Research on Recommendation of Ideological and Political Course Resources Using Nesterov Accelerated Gradient Based Deep Neural Network

An integration of ideological as well as political course learning in educational backgrounds are important in estimating the people's ethics, responsibilities and their values. The course recommendation method motivates the developments of understandable, civically and socially conscious involved students through combining the political and ideological courses in the educational systems. Thus, this research proposes the Deep Learning (DL) approach assisted estimation framework to assess the course learning of ideological and political and recommendation by Nesterov Accelerated Gradient based Deep Neural Network (NAG-DNN). The proposed method with student's feedback, digital course learning activities, classroom interactions are considered for an effective analysis of learning outcomes. The collected dataset is pre-processed through standardization, inappropriate entry removal as well as noise removal to guarantee the consistency and improve the model performance. The comparative analysis demonstrates that the proposed NAG-DNN approach attains the maximum accuracy of 99.21 %, precision of 99.32 % and recall of 99.01 % as associated with DNN approach. This finding demonstrates that proposed method attains effective and robust estimation, providing significant insights for enhancing ideological and political course learning quality and to recommend various courses.