This study seeks to understand the effects of a personalized learning platform, which applied an open learner model with self-regulation and AI-enabled data visualization features, on students' self-regulated learning strategies used and behavioral patterns during their self-directed online learning process. Results were based on a self-regulated learning scale and a prior knowledge test from 182 university students and supplemented with students' system logs to understand their behavioral patterns while interacting with the personalized learning platform. It showed that the combined self-regulation and data visualization features (dual features) improve student performance via self-regulated activities of goal setting and help-seeking. In addition, the dual features improve students' self-regulation behavior of self-assessment and motivate their self-directed learning, reflected by more frequent review of learning content after checking their performance progress charts. Therefore, this study showed that combining self-regulation strategies with data visualization can effectively enhance self-regulated learning behaviors, in which students were able to govern their learning from the feedback provided through data visualization. The results also inferred that the graphical representation using a radar chart provides an intuitive interface with low cognitive affordance to interpret learning analytics data.
- Inicie sesión para enviar comentarios