DATA MINING USING CLUSTERING TECHNIQUE AS A BASIS IN DEVELOPING A GAMIFIED LEARNING SYSTEM

Melidiossa  V. Pagudpud,

DATA MINING USING CLUSTERING TECHNIQUE AS A BASIS IN DEVELOPING A GAMIFIED LEARNING SYSTEM

Abstract:

Gamification or the integration of game rudiments into a non-gaming environment is becoming popular in education as a way to promote engagement and motivation in the learning environment. However, if gamified learning systems are to be used in schools, developers should have a good understanding of the target users. This study applied data mining using clustering technique for knowledge extraction from the National Career Assessment Examination (NCAE) result in the Division of Quirino. The NCAE is an examination given to all grade 9 students in the Philippines to assess their aptitudes in the different domains. Clustering the students is helpful in conceptualizing and developing a gamified learning system. With the use of the RapidMiner tool, clustering algorithms such as Density-Based Spatial Clustering of Applications with Noise (DBSCAN), k-means, k-medoid, expectation maximization clustering, and support vector clustering algorithms were analyzed. The silhouette indexes of the said clustering algorithms were compared, and the result showed that the k-means algorithm with k = 3 and silhouette index equal to 0.196 yields the optimal clustering algorithm to group the students. Three groups were formed having 477 students in the determined group (cluster 0), 310 proficient students (cluster 1) and 396 developing students (cluster 2). The data mining technique used in this study is essential in extracting useful information from the NCAE result to better understand the abilities of students which in turn is a good basis for developing a gamified learning system.