Didik Dwi Prasetya, Muis Muhtadi, Hanifah Nur Azizah, Azlan Mohd Zain
Concept maps are graphic representations of unique ideas widely used in learning. Concept mapping activities are often stored in an activity log which contains a record of data based on a particular time. The high activity of concept mapping can form extensive data collection and result in abundant information. An appropriate initial processing action is needed to process the concept mapping log data properly. This study aims to reduce the concept of map activity log data to obtain a reliable and noise-free dataset. This research begins with the data preprocessing stage, the initial technique in data mining that converts raw data into cleaner information and can be used for further processing. The preprocessing phase could be done using the data reduction method or adding a filter example to observe missing data on an attribute by eliminating missing observation data. The principal component analysis algorithm was used to normalize the data to become stable, neither too high nor too low. This study emphasizes that the extracted data could produce high accuracy and shorter processing time. © 2024 IEEE.
State University of Malang, Department of Electrical Engineering and Informatics, Malang, Indonesia; Universiti Teknologi Malaysia, Faculty of Computing, Johor Bahru, Malaysia