An adaptive testing system for supporting versatile educational assessment

Huang, Yueh‐Min; Lin, Yen-Ting; Cheng, Shu-Chen

doi:10.1016/j.compedu.2008.06.007

Cited by 93 publications

(45 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional item selection algorithm based on the candidate ability level and to select item of maximum information for testing [8], this method is called the maximum information method (MI), and the theoretical basis for doing so can improve the measurement accuracy. However, this method often leads to imbalance use of test item in the item pool [10]. On one hand, the use of the item which has high-discrimination is more frequent, resulting in excessive exposure of these items; On the other hand, the low-discrimination items with little or not be used [11] [12].For testing, this imbalance of item use can caused a serious impact on the test safety and development costs [13].…”

Section: Overview Of the Item Selection Approach In Catmentioning

confidence: 98%

The Study of Item Selection Method in CAT

Zhou

Qin

et al. 2012

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. Item selection method is one of the most important parts of computerized adaptive testing. Traditional method is based on the item information function to select the item which has maximum information, with the maximum information test to achieve the purpose of accurate estimates the examinee's ability level. However, this method has high item exposure rate and the test content imbalance problem, etc. To solve these problems, this article introduces a new heuristic item selection method. The results of the study show that compared with the maximum information method, with the assurance of the condition of the same measurement accuracy, the new method can better control item exposure rate and achieve content balancing.

show abstract

Section: Overview Of the Item Selection Approach In Catmentioning

confidence: 98%

The Study of Item Selection Method in CAT

Zhou

Qin

et al. 2012

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…A significant aspect of e-learning system is that they can be effectively used to assess students' learning [3,4].…”

Section: Introductionmentioning

confidence: 99%

OPCOMITS: Developing an adaptive and intelligent web based educational system based on concept map model

Doğan

Dikbıyık

2016

Comp Applic In Engineering

View full text Add to dashboard Cite

Concept map model is a method that creates domain model by identifying the relationship between concepts in course contents. This study presents an adaptive intelligent web based learning system called OPCOMITS (Object Oriented Programming Tutor using Concept Map Model). OPCOMITS has a free domain model which can be regulated by an expert for any course. It uses concept map model to regulate the topic hierarchy, to measure the student's knowledge about a topic and to stimulate learning. By employing a concept map model, it structures the course and provides an environment in which the lecturer can arrange the chapters, topics, concepts and the prerequisite relationships between the concepts. Thus, it offers an adaptive and effective learning environment by measuring the level of student's knowledge about a topic, offering reinforcing feedback, diagnosing students' weaknesses and directing them to related chapter topic in the domain for revisions. To evaluate the effectiveness of the proposed approach an experiment has been conducted on Computer Programming department in Object Oriented Programming course. From the experimental results, it is found that OPCOMITS has contributed to the academic success of students using it and students have exhibited much better learning than those who have used a conventional e-learning system. ß

show abstract

“…The system allows to select one of three predefined item selection strategies based in IRT. A similar, yet less flexible, system is proposed by (Huang, Lin, & Cheng, 2009), which provides CAT functionality for eLearning scenarios. It has a modular architecture based on ASP.NET and thus can be integrated with other platforms building on the same technology stack.…”

Section: Learning Platforms With Cat Featuresmentioning

confidence: 99%

A flexible online platform for computerized adaptive testing

Oppl

Reisinger

Eckmaier

et al. 2017

Int J Educ Technol High Educ

View full text Add to dashboard Cite

Computerized Adaptive Testing (CAT) is a field of research originating in psychometrics that has been adopted in the last years for formative and summative assessment activities in educational settings in general and in online learning in particular. While a variety of platforms is available for designing and deploying CAT the challenge of providing the flexibility in test and item design required for domain-specific assessment formats in education has hardly been addressed so far. The present article introduces a software architecture to fill this gap and enable the development of fully customizable CAT tools with respect to domain-specific item design and visualization as well as deployed CAT algorithms. A prototypical implementation of the architecture and a set of domain-specific item types are presented to demonstrate the feasibility of the proposed approach and outline future directions of development and research.

show abstract

An adaptive testing system for supporting versatile educational assessment

Cited by 93 publications

References 28 publications

The Study of Item Selection Method in CAT

The Study of Item Selection Method in CAT

OPCOMITS: Developing an adaptive and intelligent web based educational system based on concept map model

A flexible online platform for computerized adaptive testing

Contact Info

Product

Resources

About