Exam questions classification based on Bloom’s taxonomy cognitive level using classifiers combination

Dhuha Abdulhadi Abduljabbar, Nazlia Omar

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Assessment through written examination is a traditional method but it is a universal test method practiced in most of the educational institutions today. Therefore, the question must be provided in accordance with the subject content learned by students to fulfil learning objectives. However, the process of questions writing is very challenging step for the lecturer. The situation is getting more challenging when lecturers try to produce good quality and fair questions to assess different level of cognitive. Thus, the Bloom’s Taxonomy has become a common reference for the teaching and learning process used as a guide for the production of exam questions. Exam questions classification presents a particular challenge is the classification of short text questions due to short text involves text with less than 200 characters. In addition, the features of short text are very sparse and far. This study proposed a new method to classify exam questions automatically according to the cognitive levels of Bloom’s taxonomy by implementing a combination strategy based on voting algorithm that combines three machine learning classifiers. In this work, several classifiers are taken into consideration. The classifiers are, Support Vector Machine (SVM), Naïve Bayes (NB), and k-Nearest Neighbour (k-NN) that are used to classify the question with or without feature selection methods, namely Chi-Square, Mutual Information and Odd Ratio. Then a combination algorithm is used to integrate the overall strength of the three classifiers (SVM, NB, and k-NN). The classification model achieves highest result through the combination strategy by applying Mutual Information, which proved to be promising and comparable to other similar models. These experiments aimed to efficiently integrate different feature selection methods and classification algorithms to synthesize a classification procedure more accurately.

Original languageEnglish
Pages (from-to)447-455
Number of pages9
JournalJournal of Theoretical and Applied Information Technology
Volume78
Issue number3
Publication statusPublished - 31 Aug 2015

Fingerprint

Classifier Combination
Taxonomies
Taxonomy
Classifiers
Classifier
Bayes
Mutual Information
Feature Selection
Support vector machines
Feature extraction
Nearest Neighbor
Support Vector Machine
Classify
Integrate
Chi-square
Odds Ratio
Classification Algorithm
Voting
Learning Process
Learning systems

Keywords

  • Bloom’s taxonomy
  • Exam questions
  • Feature selection
  • Machine learning
  • Voting algorithm

ASJC Scopus subject areas

  • Computer Science(all)
  • Theoretical Computer Science

Cite this

Exam questions classification based on Bloom’s taxonomy cognitive level using classifiers combination. / Abduljabbar, Dhuha Abdulhadi; Omar, Nazlia.

In: Journal of Theoretical and Applied Information Technology, Vol. 78, No. 3, 31.08.2015, p. 447-455.

Research output: Contribution to journalArticle

@article{c8b24b9e70374dcdaff81961f03543e8,
title = "Exam questions classification based on Bloom’s taxonomy cognitive level using classifiers combination",
abstract = "Assessment through written examination is a traditional method but it is a universal test method practiced in most of the educational institutions today. Therefore, the question must be provided in accordance with the subject content learned by students to fulfil learning objectives. However, the process of questions writing is very challenging step for the lecturer. The situation is getting more challenging when lecturers try to produce good quality and fair questions to assess different level of cognitive. Thus, the Bloom’s Taxonomy has become a common reference for the teaching and learning process used as a guide for the production of exam questions. Exam questions classification presents a particular challenge is the classification of short text questions due to short text involves text with less than 200 characters. In addition, the features of short text are very sparse and far. This study proposed a new method to classify exam questions automatically according to the cognitive levels of Bloom’s taxonomy by implementing a combination strategy based on voting algorithm that combines three machine learning classifiers. In this work, several classifiers are taken into consideration. The classifiers are, Support Vector Machine (SVM), Na{\"i}ve Bayes (NB), and k-Nearest Neighbour (k-NN) that are used to classify the question with or without feature selection methods, namely Chi-Square, Mutual Information and Odd Ratio. Then a combination algorithm is used to integrate the overall strength of the three classifiers (SVM, NB, and k-NN). The classification model achieves highest result through the combination strategy by applying Mutual Information, which proved to be promising and comparable to other similar models. These experiments aimed to efficiently integrate different feature selection methods and classification algorithms to synthesize a classification procedure more accurately.",
keywords = "Bloom’s taxonomy, Exam questions, Feature selection, Machine learning, Voting algorithm",
author = "Abduljabbar, {Dhuha Abdulhadi} and Nazlia Omar",
year = "2015",
month = "8",
day = "31",
language = "English",
volume = "78",
pages = "447--455",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "3",

}

TY - JOUR

T1 - Exam questions classification based on Bloom’s taxonomy cognitive level using classifiers combination

AU - Abduljabbar, Dhuha Abdulhadi

AU - Omar, Nazlia

PY - 2015/8/31

Y1 - 2015/8/31

N2 - Assessment through written examination is a traditional method but it is a universal test method practiced in most of the educational institutions today. Therefore, the question must be provided in accordance with the subject content learned by students to fulfil learning objectives. However, the process of questions writing is very challenging step for the lecturer. The situation is getting more challenging when lecturers try to produce good quality and fair questions to assess different level of cognitive. Thus, the Bloom’s Taxonomy has become a common reference for the teaching and learning process used as a guide for the production of exam questions. Exam questions classification presents a particular challenge is the classification of short text questions due to short text involves text with less than 200 characters. In addition, the features of short text are very sparse and far. This study proposed a new method to classify exam questions automatically according to the cognitive levels of Bloom’s taxonomy by implementing a combination strategy based on voting algorithm that combines three machine learning classifiers. In this work, several classifiers are taken into consideration. The classifiers are, Support Vector Machine (SVM), Naïve Bayes (NB), and k-Nearest Neighbour (k-NN) that are used to classify the question with or without feature selection methods, namely Chi-Square, Mutual Information and Odd Ratio. Then a combination algorithm is used to integrate the overall strength of the three classifiers (SVM, NB, and k-NN). The classification model achieves highest result through the combination strategy by applying Mutual Information, which proved to be promising and comparable to other similar models. These experiments aimed to efficiently integrate different feature selection methods and classification algorithms to synthesize a classification procedure more accurately.

AB - Assessment through written examination is a traditional method but it is a universal test method practiced in most of the educational institutions today. Therefore, the question must be provided in accordance with the subject content learned by students to fulfil learning objectives. However, the process of questions writing is very challenging step for the lecturer. The situation is getting more challenging when lecturers try to produce good quality and fair questions to assess different level of cognitive. Thus, the Bloom’s Taxonomy has become a common reference for the teaching and learning process used as a guide for the production of exam questions. Exam questions classification presents a particular challenge is the classification of short text questions due to short text involves text with less than 200 characters. In addition, the features of short text are very sparse and far. This study proposed a new method to classify exam questions automatically according to the cognitive levels of Bloom’s taxonomy by implementing a combination strategy based on voting algorithm that combines three machine learning classifiers. In this work, several classifiers are taken into consideration. The classifiers are, Support Vector Machine (SVM), Naïve Bayes (NB), and k-Nearest Neighbour (k-NN) that are used to classify the question with or without feature selection methods, namely Chi-Square, Mutual Information and Odd Ratio. Then a combination algorithm is used to integrate the overall strength of the three classifiers (SVM, NB, and k-NN). The classification model achieves highest result through the combination strategy by applying Mutual Information, which proved to be promising and comparable to other similar models. These experiments aimed to efficiently integrate different feature selection methods and classification algorithms to synthesize a classification procedure more accurately.

KW - Bloom’s taxonomy

KW - Exam questions

KW - Feature selection

KW - Machine learning

KW - Voting algorithm

UR - http://www.scopus.com/inward/record.url?scp=84940667147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940667147&partnerID=8YFLogxK

M3 - Article

VL - 78

SP - 447

EP - 455

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 3

ER -