Ir al contenido

Documat

Selección efectiva de características en el desempeño docente por medio de técnicas de inteligencia artificial

  • Omar D. Castrillón [1] Árbol académico ; Paulo Novais [2] Árbol académico
    1. [1] Universidad Nacional de Colombia

      Universidad Nacional de Colombia

      Colombia

    2. [2] Universidade do Minho

      Universidade do Minho

      Braga (São José de São Lázaro), Portugal

  • Localización: Formación Universitaria, ISSN-e 0718-5006, Vol. 18, Nº. 4, 2025, págs. 85-96
  • Idioma: español
  • DOI: 10.4067/s0718-50062025000400085
  • Títulos paralelos:
    • Effective feature selection in professor performance using artificial intelligence techniques
  • Enlaces
  • Resumen
    • español

      El objetivo de esta investigación es identificar las características más efectivas que influyen en el desempeño docente. Se adapta una encuesta a una universidad en la región central de Colombia. La encuesta incluye una variable dependiente, denominada desempeño docente, y 18 variables independientes. Se identifican las variables independientes más influyentes sobre la variable dependiente y se evalúa la efectividad de estas variables mediante la plataforma de minería de datos y aprendizaje automático WEKA. Utilizando un proceso por pliegues de validación cruzada 50%-50% (cross validation folds), se determina con una efectividad superior al 86% que las variables más influyentes son: se aprende con profundidad, tiempo suficiente para asesorar u orientar, promoción de conexiones con otras materias o contextos, fomenta la argumentación y reflexión crítica, y adapta los métodos de enseñanza. Se concluye que el desempeño docente está asociado al comportamiento de 5 variables y se destaca que la presente investigación puede aplicarse en diversos entornos educativos, investigativos y culturales

    • English

      The objective of this research study is to identify the most effective characteristics that influence teaching performance. A survey is adapted to a university in the central region of Colombia. The survey includes a dependent variable, called teaching performance, and 18 independent variables. The most influential independent variables on the dependent variable are identified and the effectiveness of these variables is evaluated using the data mining and machine learning platform WEKA. Using a 50%-50% cross-validation folds process, it is determined with an effectiveness of over 86% that the most influential variables are: learning depth, sufficient time for advising or guiding, promoting connections with other subjects or contexts, encouraging argumentation and critical reflection, and adapting teaching methods. It is concluded that teaching performance is associated to five variables, and it is highlighted that the present research study can be applied in diverse educational, research, and cultural environments.

  • Referencias bibliográficas
    • Al-kfairy, M., Ahmed, S., y Khalil, A., Factors Impacting Users’ Willingness to Adopt and Utilize the Metaverse in Education: A systematic...
    • Aucejo, E., y Wong, K., The Effect of Feedback on Student Performance, https://doi.org/10.1016/j.jpubeco.2024.105274, Journal of Public Economics,...
    • Bakhadirov, M., Alasgarova, R., y Rzayev, J., Factors Influencing Teachers’ Use of Artificial Intelligence for Instructional Purposes, IAFOR...
    • Cai, B., y Wang, D., Prediction of Psychological Intervention for College Students in Digital Entertainment Media Environment Based on Artificial...
    • Castrillón, O., Sarache, W., y Ruiz-Herrera, S., Predicción del Rendimiento Académico por Medio de Técnicas de Inteligencia Artificial, doi:...
    • Castrillón, O., Sarache, W., y Ruiz-Herrera, S., Predicción de las Principales Variables que conllevan al Abandono Estudiantil por medio de...
    • Castrillón, O., La Preferencia de un Docente por parte de los Estudiantes: Análisis de su Elección desde la Minería de Datos, http://dx.doi.org/10.4067/S0718-50062024000400161,...
    • Castrillón, O., Análisis y predicción del desempeño docente por medio de encuestas estudiantiles: búsqueda de relaciones desde la minería...
    • Chen, L., Immersive Artificial Intelligence Technology Based on Entertainment Game Experience in Simulation of Psychological Health Testing...
    • Dol, S., y Jawandhiya, P., Classification Technique and its Combination with Clustering and Association Rule Mining in Educational Data Mining-A...
    • Feng, G., y Fan, M., Research on Learning Behavior Patterns from the Perspective of Educational Data Mining: Evaluation, Prediction and Visualization,...
    • Gaudioso, E., Montero, M., y Hernández-del-Olmo, F., Supporting Teachers in Adaptive Educational Systems Through Predictive Models: A Proof...
    • Kahandal, P., Kahandal, S., y otros tres autores, Teacher Performance Prediction Using Machine Learning, DOI: 10.48175/IJARSCT-15762, International...
    • Krzysztof, R., Exploring the Influence of Student Emotions and Professor Behaviour on Course Ratings: A Quantitative Analysis, https://doi.org/10.5281/zenodo.7097271,...
    • Mahmud, A., Hossan, A., y otros tres autores, Adoption of ChatGPT by University Students for Academic Purposes: Partial Least Square, Artificial...
    • Martinez-Moreno, J., y Petko, D., What Motivates Future Teachers? The Influence of Artificial Intelligence on Student Teachers’ Career Choice,...
    • Ma, S., y Lei, L., The Factors Influencing Teacher Education Students' Willingness to Adopt Artificial Intelligence Technology for Information-Based...
    • Mohammadpour, E., y Maroofi, Y., The disparity between performance-based and self-reported measures of TPACK: Implications for teacher education...
    • Nachouki, M., Mohamed, E., y otros dos autores, Student Course Grade Prediction Using the Random Forest Algorithm: Analysis of Predictors’...
    • Ordoñez-Avila, R., Salgado, N., y otros dos autores, Data Mining Techniques for Predicting Teacher Evaluation in Higher Education: A Systematic...
    • Sarker, S., Kumar, M., y otros dos autores, Analyzing Students’ Academic Performance Using Educational Data Mining, https://doi.org/10.1016/j.caeai.2024.100263,...
    • Schools, J., We Just Wanna Learn Too: Student-Athletes Perceptions of Stereotyping, Care, and Academic Performance, Johnson University ProQuest...
    • Sekyi, B., Arthur, F., y otros tres autores, Preservice Teachers’ Behavioural Intention to Use Artificial Intelligence in Lesson Planning:...
    • Shaofeng, W., Zhuo, S., y Ying, C., Effects of Higher Education Institutes' Artificial Intelligence Capability on Students' Self-Efficacy,...
    • UNAL., Universidad Nacional de Colombia, https://edificando.unal.edu.co/portal (2024) [ Links ]
    • Valencia, M., Correa, J., y Díaz, F., Métodos Estadísticos Clásicos y Bayesianos para el Pronóstico de Demanda. Un Análisis Comparativo, https://doi.org/10.15446/rev.fac.cienc.v4n1.49775,...
    • Wang, C., Li, T., y otros seis autores, Application of Artificial Intelligence for Feature Engineering in Education Sector and Learning Science,...
    • Witten, I., Frank, E., y otros dos autores, Data Mining Practical Machine Learning Tools and Techniques, Morgan and Kaufman publication (Elsevier),...
    • Yuan, Y., Influencing Factors and Modeling Methods of Vocal Music Teaching Quality Supported by Artificial Intelligence Technology, International...
    • Zhao, C., y Yu, J., Relationship Between Teacher’s Ability Model and Students’ Behavior Based on Emotion-Behavior Relevance Theory and Artificial...
    • Zong, Z., Design and Realization of Data Mining Simulation and Methodological Models, https://doi.org/10.1016/j.jksus.2023.102964, Journal...
Fundación Dialnet

Mi Documat

Opciones de artículo

Opciones de compartir

Opciones de entorno