Personalized Online Learning Resource Recommendation Based on Artificial Intelligence and Educational Psychology

Area of Science:

• Educational Technology
• Artificial Intelligence in Education
• Learning Analytics

Background:

• Remote education presents challenges in providing tailored learning resources.
• Personalized recommendations are crucial for improving student engagement and outcomes.
• Integrating AI with educational psychology offers a novel approach to resource allocation.

Purpose of the Study:

• To design an effective personalized online learning resource recommendation scheme for remote education.
• To leverage Artificial Intelligence (AI) and educational psychology for improved student learning outcomes.
• To develop a recommendation algorithm that adapts to individual student abilities and preferences.

Main Methods:

• Analyzing student learning behaviors to assess learning ability and classify student identities.
• Extracting features of learning resources, including difficulty level.
• Proposing a LinUCB-based recommendation algorithm with a personalized exploration coefficient based on student ability and attention scores.

Main Results:

• The proposed scheme successfully identifies appropriate learning resources matching student abilities and personalized demands.
• Experimental results demonstrate superior performance compared to existing state-of-the-art recommendation schemes.
• The system accurately recommends online learning resources, reducing exploration risks and controlling difficulty levels.

Conclusions:

• The developed AI-driven scheme effectively provides personalized learning resources in remote education settings.
• The approach balances resource difficulty with student ability, fostering potential and improving learning outcomes.
• This personalized recommendation system enhances the efficacy of online learning by catering to individual student needs.