Knowledge tracing for adaptive learning in a metacognitive tutor

Abstract Adaptive learning is provided in intelligent tutoring systems (ITS) to enable learners with varying abilities meet their expected outcomes. Despite the personalized afforded by ITSes using adaptive learning, are still susceptible shallow learning. Introducing metacognitive teach how be aware of knowledge can deeper However, on top cognitive lead unsustainable loads. Using inputs for tracing was explored managing Hidden Markov models (HMM) and artificial neural networks were used train a synthetic dataset created from predetermined learner personas. The compared without said inputs. performed better than standard while following intuitions. This indicates that combining viable option improving an important finding since online which demands skills, becoming popular various topics, including those challenging even immediate teacher assistance.