Modeling students’ learning behavior for knowledge assessment is crucial for predicting the academic performance of students. This becomes a challenge in case of online teaching and learning scenarios since the students and teachers may not be physically present at the same geographical location in contrast to physical classroom teaching. Modeling of students’ learning patterns can lead to the proper prediction of students’ academic performance; thus, early identification of students at risk of academic failure is possible. The correct assessment of student knowledge can lead to corrective measures for students and fruitful feedback for instructors. In this paper, we have used the ensemble classifiers with various machine learning algorithms on the students’ knowledge dataset to predict the level of knowledge acquired by the students. This combination of the algorithms achieved better performance as compared to an individual algorithm. It was found that taking the classifiers which are independent and have the diversity of opinion leads to improved results.

对学生的学习行为进行建模以进行知识评估对于预测学生的学习成绩至关重要。在在线教学场景中，这成为一个挑战，因为与物理教室教学相比，学生和教师可能不在物理上位于同一地理位置。对学生的学习模式进行建模可以正确预测学生的学习成绩；因此，可以及早发现有学习失败风险的学生。对学生知识的正确评估可以为学生提供纠正措施，并为教师提供丰硕的反馈。在本文中，我们在学生的知识数据集上使用了具有各种机器学习算法的集成分类器，以预测学生获得的知识水平。与单个算法相比，算法的这种组合获得了更好的性能。已经发现，采用独立的并且具有观点多样性的分类器可以改善结果。