Naïve Bayesian Integrated Apriori Algorithm with Association Rule Mining for the Quality Monitoring of Classroom Teaching in Universities

Evaluating the classroom teaching with the conventional methods is no longer adequate to fulfil the requirements of education reform. To address the less efficient evaluation systems of quality monitoring in classroom teaching, the proposed research used data mining technology. The Naïve Bayesian integrated Improved Apriori Algorithm with Association Rules Mining (NB-IAARM) is proposed in this research, to improve accuracy and efficiency of teaching evaluations. Initially, an open source data of 1000 university professors is considered with various attributes and pre-processed to obtain the error-free data. The Improved Apriori –Association Rules Mining (IAARM) method is used to mine association rules, which show patterns and correlations in the data. The weighted Naïve Bayesian (NB) model identifies and evaluates teaching quality by weighting parameters such as student feedback and teacher performance. This improves decision-making and enables university administrators to effectively monitor and improve teaching. Results showed better quality monitoring in term of minimum support of 3.89, minimum confidence of 42.85, and model accuracy with 98.63% when compared to the traditional approaches such as Support Vector Machine (SVM) and Random Forest (RF).