Authors:
Camilo Espinosa Domínguez, Juan and Munar, Leonardo Saavedra and Andrea Castillo Beltrán, Paola and Alberto Peláez Ayala, Carlos and Fernando Solano Alegría, Andrés and Alexis Ospina Galindez, Johann
Abstract:
This study characterizes Inclusive Interactive Multimedia Experiences (IIMEs) within school contexts by integrating learning analytics to enable personalized student monitoring and evaluation. By analyzing regulatory documents and multimedia systems (MS) development methodologies, this paper provides comprehensive guidance for IIME pre-production, focusing on learning objectives, activities, responsible design, and inclusion. The research presents a detailed framework for IIME development. It addresses the integration of digital media, interaction modalities, sensory systems, and emotional engagement. Furthermore, it examines the technological mediation necessary to deliver a holistic multimedia experience, prioritizing accessibility and cultural sensitivity. A case study conducted at Rafael Navia Varón School in Cali, Colombia, demonstrates the practical application of the proposed framework through the development of Decisiones Cruciales, an IIME designed to address bullying and cyberbullying via interactive storytelling. This IIME uses learning analytics to provide teachers with detailed metrics on student performance and socio-emotional competencies. The findings from the students’ analysis highlight their engagement and the educational impact of the IIME, particularly in fostering empathy and communication skills. The results underscore the potential of IIMEs to advance inclusive education by delivering adaptive and culturally relevant content. This study contributes to the academic literature by offering practical guidelines for designing and implementing IIMEs that align with universal accessibility and responsible design principles, ultimately promoting an equitable and effective educational environment.
+ Info
Authors:
Silva, Francisco da Conceição and Santana, Andre Macedo and Feitosa, Rodrigo Miranda
Abstract:
With the increasing application of Artificial Intelligence (AI) in education, it becomes essential to understand the factors influencing school dropout, as the educational context demands reliable decision-making. This study investigates dropout indicators in secondary-level technical courses at a Brazilian institution, using Explainable AI (XAI) techniques applied to Machine Learning models. The study analyzed data from 15,084 students to identify the main factors contributing to school dropout, utilizing predictive models and applying the explainability techniques LIME and SHAP to highlight key dropout factors, thereby improving prediction transparency. The results show that decision tree-based models performed best, with Random Forest achieving 85% Recall, effectively identifying students at risk of dropout. LIME and SHAP consistently highlighted school attendance, family income, and place of residence as key dropout factors. The analysis of the explainers showed that students with low attendance and lower income are more likely to drop out. These findings highlight the importance of targeted educational policies, such as scholarship programs, transportation assistance, and personalized academic support, especially for vulnerable students. This study contributes to the understanding of factors associated with school dropout and provides insights for the formulation of more effective educational policies. Strategies such as scholarship programs, transportation assistance, and academic monitoring can be implemented to reduce dropout rates.
+ Info
Authors:
Maraza-Quispe, Benjamín and Hugo Rosas-Iman, Victor and Feliciano-Yucra, Giuliana and Cesar Martínez-Lopez, Atilio and Marianela Quispe-Flores, Lita and Reyes-Villalba, Edwin and Pablo Nina-Mita, Pedro
Abstract:
The research analyzes the impact of ChatGPT on the development of investigative competencies in students of regular basic education, focusing on three main aspects: its role in information retrieval, its contribution to the generation of accurate and relevant content, and its usability in fostering investigative skills. An experimental design was applied to a sample of 100 students, with 50 students using ChatGPT during the development of learning sessions and a control group of 50 students conducting their sessions through traditional methods. The students developed research projects evaluated according to six key criteria: coherence, precision, originality, content depth, problem-solving ability, and source management. Descriptive and comparative statistical analyses indicated that the experimental group outperformed the control group in coherence, precision, and originality. However, the control group showed better performance in source management, suggesting that traditional methodologies remain more effective for handling bibliographic references and searching for reliable sources. Regarding content depth and problem-solving ability, both groups achieved similar results, with a slight advantage observed in the experimental group. In summary, ChatGPT improves students’ coherence, precision, and originality in research tasks. Nonetheless, it is recommended to integrate its use with traditional methods to strengthen source management and ensure the comprehensive development of investigative competencies, promoting the ethical and responsible use of technology.
+ Info
Authors:
Martins, Valéria Farinazzo and Kawamoto, André Luiz Satoshi and de la Higuera Amato, Cibelle Albuquerque and Eliseo, Maria Amelia and Silveira, Ismar Frango
Abstract:
Although accessibility and digital inclusion are increasingly present in our daily lives, researchers have dedicated little effort debating these topics in Computer Science courses in Brazil. This paper presents a PBL (Problem-Based Learning) approach to Human-Computer Interaction classes which encourages students to discuss and consider accessibility issues during the systems project. As a result, the students created serious games aimed at the older people audience. This topic can be explored to increase students’ motivation, engagement, and commitment in the development of computational systems. This paper describes all the development phases suggested by our approach and outlines evaluation with students and teachers and discussion on the results from its application.
+ Info
Authors:
Guerrero-Romera, Catalina and Gómez-Hernández, José-Antonio and Salvador, Dor a Sales and Vera-Baceta, Miguel-Ángel and Antonio Merlo Vega, José and Cuevas-Cerveró, Aurora
Abstract:
In the 21st century, technologies have become an essential element in the daily lives of all people and a basic resource for participating in society and exercising their full rights as citizens. Nonetheless, not all the population has the necessary resources to be able to access and be digitally trained, which is why the digital divide is one of the great challenges nowadays, especially for the migrant population. This double digital and social divide can occur to a greater extent in women, creating a series of gaps that hinder their full social inclusion and make it necessary to acquire basic competences and skills that contribute to promoting and exercising their rights on an equal footing in society. The purpose of this paper is to present a basic digital education programme aimed at migrant women that includes different contents and activities aligned with the European DigComp Framework at the basic level. It is expected that this training will have an impact on their level of digital performance and on fostering their participation and social inclusion.
+ Info
Authors:
Espinoza, Cindy and Carretero, Jesús
Abstract:
Student dropout is a significant challenge in higher education, generating frustration in society and wasting resources. As a result, student retention constitutes a constant challenge for higher education institutions everywhere. This work focuses on the question: Can intelligent predictive data analysis techniques be applied to reduce the dropout rate in public and private universities? To answer this question, we have adopted an exploratory methodological approach based on historical data from approximately 13,715 applicants who later became university students. Unlike other research, based on publicly available data and statistics, our work relies on five years of actual data of students whose behavior has been synthesized in 27 variables related to socioeconomic, academic, and family factors and analyzes it. This paper has two main contributions. First, we propose intelligent predictive data analytics techniques and demonstrate that it is possible to profile and target the applicant for higher education as a strategy to reduce the dropout rate and improve their student welfare, so that the dropout probability can be used as part of an early warning in the recruitment process. Second, we propose a methodology for the segmentation and/or archetyping of applicants, which can be part of a corrective alert in the adaptation process. The profiling model and archetyping are replicable in private and public universities since we use easily extractable generic variables that do not require the university to have a high level of maturity in data management processes. Therefore, our results contribute to educational data mining (EDM), demonstrating that intelligent predictive data analysis techniques can be used to profile and archetype private and public university applicants for higher education. The evaluation of our solution proved that the neural network model profiled the dropout applicants with an accuracy higher than up to 97%, after which unsupervised learning was applied to generate archetypes.
+ Info
Authors:
Galeazzo, Elisabete and Anjos de Souza, Rodrigo and Maldonado Peres, Henrique E. and Pérez Lisboa, Maurício O. and Beccaro, Wesley and Yoshioka, Leopoldo R.
Abstract:
Analog-to-digital (AD) conversion is a widely covered topic in Electrical and Electronic Engineering undergraduate programs. To enhance the effectiveness of learning and to engage students in this subject, hands-on activities, such as laboratory experiments, are essential bridging theory and practice. However, it has been observed that many students experience difficulties in learning this topic. One of the reasons is the students’ lack of practical skills in carrying out experimental hardware assemblies and handling instruments. Furthermore, note that the high cost of laboratory teaching infrastructure limits the availability of a sufficient quantity of materials and hardware equipment, especially when it is necessary to accommodate numerous students in practical activities simultaneously. To address these challenges, this study proposes a user-friendly Virtual Instrument (VI) developed in LabVIEW® to enhance the understanding and learning of AD conversion concepts. The VI allows users to select different signal types and configure the AD converter parameters, so the resulting effect of these modifications can be immediately viewed on the student computer screen. Due to its versatility, the computational tool has been applied to Electrical Engineering students at the Escola Politécnica of the Universidade de São Paulo (EPUSP) since 2020. It was first implemented during the social isolation caused by the COVID-19 pandemic and later incorporated into the Electrical Instrumentation course as an additional resource for in-person classes. To evaluate the effectiveness of the VI, an analysis was conducted with 59 students — 29 who exclusively performed the AD conversion experiment using the VI and 30 who used traditional electronics bench infrastructure. The first group achieved a mean grade of 8.78, compared to a mean grade of 7.53 for the control group, which used the laboratory infrastructure. These findings suggest that students using the VI statistically outperformed their counterparts, with an average grade improvement of 16.6%. Therefore, we consider our approach a valuable complementary resource for teaching fundamental AD conversion concepts, with potential for application in other areas of engineering, such as in telecommunications, embedded systems, signal processing, among others.
+ Info
Authors:
Velásquez, Juan D. and Jaramillo, Patricia and Ibarra, Sara
Abstract:
This comprehensive literature review examines the dynamic evolution of business analytics education, with a focus on curriculum innovation, experiential learning, and emerging pedagogical strategies. Analyzing 103 scholarly articles from 2012 to 2024, the study identifies three core themes: Curriculum Innovation for Industry Competencies, Experiential Learning in Analytical Decision-Making, and Innovative Pedagogies for Skill Development. These themes are further examined through nine critical dimensions: Curriculum Design, Analytical Skills Development, Industry Collaboration, and Technology-Enhanced Learning. The review highlights the increasing importance of aligning curricula with industry demands, integrating data literacy and ethical considerations, and utilizing technology to enhance learning outcomes. Challenges such as the academic-industry gap and the need for ongoing faculty development are also discussed. This review synthesizes current trends in business analytics education. It offers insights for future curriculum innovation and industry collaboration, emphasizing the need to equip graduates with essential competencies for the modern workforce.
+ Info
Authors:
Prates, Jorge Marques and Alario-Hoyos, Carlos and Maldonado, José Carlos
Abstract:
Massive Open Online Courses (MOOCs) are digital courses that offer open learning content, reaching a broad audience of students. In the realm of Software Engineering Education, MOOCs can be integrated with methodologies like flipped classrooms and blended learning. However, effectively evaluating the use of MOOCs poses a challenge due to the absence of defined metrics for assessing their quality. In this context, this study aims to scrutinize the quality of MOOCs, specifically focusing on Software Engineering. The research questions investigate several aspects through a Systematic Mapping Mapping, including the quality criteria for MOOC evaluation, specific characteristics relevant to Software Engineering education, the application of quality models, the relationship between standardized concepts in MOOCs and their quality, and the benefits of quality assessments conducted by accreditation agencies. The research endeavors to offer a comprehensive insight into quality assessment within the MOOC landscape, with a particular emphasis on Software Engineering Education. The results encompass the identification of quality criteria for evaluating MOOCs in the field of Software Engineering, as well as a deeper understanding of the particular characteristics that impact the quality of these courses.
+ Info
Authors:
Izaguirre, Evelyn Del Pezo and Abásolo, María J. and Collazos, César A.
Abstract:
UNESCO emphasizes the need for inclusive and quality education for all. In this context, the present article introduces BlipBla, a mobile and collaborative application designed to teach lip reading to preschool-aged deaf children. The development of BlipBla integrates active pedagogical methodologies, mobile technologies, and an accessible interface that facilitates interaction between teachers and students without requiring advanced reading and writing skills. The main contributions of this work include: 1) the design of an educational tool that incorporates vocabulary and sentences with clear grammatical structure; 2) the implementation of a customizable and collaborative environment; and 3) the validation of the application based on the ISO 25010 standard, which reported functional compliance above 94% in both the administrator and student environments. It is concluded that BlipBla represents a significant advancement in the development of accessible resources tailored to the needs of the deaf child community, and further testing with end users is projected to strengthen its usability and educational reach.
+ Info