Identification of conflicting questions in the PARES system

Authors

  • Avgoustos Tsinakos Kavala Institute of Technology
  • Ioannis Kazanidis Kavala Institute of Technology

DOI:

https://doi.org/10.19173/irrodl.v13i3.1176

Keywords:

Computer adaptive testing, CAT, conflict detection algorithm

Abstract

Student testing and knowledge assessment is a significant aspect of the learning process. In a number of cases, it is expedient not to present the exact same test to all learners all the time (Pritchett, 1999). This may be desired so that cheating in the exam is made harder to carry out or so that the learners can take several practice tests on the same subject as part of the course.


This study presents an e-testing platform, namely PARES, which aims to provide assessment services to academic staff by facilitating the creation and management of question banks and powering the delivery of nondeterministically generated test suites. PARES uses a conflict detection algorithm based on the vector space model to compute the similarity between questions and exclude questions which are deemed to have an unacceptably large similarity from appearing in the same test suite. The conflict detection algorithm and a statistical evaluation of its accuracy are presented. Evaluation results show that PARES succeeds in detecting question types at about 90% and its efficiency can be further increased through continuing education and enrichment of the system’s correlation vocabulary.

 

Author Biographies

Avgoustos Tsinakos, Kavala Institute of Technology

Department of Industrial Informatics

Ioannis Kazanidis, Kavala Institute of Technology

Department of Industrial Informatics

Published

2012-06-12

How to Cite

Tsinakos, A., & Kazanidis, I. (2012). Identification of conflicting questions in the PARES system. The International Review of Research in Open and Distributed Learning, 13(3), 297–313. https://doi.org/10.19173/irrodl.v13i3.1176

Issue

Section

Research Articles