ViSeq: Visual Analytics of Learning Sequence in Massive Open Online Courses

Area of Science:

• Educational Technology
• Data Science
• Human-Computer Interaction

Background:

• Massive Open Online Courses (MOOCs) generate rich data, including learner profiles, outcomes, and activity sequences.
• Analyzing learning sequences is crucial for understanding learner behavior and performance, but has been underexplored.
• Existing MOOC analytics often aggregate learning activities, losing valuable sequential information.

Purpose of the Study:

• To introduce ViSeq, a visual analytics system designed to address the loss of sequential information in MOOC data.
• To enable visualization of learning sequences for different learner groups.
• To facilitate a deeper understanding of the reasons behind diverse learning behaviors.

Main Methods:

• Development of the ViSeq visual analytics system.
• Incorporation of four linked views: projection, pattern, sequence, and individual views.
• Evaluation through case studies and expert interviews.

Main Results:

• ViSeq effectively visualizes learning sequences at multiple granularity levels.
• The system aids in identifying learner groups and their distinct sequential patterns.
• It supports comparison of individual learning paths and transitions between activities.

Conclusions:

• ViSeq enhances the analysis of MOOC learning sequences by preserving and visualizing temporal activity data.
• The system provides valuable insights into learner behavior and performance correlations.
• ViSeq offers a novel approach to understanding and improving online learning experiences.