A Unified Framework for Student Cluster Grouping with Learning Preference Associative Detection for Enhancing Students' Learning Outcomes in Computer Programming Courses

Abstract

Computer Programming is considered an important underlying ability for effectively achieving study in computer-related majors. This paper proposes a unified framework of dynamically sensing contextual indicators of the students possessive's performance of well-performing students. The said indicators once compiled into an associative relationship with the profile of individual students in terms of prior academic background and personal attributes becomes a basis for adaptively grouping students into clusters. The aim of the unified framework is to adaptively reinforce the performance of students in each independent group. The sample settings of all involved modules in the unified system gives an insight into the applicability so that educators can flexibly facilitate the classroom to achieve better academic results for students with different profiles.