Investigating features that play a role in predicting gifted student engagement using machine learning: Video log and self-report data.

This study aims to develop a predictive model for predicting gifted students' engagement levels and to investigate the features that are important in such predictions. Features reflecting students' emotions, social-emotional learning skills, learning approaches and video-watching behaviours were used in the prediction models. The study group consisted of 36 gifted students between the ages of 12 and 14 who attended an information technologies course, where students engaged with Arduino-based learning tasks. Data related to only one task were analysed. Prediction models were developed using different machine learning algorithms, and information gain scores were used to investigate important features in the prediction models. The results show that all prediction models achieved a higher classification accuracy than the base model. The highest classification accuracy (83%) was achieved with the Support Vector Machine (SVM) algorithm. Students' self-reported emotions while performing the task were found to be the most important feature in predicting their level of engagement. Other important features in predicting engagement level were the students' social-emotional learning skills, deep and surface learning approaches and their video-watching behaviours. As a result, it was found that the engagement level of gifted students could be predicted with high accuracy. These results can be used to predict students' engagement levels and to develop interventions for low-engaged students. The obtained results are discussed within the scope of emotion-aware learning design and social-emotional learning. [ABSTRACT FROM AUTHOR]