Learning Analytics in Mathematics Teacher Education At The Ceará State University

Objective: This research sought to develop a statistical model that helps to predict students at risk of not being successful in the subjects of the Undergraduate Mathematics Teacher Education Program, in distance education modality, at the Open University System of Brazil / Ceará State University (UAB/UECE). Theoretical Framework: Teacher education in Brazil faces several problems highlighted by studies. Low graduation rates require urgent measures to change this situation with quality. Learning analytics emerges as an option to improve student learning, reducing the risk of academic failure. Method: A statistical method was used for this research. It was decided to use data from the students who entered the University in 2009, in poles of two cities. The students’ access and interaction data in the Moodle environment and final performance grades in the subjects were collected. In data analysis, binary logistic regression was used. Results and Discussion: The regression model created has a high accuracy, with statistically significant predictor variables and high success percentages to predict failure and non-failure. Research Implications: This research serves as a basis for the creation of tools for real-time application of learning analysis, favoring the observation of the performance of the predictive model for the program studied. Originality/Value: Learning analytics is a new, but very promising field of research. This research is one of the pioneers on this topic in Brazil, carried out by researchers in the education area.