Study on the university students' satisfaction of the wisdom tree massive open online course platform based on...

Area of Science:

• Educational Technology
• Machine Learning
• Data Science

Background:

• Massive open online courses (MOOCs) on platforms like Wisdom Tree offer flexible learning, overcoming traditional educational barriers.
• Ensuring student satisfaction is crucial for the effectiveness and adoption of MOOCs.
• Traditional methods may not fully capture the nuances of student satisfaction in online learning environments.

Purpose of the Study:

• To develop and evaluate an intelligent algorithm for predicting university students' satisfaction with the Wisdom Tree MOOC platform.
• To achieve optimal classification accuracy and derive actionable decision rules regarding student satisfaction.
• To enhance the understanding of factors influencing student engagement and success in online courses.

Main Methods:

• A survey of 1028 information management students in Fuzhou city using electronic questionnaires.
• Principal component analysis identified six key variables: function, achievement, exercise, quality, richness, and interaction.
• An intelligent algorithm combining decision tree, support vector machine, and simulated annealing was proposed and compared against baseline models.

Main Results:

• The proposed algorithm (simulated annealing + support vector machine) achieved a classification accuracy of 99.58% on the training set.
• This significantly outperformed individual models like decision tree (92.21%), random forest (96.10%), k-nearest neighbor (95.67%), and support vector machine (97.29%).
• The algorithm successfully generated 11 decision rules offering insights into student satisfaction drivers.

Conclusions:

• The combined simulated annealing and support vector machine algorithm demonstrably enhances classification accuracy for MOOC student satisfaction.
• The derived decision rules provide valuable, data-driven information for educators and platform administrators.
• This intelligent approach offers a robust method for analyzing and improving online learning experiences.