Ideological and Political Theories Teaching in All Courses Learning System using user-to-user -based Collaborative Filtering Algorithm

Recently, process in education and classroom reform has emerged lately as a result of the growth, integration, and instructional resources of information technology. However, addressing the issues in ideological academic programs of educational system of colleges and universities, which was inconsistent and ineffectual. Therefore, this research suggested using the User-to-User -Based Collaborative Filtering Algorithm (UUBCFA) to evaluate the effectiveness of the career planning teaching model in diverse academic contexts and addressing these existing issues. Initially, the precise path guidance and real-time recommendation are obtained by using the sparsity of the data. An ideological and political course suggestion design serves the role of ensuring that the system operates in accordance with the established protocol. Consequently, the proposed UUBCFA discovers users with similar likes, recommends courses, and uses peer similarity to improve recommendation accuracy. According to the results, it clearly illustrated that the suggested UUBCFA methodology have achieved better performance in accuracy of 99.89% and precision of 99.95% which is comparatively higher than existing models such as Intellectual Cognitive-Inspired Computing (ICIC), Deep Attention-based Parallel Dual-channel Model (DAPDM) and Massive Open Online Courses (MOOCs) respectively.