Detection of Suspicious Patterns in Online MCQ Exams
Anindya Sundar Dey

Anindya Sundar Dey, School of Information Technology and Engineering, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
Manuscript received on May 01, 2019. | Revised Manuscript Received on May 09, 2019. | Manuscript published on May 20, 2019. | PP: 1-4 | Volume-5 Issue-4, May 2019. | Retrieval Number: D0906055419/19©BEIESP 
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: The purpose of this paper is to find ways to identify or detect suspicious patterns in multiple choice questions and highlight them allowing for greater scrutiny and helping curb malpractices in examination halls. For this purpose an algorithm has been developed to detect suspicious answer patterns in online MCQ exams which can detect if multiple students have been taking outside help using applications like Team Viewer. To obtain data for this project we obtained results of an MCQ test where two groups of students in who completed a MCQ test of moderate difficulty. While both groups were kept under scrutiny. Unlike group B group A had a select number of “special examinees” who were being helped by outside sources( teachers ). We later ran the test results of both the groups under the algorithm. The Algorithm was able to detect 17 Students with Suspicious Patterns in Group A. While no student was detected in Group B.
Keywords: Suspicion Threshold, Online Mcq, Suspicion Factor, Answer Key, Array of Converted Answers, Comparison Point.