A Knowledge-Based Filtering Recommendation System for Personalized Teaching Resources in Ideological and Political Theories in All Courses in English Courses

Nowadays, the rapid growth of Information Technology (IT) advancements, various network sciences and personalized learning has become a new trend in modern education. However, a multi-dimensional evaluation feedback system is lacking on learning in school ideological and political education, and failing to provide sufficient carrier support to enhance educational effectiveness. Hence, this research provides a Knowledge-Based Filtering Recommendation System for Personalized Teaching Resources in Ideological and Political Theories teaching in all courses English Courses (KBF-PTRIP). This research has taken input data from Edx dataset and given to content extraction as user input. Here, the user inputs are analyzed and the similarity between learning resources and individual learners is calculated to provide the prediction score. Then, Term Frequency-Inverse Document Frequency (TF-IDF) method is exploited to select best features with the highest prediction score. Finally, the personalized teaching resources are recommended to the user with the help of Knowledge-Based Filtering (KBF) recommender. From the results, the proposed KBF- PTRIP model achieved best results in terms of accuracy 98.82%, recall 98.73% and F1 score 96.35% respectively by comparing with the existing Primary and Secondary Education Resource System by using Collaborative Filtering (PSERS-CF) model.