Curriculum Assessment of Higher Educational Institution Using Trace-segmented Clustering

Abstract

Curriculum mining is research area that assess students’ learning behavior and compare it with the curriculum guideline. Previous work developed sequence matching alignment approach to check the conformance between students’ learning behavior and curriculum guideline. Considering only the sequence matching alignment is insufficient to understand the patterns of group of students. Another work proposed an approach by aggregating the students’ profile to represent students’ learning behavior and investigate the impact of the learning behavior to their learning performance. However, the aggregate profile approach considers the entire period of study rather than segmented period. This study proposes a methodology to assess students’ learning path with segmented period i.e. the semester of the related curriculum. The segmented-period profile generated would be the input for sequence matching alignment approach to assess the conformity of students’ behavior with the prior curriculum guideline. Real curriculum data has been used to test the effectivity of the methodology. The results show that the students can be grouped into various cluster per semesters that have different characteristic with respect to their learning behavior and performance. The results can be analyzed further to improve the curriculum guideline.

Progressive Prediction of Students’ Future Performance on Coherent Vertical Curriculum

“…Several works have been conducted on analyzing the students' performance in the coherent vertical curriculum by using cluster analysis both on aggregated and segmented data [5], [10]. There is also research implementing the cluster evolution analysis to analyze the migration of the students' learning behavior [6].…”

“…In this type of curriculum, the student needs to take the course exactly like in the curriculum guideline because there are academic standards to be achieved when student finished all course in the curriculum [4]. Indonesia is one of the countries that applied this type of curriculum to comply with the government guideline of standard competencies [5]. However, there are differences between students learning behavior with the curriculum guideline caused by various reason such as student failing the course, taking incoming courses in advanced, or credit limitation that prohibit student to take more course in particular semester.…”

“…The profile-based approach has been done by clustering the students per unit of time to understand students' learning behavior in comparison to the curriculum [5]. Also, the changes of the behavior from semester to semester have been analyzed using the migration of the students' learning behavior of the student at a certain period of time by clustering method based on students' profiles [6].…”

Profile-Based Cluster Evolution Analysis: Identification of Migration Patterns for Understanding Student Learning Behavior

“…The results showed that the students could be grouped into various clusters per semester that have different learning behavior and performance characteristics. However, the method cannot show the changes in students' learning behavior in a timely manner (e.g., from one semester to another semester) (Priyambada et al, 2018).…”

“…In the domain of EPM, the event log can be partially cut in accordance with the timestamp (i.e., period of study or semester). While work has been conducted on trace clustering in the domain of EPM [15], no studies have shown how temporal cases (i.e., students' profiles) changed over time. Most EPM emphasizes the discovered process model, i.e., the model representing students' behavior during the study period.…”