[1]汪文义,熊 建,宋丽红,等.双题匹配的MPI方法及其在平行试卷生成中的应用[J].江西师范大学学报(自然科学版),2021,(02):118-125.[doi:10.16357/j.cnki.issn1000-5862.2021.02.02]
 WANG Wenyi,XIONG Jian,SONG Lihong,et al.The Maximum Priority Index Method of Two Items Matching and Its Application on Constructing Parallel Tests[J].Journal of Jiangxi Normal University:Natural Science Edition,2021,(02):118-125.[doi:10.16357/j.cnki.issn1000-5862.2021.02.02]
点击复制

双题匹配的MPI方法及其在平行试卷生成中的应用()
分享到:

《江西师范大学学报》(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年02期
页码:
118-125
栏目:
心理与教育测量
出版日期:
2021-04-10

文章信息/Info

Title:
The Maximum Priority Index Method of Two Items Matching and Its Application on Constructing Parallel Tests
文章编号:
1000-5862(2021)02-0118-08
作者:
汪文义1熊 建1宋丽红2郑娟娟1胡海洋1
1.江西师范大学计算机信息工程学院,江西 南昌 330022; 2.江西师范大学教育学院,江西 南昌 330022
Author(s):
WANG Wenyi1XIONG Jian1SONG Lihong2ZHENG Juanjuan1HU Haiyang1
1.College of Computer and Information Engineering,Jiangxi Normal University,Nanchang Jiangxi 330022,China; 2.Collge of Education,Jiangxi Normal University,Nanchang Jiangxi 330022,China
关键词:
平行测验 组卷方法 计算机自适应测验 最大优先级指标 双题匹配 单题匹配
Keywords:
parallel tests test assembly method computerized adaptive test maximum priority index two items matching single item matching
分类号:
B 841
DOI:
10.16357/j.cnki.issn1000-5862.2021.02.02
文献标志码:
A
摘要:
大规模考试的公平性备受关注,探索能够生成多份平行测验并能保证测验质量的组卷方法十分重要.原用于计算机自适应测验(CAT)的基于最大优先级指标已开始用于组卷,但只局限于单题之间的匹配.为了增加求解空间,该文提出了一种基于最大优先级指标的双题匹配的组卷方法,实现题库中双题与种子试卷双题之间匹配,并结合平行试卷质量调整方法,用于生成平行试卷.将已有的组卷方法与双题匹配方法进行实验对比,结果表明:双题匹配方法有效地提升了生成的平行测验质量.
Abstract:
The fairness of large-scale examinations has attracted much attention.It is very important to explore a method for generating multiple parallel tests and ensuring the quality of the tests.The maximum priority index(MPI)method originally proposed in the computer adaptive test(CAT)has been applied to constructing multiple parallel tests,but it is only limited to matching between single item and single item.In order to increase the solution space,a two items matching method based on the maximum priority index is proposed to realize the matching between the two items in the item bank and the two items in the seed test,and the parallel test quality adjustment method is combined to generate parallel tests.The existing test construction method is compared with the two items matching method.The results show that the two items matching method effectively improves the quality of the parallel test.

参考文献/References:

[1] 舒清录.一种实用的随机组卷策略研究与实现[J].电脑与信息技术,2020,165(3):34-36,45.
[2] 韩啸,毕波,唐锦萍.基于基因表达式编程的计算机组卷算法研究[J].计算机技术与发展,2020,30(5):154-159.
[3] 王友仁,张砦,施玉霞,等.题库系统智能成卷理论和组卷方法研究[J].电子科技大学学报,2006,35(3):77-80.
[4] 李佳,丁树良.计算机化自适应测验中能力估计新方法[J].江西师范大学学报:自然科学版,2019,43(2):36-40.
[5] 王宣策,欧阳鑫玉.基于改进遗传算法的智能组卷系统设计[J].电脑知识与技术,2020,16(2):65-67.
[6] Wang Lei,Tang Dunbing.An improved adaptive genetic algorithm based on hormone modulation mechanism for job-shop scheduling problem[J].Expert Systems With Applications,2011,38(6):7243-7250.
[7] Lin Ying,Gong Yuejiao,Zhang Jun.An adaptive ant colony optimization algorithm for constructing cognitive diagnosis tests[J].Applied Soft Computing,2017,52(1):1-13.
[8] Lin Ying,Jiang Yeshi,Gong Yuejiao,et al.A discrete multiobjective particle swarm optimizer for automated assembly of parallel cognitive diagnosis tests[J].IEEE Transactions on Cybernetics,2019,49(7):2792-2805.
[9] Armstrong R,Jones D,Wu I L.An automated test development of parallel tests from a seed test[J].Psychometrika,1992,57(2):271-288.
[10] Swanson L,Stocking M L.A model and heuristic for solving very large item selection problems[J].Applied Psychological Measurement,1993,17(2):151-166.
[11] van der Linden W J.Linear models of optimal test design[M].New York:Springer-Verlag,2005.
[12] Adema J J,van der Linden W J.Algorithms for computerized test construction using classical item parameters[J].Journal of Educational Statistics,1989,14(3):279-290.
[13] Armstrong R D,Jones D H.Polynomial algorithms for item matching[J].Applied Psychological Measurement,1992,16(4):365-371.
[14] Chen Peihua,Chang Huahua,Wu Haiyan.Item selection for the development of parallel forms from an IRT-based seed test using a sampling and classification approach[J].Educational andPsychological Measurement,2012,72(6):933-953.
[15] Cheng Ying,Chang Huahua.The maximum priority index method for severely constrained item selection in computerized adaptive testing[J].British Journal of Mathematical and Statistical Psychology,2009,62(2):369-383.
[16] 潘奕娆.改进的最大优先指标及在计算机化自适应诊断测验中的应用[D].南昌:江西师范大学,2011.
[17] 汤楠,丁树良.一阶段选题的最大优先级指标的修正[J].江西师范大学学报:自然科学版,2012,36(5):452-455.
[18] Wang Shiyu,Zheng Yi,Zheng Chanjin,et al.An automated test assembly design for a large-scale chinese proficiency test[J].Applied Psychological Measurement,2016,40(3):233-237.
[19] Chen Peihua.Three-element item selection procedures for multiple forms assembly:an item matching approach[J].Applied Psychological Measurement,2016,40(2):114-127.
[20] Chang Huahua.Psychometrics behind computerized adaptive testing[J].Psychometrika,2015,80(1):1-20.
[21] 漆书青.现代教育与心理测量学原理[M].北京:高等教育出版社,2002.

相似文献/References:

[1]李贵玉,涂冬波,戴步云,等.计算机多阶段自适应测验的组卷方法[J].江西师范大学学报(自然科学版),2017,(05):462.
 LI Guiyu,TU Dongbo,DAI Buyun,et al.The Test Assemble Methods of Multistage Adaptive Test[J].Journal of Jiangxi Normal University:Natural Science Edition,2017,(02):462.

备注/Memo

备注/Memo:
收稿日期:2020-10-05
基金项目:国家自然科学基金(62067005,61967009,31500909),汉考国际科研基金(CTI2019B10)和江西师范大学教学改革研究(JXSDJG1848)资助项目.
作者简介:汪文义(1983—),男,湖南衡山人,副教授,博士,主要从事教育测量与信息处理的研究.E-mail:wenyiwang@jxnu.edu.cn
更新日期/Last Update: 2021-04-10