Intelligent recommendation system for College English courses based on graph convolutional networks

Area of Science:

• Educational Technology
• Artificial Intelligence
• Computer Science

Background:

• The proliferation of English courses due to international communication has led to information overload.
• This overload negatively impacts the effectiveness of recommended English courses and overall teaching performance.

Purpose of the Study:

• To develop an intelligent recommendation system for college English courses.
• To mitigate the negative effects of information overload on English course selection and learning outcomes.

Main Methods:

• A graph convolutional neural network (GCNN) model was designed incorporating college English course texts, student majors, and English proficiency.
• The GCNN model utilizes a proximity comparison strategy within the college English learning context.
• Attention mechanisms were integrated to refine feature representation and enhance recommendation accuracy for English skills.

Main Results:

• The proposed GCNN model demonstrated superior performance compared to existing college English course recommendation methods.
• Experimental data validated the effectiveness of the attention-enhanced GCNN in providing accurate course recommendations.
• The system successfully integrates multi-layer attention modeling for personalized English skill development.

Conclusions:

• The developed graph convolutional neural network model effectively addresses information overload in college English course recommendations.
• The integration of student data and learning strategies significantly improves recommendation quality.
• This approach offers a promising solution for enhancing college English education through intelligent systems.