Research on E-learning Behavior Evaluation of Students Based on Three-way Decisions Classification Algorithm
Abstract
With the popularization and application of E-learning platform, it is feasible to collect learning behavior data of students, which provides data basis for analyzing the knowledge and rules contained in learning process of students. At present, the common e-learning platform only realizes the simple statistics and display function for the data, and does not do further in-depth calculation. The data observed by educators are still superficial learning phenomena, and they cannot see the learning rules behind the appearance. It is difficult to effectively guide students, change their learning routes and feedback teaching strategies. In view of this, the main characteristics of learning behavior deeply mined from learning activities and learning evaluation, and the important data feature items affect E-learning effect obtained. Three decision classification algorithms applied to establish prediction and evaluation model for students with learning behavior risk. The overall accuracy of model test is in line with the expectation. This provides a practical application modeling method for further implementation of personalized learning service.