Building a Descriptive Exam Model for Student Performance using Process Mining Techniques in Examaize System
Lalbihari Barik, Department of Information Systems, Faculty of Computing and Information Technology in Rabigh, King Abdulaziz University, Kingdom of Saudi Arabia.
Manuscript received on December 19, 2019. | Revised Manuscript received on December 30, 2019. | Manuscript published on January 10, 2020. | PP: 1043-1050 | Volume-9 Issue-3, January 2020. | Retrieval Number: C8025019320/2020©BEIESP | DOI: 10.35940/ijitee.C8025.019320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Paper The objective of this research paper is to determine the understanding of students’ course contents and evaluate student performance according to expectations. There are predefined navigation models available to answer Multiple Choice Questions (MCQs). The individual student responds to these questions in their navigation pattern that results in various Student Performance Outcomes. The research presents the process mining techniques to evaluate students’ answers in the MCQs predefined navigation model in the exaMAIZE Assessment System. This research shows that students navigate all the twenty-five questions according to their way of answering the exam, where seven questions are under high frequency and later analyze to revise the answer on suspicion or difficult. The experiment compared Student Exam Outcomes with the Student Performance Outcomes of each outcome, and the frequency of navigating a question to find out individual student Strengths and Weaknesses. This work can be extended future development of efficient process mining algorithms by applying the next academic session to improve student performance.
Keywords: Online Assessment, eLearning, Student Evaluation Methods, Process Mining, Educational Data mining
Scope of the Article: Data mining