Research on Eye Movement Feature Mining to Represent Learning Engagement in the Process of Natural Reading

Learning engagement is an important factor affecting the effect of natural reading, and eye movement characteristics, as an important indicator reflecting the cognitive process, play a crucial role in understanding learning engagement in the natural reading process. In this study, the data collected by eye-tracking technology and the learning engagement scale filled in by the subjects at the end of the study were combined to classify the learning engagement of the learners in the natural reading process, classify, statistically and cluster analyse the eye-movement data in combination with different degrees of engagement, and display the results of the analyses in a visual presentation, which concluded that there is a moderate correlation between the number of gaze points and the duration of gaze and learning engagement respectively, and there is also a certain correlation between the sweeping mode and learning engagement, and there is also a certain relationship between the sweeping mode and learning engagement. It was found that the number of gaze points and gaze duration were moderately correlated with learning engagement, and that there was also a relationship between scanning mode and learning engagement, which is expected to provide personalised intervention and support services for teachers and teaching administrators.