基于项目评分预测技术的自适应试卷生成算法研究  

Self-adaptive test building algorithm based on Collaborative Filtering technique

作　　者：巩玉玺[1] 罗容[1] 

机构地区：[1]青岛理工大学计算机工程学院,青岛266033

出　　处：《青岛理工大学学报》2007年第2期86-89,共4页Journal of Qingdao University of Technology

摘　　要：自适应学习是当前网络教育中的一个研究热点.将项目评分预测技术引用到自适应试卷生成算法中,利用题目之间的相似性预测学习者对未评分题目的评分,在此基础上采用一种新颖的相似性度量方法计算目标学习者的最近邻居,构造自适应的试卷系统.实验结果表明,本算法可以有效解决学习者初始学习时评分数据极端稀疏情况下传统相似性度量方法存在的问题,显著提高自适应试卷生成系统的质量.Self-adaptive learning system is a hotpot on the net education. This paper brings forward a new self-adaptive algorithm based on collaborative filtering technique. This method predicts item ratings that the user has not been rated by the similarity of items, then takes a new similarity measure to find the target user＇s neighbors. The experiment results suggest that this method can efficiently improve the extreme sparsity of user rating data, improve a quality of self-adaptive test building system.

关 键 词：自适应 项目评分预测 试卷生成 

分 类 号：G434[文化科学—教育学]