Online Education Satisfaction Assessment Based on Machine Learning Model in Wireless Network Environment.

Area of Science:

• Educational Technology
• Computer Science
• Data Science

Background:

• Online education has rapidly advanced due to technological and societal shifts.
• However, rapid growth has outpaced regulatory systems, leading to suboptimal user experience and satisfaction.
• Establishing robust user satisfaction models is crucial for service quality improvement and industry standard development.

Purpose of the Study:

• To address limitations in traditional online education satisfaction evaluation methods.
• To develop an accurate and stable machine learning model for assessing user satisfaction in online education.
• To leverage big data analytics for enhancing the online learning experience.

Main Methods:

• Utilized machine learning algorithms as the core of the satisfaction evaluation model.
• Improved decision trees using a cost-sensitive approach to account for classification error costs.
• Integrated multiple decision trees using the random forest principle to enhance model accuracy and stability.

Main Results:

• The developed model demonstrated improved accuracy compared to traditional methods.
• Experimental validation confirmed the model's enhanced stability and effectiveness.
• The cost-sensitive decision tree and random forest integration proved beneficial for satisfaction prediction.

Conclusions:

• The proposed machine learning model offers a significant advancement in evaluating online education user satisfaction.
• This research provides valuable insights for improving online education service quality and competitiveness.
• The findings offer a reference for future research in online education satisfaction rating technologies.