Recomendaciones para juegos serios basadas en analíticas de aprendizaje

Learning Analytics in Serious Games (SG) are a key instrument for capturing information about the competencies a player demonstrates during interaction. Nevertheless, these metrics alone are insufficient to fully automate the teaching–learning process. Hence the need to equip SGs with adaptive systems that, based on the data collected, can deliver personalized recommendations and immediate feedback. In this way, each game session becomes not only a ludic experience but also a guided learning space that helps the student approach the desired knowledge state.The general objective of this research is to build a theoretical–practical framework that enables the incorporation of such recommendations into an SG, drawing on performance metrics obtained through Learning Analytics. The specific objectives are: (1) to design and implement an adaptive system capable of using Artificial Intelligence to generate data-driven recommendations; and (2) to conduct a field study that analyzes the feasibility and integration possibilities of this process in a concrete game.