally improved performance but did not surpass that of traditional algorithms. Deep learning models (ANN-GCB) achieved the best balance, with 94% accuracy and 91% MCC, respectively, demonstrating their superiority for this classification task. The model was validated with external sources from different repositories, yielding an 85% success rate, and with a group of 138 students, achieving a 96.7% correct or partially correct classification rate.
+ Info
Authors:
Thiago J. Luz
Abstract:
The demand for engineering programmes has declined by 30% over the last decade, creating a critical need for retention strategies. In 2021, the mandatory integration of extension into the undergraduate curriculum was established in Brazil, requiring that a minimum of 10% of the total curriculum be dedicated to extension activities. This exploratory case study investigates the impact of extension activities integrated into the curriculum on the holistic development and academic retention of nontraditional engineering students (working adults) at a private higher education institution. It aims to analyse the potential of extension as a strategic tool to mitigate the “engineering blackout” and the skills gap in the labour market. This study analyses the implementation of service-learning in two courses of an Electrical Engineering programme between 2024 and 2025, in which 38 students participated. The intervention involved nine service-learning projects ranging from technical consultancy to community co-creation. Data collection utilised individual self-assessments and technical reports, analysed through content analysis based on the Queiruga-Dios framework and Freire’s theoretical perspective. Findings indicate that 92% of students developed technical skills and 89% improved soft skills, such as teamwork and adaptability. Furthermore, 76% demonstrated a shift in social responsibility attitudes, and four out of nine projects achieved a transformative approach, characterised by direct co-creation and dialogue. Crucially, the extension courses achieved a 97.4% student success rate, contrasting sharply with a 36.1% failure/dropout rate in standard technical courses during the same period. The study concludes that mandatory extension effectively democratizes professional skill acquisition and fosters organic community engagement, serving as a vital retention strategy for private institutions despite resource constraints.
+ Info