Identification of the Students Learning Process During Education Robotics Activities

Area of Science:

• Educational Technology
• Robotics in Education
• Data Analytics in Learning

Background:

• Educational Robotics (ER) activities are increasingly used to engage students.
• Integrating sensors in ER enhances robot-environment interaction and learning complexity.
• Understanding student programming strategies is key to assessing ER impact.

Purpose of the Study:

• To design and evaluate an assessment process for Educational Robotics impact on student learning.
• To investigate pedagogical and quantitative outcomes of ER activities using data analytics.
• To explore student problem-solving pathways in programming robotic artifacts with sensors.

Main Methods:

• Utilized Educational Data Mining (EDM) and machine learning (k-means clustering).
• Collected programming attempt data from primary and secondary students using Lego Mindstorms EV3 and visual programming.
• Designed a tracking system to log programming sequences for analysis.

Main Results:

• Identified distinct patterns in programming sequence creation.
• Extracted various problem-solving pathways employed by student teams.
• Analyzed the relationship between problem-solving pathways and early achievement indicators.

Conclusions:

• The assessment process effectively captures student engagement and learning in ER.
• Data mining and machine learning can reveal valuable insights into student problem-solving strategies.
• ER activities, particularly with sensor integration, offer rich data for educational research.