Optimization Algorithm for Ideological and Political Curriculum Environment in Colleges Using Data Analysis and...

Area of Science:

• Educational Technology
• Data Science
• Network Science

Background:

• Big data (BD) analysis offers new approaches for university ideological and political education (IPE).
• Intelligent teaching systems require enhanced intelligence and personalization.
• Complex networks present unique challenges for optimization algorithms.

Purpose of the Study:

• To design and implement an intelligent teaching system leveraging big data.
• To enhance the Teaching-Learning Based Optimization (TLBO) algorithm for complex network characteristics.
• To improve the effectiveness of university IPE through data-driven insights.

Main Methods:

• Utilized association rule mining from data mining for system components.
• Implemented population initialization and neighborhood-based search operators for diversity.
• Optimized the TLBO algorithm with a neighborhood search strategy for complex networks.

Main Results:

• The optimized TLBO algorithm achieved an average modularity value of 0.5238 on real-world datasets.
• The algorithm demonstrated strong performance in identifying community problems.
• The system design successfully integrated big data analysis for personalized education.

Conclusions:

• The proposed system effectively enhances university IPE through intelligent, personalized teaching.
• The optimized TLBO algorithm is a robust tool for community detection in complex networks.
• Big data analytics provides a valuable framework for advancing educational methodologies.