<![CDATA[One of the main elements affecting students' academic success in higher education is their interest in learning. However, direct observation is frequently used to subjectively identify differences in students' learning interests, which could result in inaccurate assessments. Therefore, in order to objectively classify students according to their learning characteristics, a data-driven approach is needed. The purpose of this study is to analyze and categorize students' learning interest levels using the K-Means clustering algorithm. Thirty university students filled out a learning interest questionnaire with a Likert scale of 1 to 5. Attendance at lectures, classroom activity, timely completion of assignments, level of independent study, and interest in the course are among the variables examined. Three clusters—representing high, medium, and low learning interest levels—were created using the K-Means algorithm. Based on the final cluster centroids, the results show that the K-Means algorithm successfully divided the students into three clusters: 11 students with high learning interest, 12 students with moderate learning interest, and 7 students with low learning interest. These results offer an unbiased summary of students' learning environments and can be used as a foundation for creating more focused and efficient teaching methods in higher education.]]>
Copyrights © 2026
