Personalized adaptive online learning analysis model based on feature extraction and its implementation

Modern people pay more and more attention to individualized learning. The traditional teaching method is to explain all the learning contents in a unified way. The setting of teaching contents and courseware are relatively fixed, which can not provide individualized choices for different learners. The core of the adaptive learning system based on feature extraction studied in this paper is that the system recommends personalized learning content for learners according to the learner model. To establish and personalize the self-adaptive learning engine mechanism, a personalized self-adaptive learning content presentation based on clustering is proposed. This study can analyze the data of students’ learning behavior and knowledge mastery, recommend reasonable learning path and learning resources with appropriate difficulty, give timely and accurate feedback to students’ learning effect, provide personalized service intervention, and promote teaching and learning.