IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Intelligent Questioning System Based on Fuzzy Logic

Intelligent Questioning System Based on Fuzzy Logic
View Sample PDF
Author(s): Omer Deperlioglu (Afyon Kocatepe Üniversitesi, Turkey), Guray Sonugur (Afyon Kocatepe Üniversitesi, Turkey)and Kadir Suzme (Afyon Kocatepe Üniversitesi, Turkey)
Copyright: 2015
Pages: 23
Source title: Artificial Intelligence Applications in Distance Education
Source Author(s)/Editor(s): Utku Kose (Usak University, Turkey)and Durmus Koc (Usak University, Turkey)
DOI: 10.4018/978-1-4666-6276-6.ch005

Purchase

View Intelligent Questioning System Based on Fuzzy Logic on the publisher's website for pricing and purchasing information.

Abstract

One of the most important functions of distance learning systems is determining the student knowledge level and performance clearly. In traditional education systems, students can be assessed in single-stage via tests and homework studies, which consist of multiple-choice questions. However, this method cannot provide accurate results since it is not able to evaluate student knowledge level and question difficulty level. In this chapter, a system and software structure that can determine student knowledge levels, topic difficulty level, and question difficulty levels according to instant student answers for the exam is introduced. In forming student knowledge levels, content monitoring and test data taken from distance education vocational school were used. In this way, more accurate results have been obtained. The fuzzy logic technique has been used to determine (classify) student knowledge levels and topic difficulty levels clearly. In order to determine next questions adaptively, the stored questions have been classified with division clustering methods, and the most suitable questions for the related student knowledge level have been found by using the nearest neighbor algorithm.

Related Content

Sylvia Robertson. © 2023. 28 pages.
Dimitrios Stamovlasis, Charalampos Tsanidis. © 2023. 23 pages.
Ikram Chelliq, Lamya Anoir, Mohamed Erradi, Mohamed Khaldi. © 2023. 26 pages.
Vasiliki Ioakeimidou. © 2023. 27 pages.
Eleni Bonti. © 2023. 25 pages.
Lamya Anoir, Ikram Chelliq, Mohamed Erradi, Mohamed Khaldi. © 2023. 29 pages.
Shibu Puthalath, M. R. Mallaiah, Viswesh Sekhar. © 2023. 17 pages.
Body Bottom