Recommended Teaching Resources for Ideological and Political Courses Based on Normalized Discounted Cumulative Gain

Nowadays, the evaluation of education quality has become a pressing concern globally, driven by the need to ensure that educational institutions provide students with knowledge. Traditional approaches for recommendation of teaching resources for ideological and political courses had faced several challenges which include lack of personalization and limited contextual understanding. Therefore, this research proposes Normalized Discounted Cumulative Gain (NDCG) for recommendation of teaching resources for ideological and political courses which is employed on Open Educational Resources (OER) dataset. Then, content is extracted by using Natural Language Tool Kit (NLTK) for annotated documents which helped in identifying key components. After that, features are selected by using Proximal Policy Optimization (PPO) which prevent overfitting. Next, the realization of Deep Reinforcement Learning (DRL) evaluated fine-tuning and enhanced student performance and instructor satisfaction with expected reward through Policy Gradient Method (PGM). Finally, NDCG evaluates both relevance and position of recommended data with updated gradient using distribution over the action space of literature courses. The proposed NDCG achieved better results in accuracy (98.22%) along with a recall (89.90%) and an Fl-score (95.45%) when compared with existing Bayesian Personalized Ranking Matrix Factorization (BPRMF).