结合α分层改进基于IRT计算机自适应题库系统  

Improvement of IRT computer adaptive item bank system based on the combination ofα stratification

作　　者：颜杰群[1] 

机构地区：[1]泉州经贸职业技术学院,福建泉州362000

出　　处：《齐齐哈尔大学学报（自然科学版）》2014年第4期23-25,共3页Journal of Qiqihar University(Natural Science Edition)

摘　　要：IRT理论中基于最大信息量函数的选题方法会使系统偏向于选取信息函数值最大的试题进行测验,容易造成部分试题被反复选取,导致试题的曝光度过高从而影响后期测验的有效性。本文在原有选题策略的基础上融入α分层和内容筛选,有效地提高了系统的有效性和安全性。The method of the maximum amount of information function based on IRT theory makes the system tend to choose the maximum value of test information function test, causing part of the test was repeated selection easily, resulting in a high visibility of test, thus affecting the effectiveness of post test. This paper combinesαstratification and content filtering based on the original selection strategies , effectively improving the effectiveness and safety of the system.

关 键 词：项目反应理论(IRT) 选题策略 信息函数I(θ) α分层 

分 类 号：TP317.1[自动化与计算机技术—计算机软件与理论]