Integration of Collaborative Filtering Into Naive Bayes Method to Enhance Student Performance Prediction

Literature Review

Advances in information and communication technologies have facilitated the widespread use of virtual learning environments as tools in teaching and learning processes. Virtual platforms generate a large volume of educational data, the analysis of which helps to improve education and reduce dropouts and dismissals in distance learning.

The integration of collaborative filtering methods with naive Bayes represents an innovative approach to enhancing the accuracy of predicting student performance. These methods can be used to forecast students' academic achievements, which is an important tool in educational psychology and learning theory. Research shows that collaborative filtering methods, such as collaborative filtering regression and matrix factorization, are successfully applied to predicting students' academic performance by considering similarities based on their grades in previous courses (Bydžovská, 2015; Adán-Coello & Tobar, 2016).