The swift increase in the use of MOOC learning, alongside the ever-increasing amount of instructional materials, has posed more difficulty to effectively reach useful information especially when it comes to the quality of teaching. Considering this, the present research presents a classification algorithm applicable to online vocal music course resources. This approach will improve the process of categorizing such materials through extracting important features and using a decision tree classifier. The experimental analysis was done on a vocal music course resources data set, which showed that the approach produces a classification error score of lower than 82 percent and a low F1 error score of less than 81 percent, indicative of uniform results. The method demonstrates an increase in classification accuracy compared to other approaches (4.18 to 6.45). Moreover, the algorithm also scored high in two other datasets. The results of the present study indicate that the suggested methodology is very successful in the process of classifying online vocal music educational materials, which can be greatly beneficial in terms of resource management in online vocal music classes.
