LACLO Sesión 3: Analítica de datos en educación (2)
- Learning Objects and Youtube: an analysis of videos and their categories. Brasil
- Autor(es): Henrique Carvalho, Cristiano Pitangui, Eduardo Trindade, Luciana Assis and Alessandro Vivas
- Abstract: Technology has contributed to the Educational area by providing numerous digital content. However, the excess of available materials makes its selection very tiring and frustrating. In order to overcome this difficulty Learning Objects are used during technology learning. The online video-sharing platform YouTube offers several Learning Objects and has more than 2 billion monthly accesses, being widely used for learning purposes. This work presents an analysis of the search engine for educational content videos from YouTube. Results point out that, for educational content, the categorization provided by the platform is generally not assertive.
- Expositor(a): Henrique Carlos Fonte Boa Carvalho
- Evaluation of the impact of Learning Objects in Digital TV. Ecuador
- Autor(es): Lourdes Illescas-Peña and Carlos Villie Morocho
- Abstract: The learning objects have been used in educational settings with great success. Different definitions have been adapted to the teaching-learning processes in which educational resources are gaining strength each time. In another context, digital television has developed communication platforms that allow users to interact with tv content. This work presents a methodological adaptation in the development of learning objects to apply them in a Digital TV format. A usability assessment was applied to users with a varied group in controlled conditions. In addition, an acceptance quality evaluation was carried out on a group of university students. Finally, the results showed that 62.5% of users were able to complete all the tasks assigned in the learning objects and 66.67% showed that they would be willing to use this type of application.
- Expositor(a): Lourdes Illescas
- Relationship between social loneliness and creative ability in art students in Covid-19 times. Perú
- Autor(es): Olger Gutierrez Aguilar, Raúl Felipe Velarde Sánchez, Edgar Alcides Chauca Quispe, Raúl David Oblitas Flores, Freddy Alberto Chambi Quispe and Erika Giuliana Paredes Delgado
- Abstract: El propósito de este estudio fue probar la relación existente entre la soledad social y la capacidad creativa, en estudiantes de arte de tres regiones del sur del Perú, esto debido a que existe una serie de artistas de la pintura a lo largo de la historia universal, que han alcanzado niveles excepcionales de creatividad en contextos de soledad social, el estudio, pretende validar un modelo de relación entre estas dos variables, teniendo en cuenta el contexto, caracterizado por un aislamiento social y una mediación con las tecnologías en la práctica educativa e-learning utilizando el LMS – Moodle. El estudio comprende de dos fases, en primer lugar, un análisis factorial exploratorio mediante el SPSS, en segundo lugar, para el análisis confirmatorio, se utilizó la metodología PLS-SEM, que es un método multivariante llamado, Modelación de Ecuaciones Estructurales con Mínimos Cuadrados Parciales. El modelo se validó con una muestra de 216 estudiantes de las regiones de Arequipa, Tacna y Cusco. El estudio revelaría una relación casi inexistente entre las variables de estudio, como son la soledad social y la capacidad creativa. Con los resultados obtenidos, obligaría a repensar que el artista de la pintura, no necesita de la soledad social para involucrarse en un proceso creativo.
- Expositor(a): Olger Albino Gutiérrez Aguilar
- Prediction analysis of student dropout in a Computer Science course using Educational Data Mining. Brasil
- Autor(es): Alexandre Gomes da Costa, Emanuel Queiroga, Cristian Cechinel, Tiago Thompsen Primo and Júlio C. B. Mattos
- Abstract: Educational Management Systems store a large amount of data from interaction of not only students and professors but also of students and the educational environment. Analyze and find patterns manually from a huge amount of data is hard, so Educational Data Mining (EDM) is widely used. This work presents a model that can predict the student's risk of dropout using data from the first three semesters attended by Computer Science Undergraduate students (N=1516) from Federal University of Pelotas. This work uses the CRISP-DM methodology e data from Cobalto Management System. The results are shown for three algorithms and for the RandomForest algorithm a precision of 95.12\% and a Recall of 91.41\% is presented indicating that it is possible to use a prediction model using only the data from the first three semesters of the course.
- Expositor(a): Tiago Primo
- Predicción temprana de abandono en cursos online mediante Redes Neuronales Artificiales. Ecuador
- Autor(es): Hermel Santiago Aguirre Montaño and Ma. Carmen Cabrera-Loayza
- Abstract: Los crecientes avances tecnológicos, han creado la necesidad de implementar nuevos métodos de enseñanza, de ahí nace la educación en línea, la cual se define como la educación mediada por un entorno de aprendizaje virtual. Este tipo de educación, al no ser una educación tradicional y presencial, dificulta el seguimiento de los estudiantes obteniendo altas tasas de abandono. El uso de redes neuronales artificiales ayuda a predecir el comportamiento de los estudiantes utilizando datos históricos y obtener resultados en etapas tempranas de su desempeño estudiantil, permitiendo a los docentes definir estrategias para abordar la alta tasa de deserción estudiantil y tomar acciones tempranas para evitarlo.
- Expositor(a): Hermel Santiago Aguirre Montaño