Educational data can be analyzed to inform interventions that improve the learning process. Visualization systems can improve course content and provide personalized feedback. Adaptive systems allow automatic decisions based on student data. Prediction tools can forecast learning gains, certificates earned, social engagement, cheating, and system usage based on personality. The SHEILA project studied policy, adoption, staff and student perspectives, and developed a framework for institutional strategies around educational data. The LALA project builds capacity in Latin America for creating and customizing learning analytics tools to enhance academic decision-making.
«Intervención y actuaciones en base a datos educativos», por Pedro J. Muñoz Merino, profesor titular de la UC3M
1. Intervention and actions
based on educational data
Pedro J. Muñoz-Merino
Universidad Carlos III de Madrid
Twitter: @pedmume
Email: pedmume@it.uc3m.es
2. Introducción
Educational Data -> analyse ->
interventions-> improvement of the
learning process
Technical: tools and services
Institutional adoption
2
5. Automatic decissions: Adaptive
systems
5
PJ Muñoz-Merino, R. Gonzalez Novillo, C Delgado Kloos: "Assessment of
skills and adaptive learning for parametric exercises combining knowledge
spaces and item response theory. Appl. Soft Comput. 68: 110-124 (2018)
6. Prediction about the future
• Prediction about
• Learning gains
• Certificate earners
• Social activity
• Cheating
• System behaviours
• Personality
6
10. LALA project
10
Build capacity in Latin American higher education institutions to
create, adapt, implement learning analytics tools to improve the
academic decision processes
https://www.lalaproject.org/