Student elective course selection patterns and satisfaction determinants identified through educational data mining

Area of Science:

• Educational Technology
• Data Mining in Education
• Higher Education Studies

Background:

• Digital transformation is reshaping higher education curricula.
• There is a growing emphasis on student agency and personalized learning paths.
• Understanding student preferences in elective courses is crucial for curriculum optimization.

Purpose of the Study:

• To analyze student preferences and satisfaction with elective courses using educational data mining.
• To identify patterns in course selection and determinants of satisfaction.
• To evaluate the effectiveness of the individual educational trajectory framework.

Main Methods:

• Educational data mining techniques were applied.
• Analysis of course selection patterns and satisfaction determinants among 1,089 students.
• Identification of distinct student segments based on preferences and satisfaction.

Main Results:

• Four distinct student segments with varying preferences and satisfaction profiles were identified.
• Information availability, career goal alignment, teaching quality, and course relevance significantly predict student satisfaction.
• The study identified key factors influencing student choices and satisfaction in elective courses.

Conclusions:

• A data-driven framework for optimizing elective course systems is proposed, integrating learning analytics and personalized recommendations.
• Educational technology can enhance student agency in curriculum customization.
• Findings support Sustainable Development Goal 4 by promoting inclusive, personalized education for future employment.