Research on recognition and intervention of behavior sequences in virtual museum learning

Area of Science:

• Educational Technology
• Virtual Learning Environments
• Museum Studies

Background:

• Virtual museums provide flexible learning opportunities, transcending physical and temporal constraints.
• Effective intervention strategies for optimizing virtual museum learning experiences remain underexplored.
• Understanding learner engagement is crucial for designing effective virtual educational tools.

Purpose of the Study:

• To investigate learner behavior and engagement in a virtual museum setting.
• To identify distinct learner types based on immersion levels.
• To develop and evaluate intervention strategies for enhancing virtual museum learning.

Main Methods:

• Utilized fuzzy c-clustering analysis for virtual museum learning behavior recognition.
• Employed lag sequential analysis (LSA) to analyze sequential learning behaviors.
• Applied random forest algorithm to identify key behavioral indicators for intervention.

Main Results:

• Identified four learner types: high, medium, low, and absent museum immersion.
• Categorized learners into middle & high and low & absent immersion groups for targeted interventions.
• Demonstrated significant learning state improvements in some learners after implementing intervention strategies.

Conclusions:

• Learner immersion levels in virtual museums can be categorized and analyzed.
• Targeted interventions, including support, guidance, and gamification, can effectively enhance virtual museum learning.
• This study provides a framework for optimizing virtual museum educational experiences through data-driven interventions.