Didik Dwi Prasetya, Ahmad Maulanal Fahmi, Muhammad Jauharul Fuady, Triyanna Widiyaningtyas, Azlan Mohd Zain, Tsukasa Hirashima
Log data serves as an essential asset for capturing system events and states throughout its execution. This study aims to uncover the underlying cognitive processes in extended concept map construction by analyzing user interaction logs through data-driven techniques. Two extended concept map techniques: extended kit-build (EKB), which combines closed-ended and open-ended fashion, and extended scratch-build (ESB), which extends open-ended with the same technique, were involved in this research. The research utilized 39,781 rows of log data documenting concept map creation activities. The focus of this study is to reveal the patterns in concept proposition construction over time and visualize the number of propositions generated by each user. The experimental results demonstrate that the observed patterns in closed-ended and open-ended concept map construction are consistent with established theories, especially concerning the diversity of actions and achievement levels. This study emphasizes the crucial role of educational data science in uncovering valuable insights from learning activities. © 2025 IEEE.
State University of Malang, Department of Electrical Engineering and Informatics, Malang, Indonesia; Universiti Teknologi Malaysia, Faculty of Computing, Johor Bahru, Malaysia; Hiroshima University, Department of Information Engineering, Hiroshima, Japan
