Data Generation Strategies for the Application of Adaptive Learning Analytics

In increasingly data-rich environments, disciplines such as Adaptive Learning Analytics (ALA) are growing in scope, reach and importance. However, inadequate or insufficient data is frequently encountered. This paper proposes a series of data generation strategies for the application of ALA by analyzing data from successful cases and literature. The data that could be obtained from students were identified and categorized into online behavior, academic, personal, face-to-face behavior and test for personalization. Subsequently data used in successful cases were analyzed and possible adaptive possibilities to be considered were proposed. In addition, a prototype guide for educators is presented, detailing a step-by-step process for implementing these strategies in course design. The guide includes the definition of objectives and context, curriculum content design, implementation, monitoring, evaluation, and adaptation of the course. Finally, an example of the data that could be generated through these strategies is presented, emphasizing the need to selectively choose components and determinants to prevent exponential growth in the adaptation rate. With the results of the research, it can be concluded that through defined strategies, teachers can generate data that allows the implementation of ALA applications.