Temporal Dynamics of Meta-Awareness of Mind Wandering During Lecture Viewing: Implications for Learning and Automated Assessment Using Machine Learning.

Remote learning settings require students to self-regulate their behavioral, affective, and cognitive processes, including preventing mind wandering. Such engagement in task-unrelated thoughts has a negative impact on learning outcomes and can occur with or without students' awareness of it. However, research on the meta-awareness of mind wandering in education remains limited, predominantly relying on self-report measures that capture discrete information at specific time points. Therefore, there is a need to investigate and measure temporal dynamics in the meta-awareness of mind wandering continuously over time. This study examined the temporal patterns of 15 mind-wandering and meta-awareness probes in a sample of university students (N = 87) while they watched a video lecture. We found that the majority (60%) of mind wandering occurred with meta-awareness. Cluster analysis identified five distinct thought sequence clusters. Thought patterns dominated by unaware mind wandering were negatively associated with fact- and inference-based learning, whereas persistent aware mind-wandering patterns were linked to reduced deep-level understanding. Initial exploration into predictive modeling, based on eye gaze features, revealed that the models could distinguish between aware and unaware mind-wandering instances above the chance level (macro F1 = 0.387). Model explainability methods were employed to investigate the intricate relationship between gaze and mind wandering. It revealed the importance of eye vergence and saccade velocity in distinguishing mind-wandering types. The findings contribute to understanding mind-wandering meta-awareness dynamics and highlight the capacity of continuous assessment methods to capture and address mind wandering in remote learning environments. Educational Impact and Implications Statement: Learners often experience thoughts that are unrelated to the learning task, a phenomenon known as mind wandering. They are aware of these thoughts sometimes and are sometimes unaware of them. This study sheds light on learners' attention during online learning, specifically when watching a video lecture. We collected data from 87 university students by repeatedly interrupting them to ask where their attention was directed, gathering their reports on both aware and unaware mind wandering, and recording their gaze using eye trackers. Thought patterns dominated by unaware mind wandering were negatively associated with fact- and inference-based learning, whereas persistent aware mind-wandering patterns were linked to reduced deep-level understanding. Crucially, these internal experiences were reflected in students' gaze patterns, suggesting that eye-tracking and machine learning could help identify when a student's mind is wandering. This advancement holds great promise for educators aiming to create more engaging remote learning experiences, as it allows to react to in different ways, potentially addressing different underlying causes and for researchers dedicated to enhancing our comprehension of student attention dynamics. [ABSTRACT FROM AUTHOR]