Machine learning techniques for the prediction of performance in the learning process are primarily studied at the post-secondary level of education. Data sets are usually large at that level, resulting in predictive models that have a high accuracy. In contrast, limited research has been conducted at the secondary school level, mostly due to the typically small data sizes and the unique educational challenges of that level. In the present study we aimed to address such issues by implementing a model to predict the final performance of lower secondary school students in a course on Informatics, using a teaching scenario that combined the flipped classroom, a variation of the jigsaw technique and educational robotics. Given the student grades from the first third of the year, as well as demographics data, we used an IBM data analytics tool to create and test several predictive models. The CHAID algorithm achieved the highest accuracy (82.14%) and AUC value, outperforming others like Quest, C5, BN, and RF. The tool also pinpointed the educational activity that was the most significant predictor of final performance, indicating its strong instructional value. Despite the relatively small dataset, the results suggest that careful parameter selection can yield models that predict learner performance with a high accuracy and assist educators in continuously improving their teaching for better student outcomes.
Assessing competencies in engineering education increasingly requires digital assessment approaches that support learning regulation, instructional decision-making, and educational quality, rather than focusing solely on measurement efficiency. Computerized adaptive testing (CAT), grounded in Item Response Theory (IRT), provides a robust methodological foundation for personalized assessment. However, its pedagogical effectiveness in formative contexts depends critically on curriculum alignment, diagnostic capacity, and adaptive control strategies. This study proposes and evaluates a formative adaptive assessment framework for engineering education that integrates an IRT-based CAT engine with a Bayesian network- based diagnostic component. The framework is designed to support competency-oriented feedback, learning monitoring, and instructional interpretation within a curriculum-aligned assessment structure. Assessment relies on dichotomous multiple-choice items explicitly aligned with engineering learning outcomes, while item selection dynamically adapts to learners' evolving proficiency estimates. In parallel, probabilistic diagnostic modelling prioritizes under-assessed competencies throughout the adaptive process. Item calibration was conducted using empirical data collected from 612 university students in computer science, and system performance was examined through a simulation-based evaluation involving 500 simulated learners. Results demonstrate high estimation accuracy (r = 0.912) and satisfactory reliability for formative use across most learner profiles. Reduced precision at the extremes of the proficiency continuum and imbalances in item exposure were also observed, highlighting structural limitations primarily related to item bank coverage and curriculum representation rather than to the adaptive algorithms themselves. Overall, the proposed framework positions adaptive assessment as a pedagogically grounded tool for formative learning support, instructional decision-making, and quality assurance in engineering education.
The growing incorporation of generative artificial intelligence (GAI) in educational settings is transforming the teaching of technical writing in engineering education. However, there is little evidence on how students adopt these technologies in the development of technical reports, a key transversal skill in their future professional practice. This case study analyzes the relationship between GAI acceptance and self-efficacy in technical report writing among 158 engineering students at a national university in Peru. A quantitative, correlational approach and a non-experimental design were used. The results indicate that most students show moderate to high levels of technological acceptance and self-efficacy in writing technical reports, with a clear predominance of positive attitudes towards the use of GAI. Significant positive correlations were found between the dimensions of perceived use, ease of use, and intention to use GAI with the key stages of planning, drafting, and reviewing technical reports. It is concluded that the effective integration of GAI improves academic and professional engineering education by strengthening students' confidence and skills in specialized writing. Finally, it is recommended that future research incorporate variables such as intrinsic motivation and critical thinking, considering their application in different branches of engineering.
This study aims to identify opportunities for improving a project-based, design-oriented learning approach in design studies, focusing on mechanisms that promote student motivation, competence, and identity development in the context of interdisciplinary cooperation. The following research methods were employed: scientific literature analysis and focus group discussions to ensure data triangulation. Action pilot research was conducted during the development of a design project, with its stages aligned to the phases of the design process. The findings highlight key factors contributing to students' personal development and successful project outcomes. These include the organization and material infrastructure of the study process, the importance of collaboration across institutional units, among lecturers, and between lecturers and students. The study concludes that strengthening collaboration and stakeholder involvement in the improvement of the study process enhances students' learning experiences, facilitates knowledge exchange, and increases motivation and learning effectiveness.
This study explains undergraduate engineering students' engagement in blended learning through the lens of Herzberg's Two-Factor Theory and the mediating role of learning motivation. Survey data from 656 engineering students enrolled in blended courses at Hanoi University of Science and Technology were analyzed using PLS-SEM. Results indicated that motivator factors strongly influenced learning motivation, which in turn significantly predicted learning engagement, while hygiene factors had only a small direct effect on learning motivation but an indirect role through motivator factors. Mediation analysis confirmed a ing 58% of motivation and 78% of engagement variance. The findings highlight that stable course conditions enable pedagogy-centered motivators to activate motivation and sustain engagement. Practical implications emphasize the need for designing blended courses that combine reliable technical environments with intrinsically motivating learning designs.
