Hybrid Feature Extraction Model to Categorize Student Attention Pattern and Its Relationship with Learning

The increase of instructional technology, e-learning resources, and online courses has created opportunities for data mining learning analytics in the pedagogical domain. A large amount is obtained from this domain that can be analyzed interpreted so educators understand students’ attention. In a classroom where students have their own computers front them, it important instructors to whether are paying We collected on- off-task analyze attention behaviors students. Educational extracts hidden information educational records, we using classify student patterns. hybrid method used combine various techniques like classifications, regressions, or feature extraction. our work, combined two extraction techniques: principal component analysis linear discriminant analysis. Extracted features by kernel support vector machine (SVM) Classification results compared with SVM. Our achieved best terms accuracy, precision, recall, F1, kappa. Also, correlated learning. Here, corresponds tests final course grade. For determining correlation between grades attention, Pearson’s coefficient p-value were used.