Contributions to learning analytics focused on assessment and self-regulated learning

  1. Liz Domínguez, Martín
Dirixida por:
  1. Manuel Caeiro Rodríguez Director
  2. Martín Llamas Nistal Director

Universidade de defensa: Universidade de Vigo

Fecha de defensa: 10 de marzo de 2023

  1. Manuel J. Fernández Iglesias Presidente
  2. Ainhoa Izaro Álvarez Arana Secretario/a
  3. Antonio José Nunes Mendes Vogal
  1. Enxeñaría telemática

Tipo: Tese


In recent years, the data mining and analysis disciplines have seen an important increase in relevance, both for enterprises and in research. The set of techniques belonging to these knowledge fields have applications in a very wide variety of contexts, among which is the educational one. The particularizations of these two disciplines for the educational area are known as educational data mining (EDM) and learning analytics (LA). The latter is the main topic of this project. They are defined as a series of techniques for the measurement, acquisition, analysis and representation of data about students and their contexts, with the objective of understanding and optimizing learning and the environments in which it occurs. The proposed research project will explore the possibilities that learning analytics can offer with the goal of improving the learning process in university courses, paying special attention to assessment tasks and self-regulated learning (SRL) approaches. In order to do this, student data will be analyzed. This data can be obtained from learning management systems (LMS), which are commonly used in current university courses. As a result of analysis, indicators of student progress, as well as performance predictions, will be obtained. These results can be useful for instructors to identify struggling students at an early stage, as well as providing statistics so that the students themselves can effectively assess their own progress. This project fits into an important research category inside the education technologies field. The main goal will be to propose original contributions to the learning analytics discipline, achieving a positive impact within the reaserch community in this knowledge field.