An Evolutionary Approach for Question Selection from a Question Bank: A Case Study

An Evolutionary Approach for Question Selection from a Question Bank: A Case Study

Dimple V. Paul (Department of Computer Science, DM's College of Arts, Science and Commerce, Mapusa, Goa, India), Shankar B. Naik (Department of Computer Science, Dhempe College of Science, Miramar, Goa, India) and Jyoti D. Pawar (Department of Computer Science and Technology, Goa University, Taleigao, Goa, India)
Copyright: © 2014 |Pages: 15
DOI: 10.4018/ijictrda.2014010104
OnDemand PDF Download:
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The success of any educational program depends on its evaluation system. Examinations are a part of learning process which acts as an element in evaluation. For the smooth conduct of examinations of various universities and academic institutions, the question paper generation process would be helpful. However, examination question paper composition is a multi-constraint concurrent optimization problem. Question selection plays a key role in question paper generation systems. Also it is the most significant and time consuming activity. The question selection is handled in traditional question paper generation systems by using a specified question paper format containing a listing of weightages to be allotted to each unit/module of the syllabus. They do not consider other constraints such as total time duration for completion of the paper, total number of questions and the difficulty level of the questions in the question paper etc. In this paper, the authors have modeled the Question Selection Problem as a multi-constraint optimization problem and proposed an Evolutionary Approach for the implementation same. The authors have experimented with this approach on a case study. The results obtained in this case study are interesting and promising to continue its implementation work and further research.
Article Preview
Top

2. Literature Review

The approaches commonly used till date for selecting questions for question paper generation by paper setters fall under the following two broad categories – Manual and Automated. The manual approach mostly includes the following steps:

  • 1.

    Get set of questions from different faculties spread across different place;

  • 2.

    A committee, which scrutinizes and consolidates all questions collected from faculties.

The automated tools listed below are for multiple choice question paper generation and they are reported to be randomly selecting the questions from a common question bank (Huband & Hingston, 2006; Mehmet,2010; Zhen-hua & Hao-shuai & Hun-e, 2011):

  • 1.

    ExamBuilder: A web-based application to administer and conduct exams over the internet-http://www.exambuilder.com;

  • 2.

    TestGenerator: An online testing and assessment application designed to simplify the entire process of test creation, delivery and administration for automatic generation of examination question paper-http://www.testshop.com.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 4: 1 Issue (2014)
Volume 3: 2 Issues (2012)
Volume 2: 2 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing