| 基于BP神经网络的认知诊断评估分类准确率影响因素分析 |
| |
| 引用本文： | 聂畅,孙小坚,辛涛.基于BP神经网络的认知诊断评估分类准确率影响因素分析[J].中国考试,2021(3). |
| |
| 作者姓名： | 聂畅 孙小坚 辛涛 |
| |
| 作者单位： | 北京师范大学;西南大学 |
| |
| 基金项目： | 中国基础教育质量监测协同创新中心2019年度自主课题“人工神经网络在认知诊断评估中的实现及影响因素研究”(BJZK-2019A1-19005)。 |
| |
| 摘 要： | BP神经网络是目前应用最广泛的人工神经网络模型之一,在分类和识别上表现出良好的特性,因此被研究者用于认知诊断评估以对被试进行诊断分类。通过模拟研究,考查属性个数、属性层级关系、测验长度、题目质量、测试样本量5个因素对BP神经网络在认知诊断中分类准确性的影响。结果表明:1)基于BP神经网络的认知诊断分类准确率不依赖于测试样本量;2)题目质量和测验长度对BP神经网络的诊断准确率有显著的积极影响;3)属性个数对BP神经网络的分类准确率有消极影响;4)题目质量一定程度上会影响BP诊断方法在不同属性层级结构上的分类准确率。
|
| 关 键 词： | BP神经网络 认知诊断评估 分类准确率 测验质量 测验技术 |
Factors Affecting the Classification Accuracy in Cognitive Diagnosis AssessmentBased on BP Neural Network |
| |
| NIE Chang,SUN Xiaojian,XIN Tao.Factors Affecting the Classification Accuracy in Cognitive Diagnosis AssessmentBased on BP Neural Network[J].China Examinations,2021(3). |
| |
| Authors: | NIE Chang SUN Xiaojian XIN Tao |
| |
| Institution: | (Beijing Normal University,Beijing 100875,China;Southwest University,Chongqing 400715,China) |
| |
| Abstract: | BP neural network is one of the most widely used artificial neural network models.It has good intelligence in classification and recognition.Therefore,it has been used by many researchers in cognitive diagnostic assessment.In order to explore the influencing factors on the classification accuracy in cognitive diagnosis assessment based on BP neural network,this paper uses the simulation method to investigate how the five factors(number of attributes,attribute hierarchy,test length,item parameters,test sample size)affect the classification accuracy in cognitive diagnosis based on BP neural network.The results show that:1)The classification accuracy based on BP neural network does not depend on the sample size;2)The item parameters and the length of the test have significant positive effects on the diagnostic accuracy based on BP neural network;3)The number of attributes has a negative impact on the classification accuracy based on BP neural network;4)The item parameters will affect the classification accuracy of different attribute hierarchy in cognitive diagnosis based on BP neural network. |
| |
| Keywords: | BP neural network cognitive diagnostic assessment accuracy of classification test quality test technique |
| 本文献已被 维普 等数据库收录！ |
