The utilization of data analysis techniques in predicting student performance in massive open online courses (MOOCs)

Area of Science:

• Educational Technology
• Data Science in Education
• Online Learning Analytics

Background:

• The rise of the internet has fueled the growth of open online learning platforms, leading to Massive Open Online Courses (MOOCs) with millions of global enrollments.
• MOOCs offer flexible, online learning experiences, expanding access to education but are challenged by low student completion rates.

Purpose of the Study:

• To explore the impact of technology on open learning within MOOCs.
• To develop a predictive approach for identifying at-risk students by capturing and analyzing performance data.
• To mitigate dropout rates in online learning environments.

Main Methods:

• Utilized the eRegister system for capturing and analyzing learner data.
• Focused on identifying trends in student performance through data analysis.
• Developed a method to normalize data for consistent time-series analysis.

Main Results:

• High levels of engagement, interaction, and attendance correlate with higher academic marks.
• The developed approach successfully normalizes data into consistent series for analysis.
• The system can transform data into a statistical dashboard for MOOC organizers.

Conclusions:

• Predictive systems are essential for online learning communities to support student success.
• Data-driven insights can proactively identify and assist students at risk of dropping out.
• The eRegister system provides a valuable tool for enhancing MOOC effectiveness and learner retention.