Improving Effectiveness of Teaching Quality in Ideological and Political Courses Using K-Means Clustering Analysis

Nowadays, learning needs the practices that involves improving of teaching quality in ideological and political courses for education. Moreover, in the digitized era, life has become simpler with the increased information technology. However, the education department globally facing frequent challenges and complexities in leveraging technology for enhancing teaching and learning experiences that ensure equitable access to quality education, and prepare students for an increasingly digital future. Therefore, this paper proposes a clustering algorithm to evaluate the effectiveness of ideological and political courses. The EdX dataset, comprising 976 courses, is used to collect information. The Convolutional Neural Network (CNN) method is used to extract the relevant feature and the Multiverse Optimization (MVO) algorithm is applied to selecting the relevant features with input from extracted features. Then, K-Means Cluster Analysis groups similar courses, and the Optimization and Improvement of teaching quality by K-Means Algorithm refines the clustering model. The proposed K-Means algorithm enables the evaluation of teaching effectiveness, allowing for the identification of successful strategies and areas for improvement. The performance of proposed K-Means clustering evaluated with the various metrics such as average error of 60.43%, Mean Percentage Error (MPE) of 52.78<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> with the Edx dataset.