Santiago Castro-Arias
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Santiago Castro-Arias has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Monica-Daniela Gomez-Rios
Universidad Politécnica Salesiana
7 shared publications - Miguel-Angel Quiroz-Martinez
Universidad Politécnica Salesiana
6 shared publications - Angel Torres-Toukoumidis
Social Science Knowledge and Human Behavior Department, Universidad Politécnica Salesiana, Cuenca, Ecuador
3 shared publications - Maikel Yelandi Leyva Vázquez
Universidad Bernardo O'Higgins, Santiago, Chile; Universidad de Guayaquil, Guayaquil, Ecuador, Chile
2 shared publications - Moisés Pallo Chiguano
Universidad Politécnica Salesiana
2 shared publications - Andrea Mila-Maldonado
Universidade de Vigo
1 shared publication
Latest Publications
- Open Access
- 6 August 2026
- Published by MDPI AG in Healthcare
- Vol. 14 (15) , 2424
The Role of Emotions in Health Literacy and Patient Education: Trends, Technologies, and Future Opportunities—A Scoping Review
Background/Objectives: Health literacy and patient education play a key role in supporting informed decision-making, treatment adherence, and disease self-management. While educational interventions have traditionally focused on improving knowledge and understanding, emotions are increasingly recognized as factors associated with learning processes and healthcare experiences. This scoping review mapped the role of emotions in health literacy and patient education by identifying the emotions investigated, assessment methods, technologies employed, educational outcomes, and opportunities for emerging technologies. Methods: A scoping review was conducted following PRISMA-ScR and Joanna Briggs Institute guidance. Searches were finalized in Scopus and PubMed on 6 June 2026, with no publication-date restrictions; only English-language journal articles and reviews were eligible. Two reviewers screened records, extracted data, and classified studies, resolving disagreements by consensus and consulting methodological or clinical co-authors when needed. Results: A total of 135 studies were included. Anxiety and emotional distress were the most frequently investigated emotional categories, whereas emotional support, reassurance, and emotional engagement received less attention. Interviews, surveys, questionnaires, and standardized scales were the predominant assessment methods. Emotional well-being and understanding were the most frequently reported educational outcomes, followed by adherence, communication, and emotional support. Educational programs and educational materials were the most commonly employed approaches, while digital health solutions appeared less frequently. Limited use of artificial intelligence and objective emotion-recognition methods was identified. Conclusions: Emotional factors were associated with several patient-education outcomes, but the heterogeneous and predominantly self-reported evidence does not establish causality. Emerging technologies warrant further evaluation before their effectiveness, feasibility, and safety in patient education can be established.
- 6 August 2026
- Published by MDPI AG in Healthcare
- Vol. 14 (15) , 2424
Open AccessThe Role of Emotions in Health Literacy and Patient Education: Trends, Technologies, and Future Opportunities—A Scoping Review
Background/Objectives: Health literacy and patient education play a key role in supporting informed decision-making, treatment adherence, and disease self-management. While educational interventions have traditionally focused on improving knowledge and understanding, emotions are increasingly recognized as factors associated with learning processes and healthcare experiences. This scoping review mapped the role of emotions in health literacy and patient education by identifying the emotions investigated, assessment methods, technologies employed, educational outcomes, and opportunities for emerging technologies. Methods: A scoping review was conducted following PRISMA-ScR and Joanna Briggs Institute guidance. Searches were finalized in Scopus and PubMed on 6 June 2026, with no publication-date restrictions; only English-language journal articles and reviews were eligible. Two reviewers screened records, extracted data, and classified studies, resolving disagreements by consensus and consulting methodological or clinical co-authors when needed. Results: A total of 135 studies were included. Anxiety and emotional distress were the most frequently investigated emotional categories, whereas emotional support, reassurance, and emotional engagement received less attention. Interviews, surveys, questionnaires, and standardized scales were the predominant assessment methods. Emotional well-being and understanding were the most frequently reported educational outcomes, followed by adherence, communication, and emotional support. Educational programs and educational materials were the most commonly employed approaches, while digital health solutions appeared less frequently. Limited use of artificial intelligence and objective emotion-recognition methods was identified. Conclusions: Emotional factors were associated with several patient-education outcomes, but the heterogeneous and predominantly self-reported evidence does not establish causality. Emerging technologies warrant further evaluation before their effectiveness, feasibility, and safety in patient education can be established.
- 2 August 2026
- Published by Springer Nature
- p. 484-494
Media Representations in Emergency Contexts: A Bibliometric Analysis of Humanitarian Crises
- 2 August 2026
- Published by Springer Nature
- p. 484-494
Media Representations in Emergency Contexts: A Bibliometric Analysis of Humanitarian Crises
- 27 May 2026
- Published by Springer Nature
- p. 296-309
Framework for Implementing LLMS for Software Quality
- 27 May 2026
- Published by Springer Nature
- p. 296-309
Framework for Implementing LLMS for Software Quality
- Open Access
Lightweight Machine Learning-Based QoS Optimization for Multi-UAV Emergency Communications in FANETs
Flying Ad Hoc Networks (FANETs) composed of multiple unmanned aerial vehicles (UAVs) are a promising solution for emergency wireless communications when terrestrial infrastructure is unavailable. However, ensuring reliable Quality of Service (QoS) in these highly dynamic networks remains challenging due to topology changes, varying propagation conditions, and congestion. This work proposes a lightweight machine learning-based QoS optimization framework for multi-UAV emergency communications that combines realistic mobility modeling, empirical channel measurements, and adaptive traffic prioritization. UAV mobility patterns are generated with ArduSim, while LoS/NLoS propagation models are derived from real UAV flight experiments and integrated into ns-3. Multiple supervised machine learning algorithms—including Decision Trees, Random Forest, Support Vector Machines, k-NN, Gradient Boosting, and CatBoost—are trained using four input features derived from the network state: , , , and . Simulation results show that the proposed AI SMOTE EMERGENCY scheme, based on CatBoost, improves the Packet Delivery Ratio (PDR) by approximately 43% over the No-QoS baseline, achieving 89–93% delivery across all four application ports. Compared with EDCA, the proposed scheme maintains reliable delivery for all services, increases emergency throughput by 34–36%, and reduces end-to-end delay by about 70%. In addition, the higher delivery reliability translates into clear communication energy benefits, reducing energy waste across all evaluated topologies when compared with the No-QoS baseline. The inference time remains below 0.002 s, supporting real-time QoS adaptation in resource-constrained UAV networks.Open AccessLightweight Machine Learning-Based QoS Optimization for Multi-UAV Emergency Communications in FANETs
Flying Ad Hoc Networks (FANETs) composed of multiple unmanned aerial vehicles (UAVs) are a promising solution for emergency wireless communications when terrestrial infrastructure is unavailable. However, ensuring reliable Quality of Service (QoS) in these highly dynamic networks remains challenging due to topology changes, varying propagation conditions, and congestion. This work proposes a lightweight machine learning-based QoS optimization framework for multi-UAV emergency communications that combines realistic mobility modeling, empirical channel measurements, and adaptive traffic prioritization. UAV mobility patterns are generated with ArduSim, while LoS/NLoS propagation models are derived from real UAV flight experiments and integrated into ns-3. Multiple supervised machine learning algorithms—including Decision Trees, Random Forest, Support Vector Machines, k-NN, Gradient Boosting, and CatBoost—are trained using four input features derived from the network state: , , , and . Simulation results show that the proposed AI SMOTE EMERGENCY scheme, based on CatBoost, improves the Packet Delivery Ratio (PDR) by approximately 43% over the No-QoS baseline, achieving 89–93% delivery across all four application ports. Compared with EDCA, the proposed scheme maintains reliable delivery for all services, increases emergency throughput by 34–36%, and reduces end-to-end delay by about 70%. In addition, the higher delivery reliability translates into clear communication energy benefits, reducing energy waste across all evaluated topologies when compared with the No-QoS baseline. The inference time remains below 0.002 s, supporting real-time QoS adaptation in resource-constrained UAV networks. - Open Access
- 15 January 2026
- Published by Universidad de la Sabana in Palabra Clave
- Vol. 28 (4)
Tendencias léxicas, emocionales y temáticas de los debates presidenciales. Casos México, Estados Unidos y Ecuador
Este artículo analiza comparativamente los debates presidenciales recientes en Ecuador, México y Estados Unidos, identificando tendencias léxicas, emocionales y temáticas mediante técnicas de procesamiento de lenguaje natural. Se examinaron cinco debates oficiales entre 2024 y 2025 mediante análisis léxico, afectivo y temático, utilizando frecuencias, diversidad vocabular, distribución emocional, polaridad y redes de tópicos. Los resultados muestran una fuerte personalización del discurso centrada en los candidatos, con mayor riqueza léxica en Estados Unidos, repetición en México y focalización temática en Ecuador. Emociones como la confianza y la anticipación dominaron en los tres contextos, seguidas por el miedo, lo que revela estrategias de movilización contenidas. Los índices de legibilidad fueron alarmantemente bajos, lo que plantea tensiones en la accesibilidad ciudadana al lenguaje político. Temáticamente, Ecuador priorizó seguridad y gobernabilidad, México abordó programas sociales y cuestiones de género y Estados Unidos enfatizó política exterior y liderazgo institucional. El estudio muestra que, aunque cada país articula prioridades políticas distintas, los debates funcionan como una plataforma estratégica donde se combinan liderazgo, gestión emocional y construcción temática con la lógica mediática que caracteriza a las democracias contemporáneas.
- 15 January 2026
- Published by Universidad de la Sabana in Palabra Clave
- Vol. 28 (4)
Open AccessTendencias léxicas, emocionales y temáticas de los debates presidenciales. Casos México, Estados Unidos y Ecuador
Este artículo analiza comparativamente los debates presidenciales recientes en Ecuador, México y Estados Unidos, identificando tendencias léxicas, emocionales y temáticas mediante técnicas de procesamiento de lenguaje natural. Se examinaron cinco debates oficiales entre 2024 y 2025 mediante análisis léxico, afectivo y temático, utilizando frecuencias, diversidad vocabular, distribución emocional, polaridad y redes de tópicos. Los resultados muestran una fuerte personalización del discurso centrada en los candidatos, con mayor riqueza léxica en Estados Unidos, repetición en México y focalización temática en Ecuador. Emociones como la confianza y la anticipación dominaron en los tres contextos, seguidas por el miedo, lo que revela estrategias de movilización contenidas. Los índices de legibilidad fueron alarmantemente bajos, lo que plantea tensiones en la accesibilidad ciudadana al lenguaje político. Temáticamente, Ecuador priorizó seguridad y gobernabilidad, México abordó programas sociales y cuestiones de género y Estados Unidos enfatizó política exterior y liderazgo institucional. El estudio muestra que, aunque cada país articula prioridades políticas distintas, los debates funcionan como una plataforma estratégica donde se combinan liderazgo, gestión emocional y construcción temática con la lógica mediática que caracteriza a las democracias contemporáneas.
- 2 January 2026
- Published by Springer Nature
- p. 295-310
Use of a Vocational Test Using a Chatbot in the Selection of a University Career
- 2 January 2026
- Published by Springer Nature
- p. 295-310
Use of a Vocational Test Using a Chatbot in the Selection of a University Career
- 30 July 2025
- Published by Salesian Polytechnic University of Ecuador
- p. 247-264
Inteligencia artificial para la evaluación ética y personalizada de trabajos de titulación en la educación superior
El presente trabajo explora el potencial de la inteligencia artificial (IA) en la evaluación ética y personalizada de trabajos de titulación en la educación superior. A partir de una revisión conceptual y bibliométrica, se argumenta cómo la IA, integrada con el enfoque de aprendizaje basado en investigación (ABI), puede ofrecer soluciones que fomenten la originalidad, la autonomía y la equidad en la formación académica.Se plantea una propuesta que conjuga modelos de tutoría automatizada, retroalimentación inteligente y asignación óptima de recursos humanos, todo dentro de un marco institucional que respete la privacidad, la ética y el desarrollo integral del estudiante. A la par, se discute la necesidad de políticas que regulen el uso de IA generativa, asegurando que complemente y no sustituya el rol del tutor humano, promoviendo un aprendizaje profundo, reflexivo y socialmente relevante (Delgado y Martín, 2024; Lérias et al., 2024; López Chila et al., 2024). Lo que hoy tenemos enfrente no solo es la automatización de tareas intelectuales que requieren que los programas educativos se adapten y actualicen, sino que además sean inclusivos, pero será necesario abordar también las brechas tecnológicas en aumento ubicados en países en desarrollo como sucede en Ecuador, Bolivia y Perú en lugares marginales y de difícil acceso determinados por la cobertura de internet.
- 30 July 2025
- Published by Salesian Polytechnic University of Ecuador
- p. 247-264
Inteligencia artificial para la evaluación ética y personalizada de trabajos de titulación en la educación superior
El presente trabajo explora el potencial de la inteligencia artificial (IA) en la evaluación ética y personalizada de trabajos de titulación en la educación superior. A partir de una revisión conceptual y bibliométrica, se argumenta cómo la IA, integrada con el enfoque de aprendizaje basado en investigación (ABI), puede ofrecer soluciones que fomenten la originalidad, la autonomía y la equidad en la formación académica.Se plantea una propuesta que conjuga modelos de tutoría automatizada, retroalimentación inteligente y asignación óptima de recursos humanos, todo dentro de un marco institucional que respete la privacidad, la ética y el desarrollo integral del estudiante. A la par, se discute la necesidad de políticas que regulen el uso de IA generativa, asegurando que complemente y no sustituya el rol del tutor humano, promoviendo un aprendizaje profundo, reflexivo y socialmente relevante (Delgado y Martín, 2024; Lérias et al., 2024; López Chila et al., 2024). Lo que hoy tenemos enfrente no solo es la automatización de tareas intelectuales que requieren que los programas educativos se adapten y actualicen, sino que además sean inclusivos, pero será necesario abordar también las brechas tecnológicas en aumento ubicados en países en desarrollo como sucede en Ecuador, Bolivia y Perú en lugares marginales y de difícil acceso determinados por la cobertura de internet.
- 14 May 2025
- Published by Springer Nature
- p. 19-30
Augmented Reality in Teaching Technological Concepts: Emotions and Learning in Elementary School Students
- 14 May 2025
- Published by Springer Nature
- p. 19-30
Augmented Reality in Teaching Technological Concepts: Emotions and Learning in Elementary School Students
- 14 May 2025
- Published by Springer Nature
- p. 30-40
Use of the LLAMA2 Tool for the Early Detection of Bullying in Seventh-Grade Children
- 14 May 2025
- Published by Springer Nature
- p. 30-40
Use of the LLAMA2 Tool for the Early Detection of Bullying in Seventh-Grade Children