Impact of an adaptive environment based on learning analytics on pre-service science teacher behavior and self-regulation

Learning analytics provides valuable data to inform the best decisions for each learner. This study, based on adaptive environment (AE) learning analytics dashboards, examines how instructor interventions affect student self-regulation abilities and academic performance. It identifies the self-regulation categories requiring the most support to correct learning paths. Little is known about how interventions in an AE can influence learners' self-regulation based on performance indicators, particularly in science education. The study included 95 Faculty of Education and the Department of Science students. Using a longitudinal clustering approach, researchers identified three unique self-regulated learning (SRL) profiles: oriented, adaptive, and minimally self-regulated learners. While the results showed that the learning analyses were useful in guiding the process of appropriate interventions through an adaptive environment for each student by providing indicators and raising the level of self-regulation for each group separately, the results also showed that there was no change in the classification of self-regulation into groups and that no students moved between groups. These findings highlight the complexity of SRL, suggesting that while interventions can impact engagement and behavior, they may not be sufficient to change the learner's underlying profile. In academic performance, statistically significant differences were found, with the oriented self-regulation group outperforming the adaptive and minimally self-regulated groups. The findings underscore the importance of learning analytics and their indicators for timely interventions in adaptive environments. Additionally, the AE was highly effective, offering students opportunities to review material, which improved their study techniques, test-taking strategies, and overall learning experience.