Automated exam question generator using genetic algorithm

Rahim, Tengku Nurulhuda Tengku Abd; Aziz, Zalilah Abd; Rauf, Rose Hafsah Ab.; Shamsudin, Noratikah

doi:10.1109/ic3e.2017.8409231

Cited by 17 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI technology not only can generate exam questions (Rahim, Aziz, Rauf, & Shamsudin, 2018), but also can automatically correct the assignments and test papers (Li et al, 2018). Correcting homework and test papers are routine tasks for teachers.…”

Section: Teaching Evaluationmentioning

confidence: 99%

A Review on Artificial Intelligence in Education

Huang

Saleh

Liu

2021

Acad. J. Interdiscip. Stud.

106

View full text Add to dashboard Cite

The emergence of innovative technologies has an impact on the methods of teaching and learning. With the rapid development of artificial intelligence (AI) technology in recent years, using AI in education has become more and more apparent. This article first outlines the application of AI in the field of education, such as adaptive learning, teaching evaluation, virtual classroom, etc. And then analyzes its impact on teaching and learning, which has a positive meaning for improving teachers' teaching level and students' learning quality. Finally, it puts forward the challenges that AI applications may face in education in the future and provides references for AI to promote education reform. Received: 16 January 2021 / Accepted: 24 March 2021 / Published: 10 May 2021

show abstract

Section: Teaching Evaluationmentioning

confidence: 99%

A Review on Artificial Intelligence in Education

Huang

Saleh

Liu

2021

Acad. J. Interdiscip. Stud.

106

View full text Add to dashboard Cite

show abstract

“…They proposed a new fitness function using the total score, difficulty, knowledge score, cognitive level, question type, and estimated time parameters. GA with Bloom Taxonomy, proposed by Rahim et al (2017), generates exam papers to evaluate different learning levels depending on cognitive levels and choices. In their proposed algorithm, the chromosome structure of an individual and a new fitness function are designed using Bloom's Taxonomy levels to evaluate each candidate exam paper containing all learning levels of Bloom's Taxonomy.…”

Section: Related Workmentioning

confidence: 99%

“…Several optimization algorithms have been successfully applied to several models for solving ATDP. These studies (Liu et al, 2013; Luantangsrisuk et al, 2016; Rahim et al, 2017; Yildirim, 2010) showed that there is great potential to be developed in ATDP. Recent literature shows that the dataset consists of a real question structure, and a limited number of questions pool by using traditional algorithms has been recently studied.…”

Section: Related Workmentioning

confidence: 99%

“…Yang, 2015), 'automatic question paper generation' (Naik et al, 2014), 'automated test assembly' (Luantangsrisuk et al, 2016), 'test design' (Alves et al, 2010), and so on. Considering the studies in the literature, the problem of automated exam paper generation was implemented with evolutionary, heuristic, meta-heuristic and swarm-based algorithms such as random algorithm (Naik et al, 2014), genetic algorithm (GA) (Ince et al, 2020;Ming-zhu et al, 2013;Rahim et al, 2017;Yildirim, 2010), particle swarm optimization (PSO) (Zhang & Zhang, 2015), simulated annealing (SA) (J. Yang, 2015), bee colony (Luantangsrisuk et al, 2016), fuzzy logic (Chavan et al, 2016), neural networks (Subramanian et al, 2019), and ant colony (Liu et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

“…The problem is studied under different titles, such as ‘exam paper generation’ (Wu et al, 2020), ‘automatic generation of exams’ (Grun & Zeileis, 2009), ‘generating test’ (Yildirim, 2010), ‘automatic item generation’ (Gierl et al, 2012), ‘generating test paper’ (Ming‐zhu et al, 2013; J. Yang, 2015), ‘automatic question paper generation’ (Naik et al, 2014), ‘automated test assembly’ (Luantangsrisuk et al, 2016), ‘test design’ (Alves et al, 2010), and so on. Considering the studies in the literature, the problem of automated exam paper generation was implemented with evolutionary, heuristic, meta‐heuristic and swarm‐based algorithms such as random algorithm (Naik et al, 2014), genetic algorithm (GA) (Ince et al, 2020; Ming‐zhu et al, 2013; Rahim et al, 2017; Yildirim, 2010), particle swarm optimization (PSO) (Zhang & Zhang, 2015), simulated annealing (SA) (J. Yang, 2015), bee colony (Luantangsrisuk et al, 2016), fuzzy logic (Chavan et al, 2016), neural networks (Subramanian et al, 2019), and ant colony (Liu et al, 2013). The main drawback of these studies is that there is no standard dataset (question banks).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated test design using swarm and evolutionary intelligence algorithms

et al. 2021

View full text Add to dashboard Cite

The world's increasing dependence on computer‐assisted education systems has raised significant challenges about student assessment methods, such as automated test design. The exam questions should test the students' potential from various aspects, such as their intellectual and cognitive levels, which can be defined as attributes of the questions to assess student knowledge. Test design is challenging when various question attributes, such as category, learning outcomes, difficulty, and so forth, are considered with the exam constraints, such as exam difficulty and duration. In this paper, four contributions are provided to overcome test design challenges for the student assessment. First, a tool is developed to generate a synthetic question pool. Second, an objective function is designed based on the considered attributes. Third, the popular swarm and evolutionary optimization methods, namely particle swarm optimization, genetic algorithm, artificial bee colony, differential search algorithm are comparatively studied with novel methodologies applied to them. Finally, as the state of the art methods, artificial bee colony, and differential search algorithm are further modified to improve the solution of the test design. To perform the proposed algorithms, a dataset of 1000 questions is built with the proposed question attributes of the test design. Algorithms are evaluated in terms of their successes in both minimizing the objective function and running time. Additionally, Friedman's test and Wilcoxon rank‐sum statistical tests are applied to statistically compare the algorithms' performances. The results show that the improved artificial bee colony and the improved differential search provide better results than others in terms of optimization error and running time.

show abstract