一种基于SVD和Rough集的信息过滤方法  

A New Method for Information Filter Based on SVD and Rough Sets

作　　者：陈彩云[1] 李治国[1] 

机构地区：[1]南开大学组合数学研究中心,天津300071

出　　处：《计算机工程与应用》2003年第34期99-101,共3页Computer Engineering and Applications

基　　金：国家自然科学基金;国家973基础研究发展项目(编号:G19980306);教育部;科技部基金

摘　　要：论文提出了一种信息过滤方法,即在奇异值分解(SVD)的基础上,运用粗糙集(Rough Sets)理论进行信息过滤。通过对词语×文档矩阵进行奇异值分解得出近似矩阵,改变了一些词语在相应文档中的重要性,从而使得词语更好地体现文档内容。然后运用粗糙集理论中决策表上的规则推理方法,生成人们感兴趣信息的规则库,将未知文档的条件属性与规则库中的规则进行相似匹配,进行信息过滤。实验表明,该方法在准确度方面比传统的VSM和LSI要好。This paper proposes a new method for information filter based on Rough Sets theory and SVD.The authors have changed the importance of terms in corresponding documents by singular value decompose(SVD).Then they generate the rules which are useful to us based on the decision tables of Rough Set theory .When an unknown document is inputted,they just match approximately the condition property of the document to these rules and remained useful infor-mation.The experiment proves that the method is better than traditional VSM and LSI in precision.

关 键 词：奇异值分解粗糙集 信息过滤 规则提取 

分 类 号：G202[文化科学—传播学]