基于阅读价值的科技文献排序方法研究  

Method on Ranking of Scientific Papers Based on Reading Value

作　　者：张光前[1] 刘欣[1] 冯永琴[1] 

机构地区：[1]大连理工大学管理学院,大连116024

出　　处：《情报学报》2009年第6期844-850,共7页Journal of the China Society for Scientific and Technical Information

基　　金：国家自然科学基金面上项目（70872015,70573017）;教育部博士点基金新教师项目（20070141037）;大连理工大学人文社科基金项目（DUTHS2008301）.

摘　　要：科技文献的准备是开展科研工作的必须步骤和重要基础,而当前从电子期刊数据库中检索到的相关文献往往成百上千篇。如何判断一篇文献的阅读价值,并快速准确地获得相关知识,成为科技文献服务方面的一个共性需求。本文针对在科研工作中需要快速对文献按阅读价值进行排序并获得相关知识这一共性需求,以PageRank算法为基础,提出并验证了一种综合考虑文献的内容、期刊、作者、时间等反映文献阅读价值的因素对文献进行排序的PaperRank方法。该方法在得到依据文献阅读价值的排序结果的同时,还可获得在某一问题或领域研究中的重要作者和重要文献等相关知识。The preparation of scientific literature is a necessary step and an important foundation of the scientific work, but at present there are always hundreds and thousands of related papers which are searched from the electronic journal database. In the scientific literature service, how to estimate the reading value of a scientific paper and then obtain the related knowledge quickly and accurately is a common requirement. In view of this common requirement, the paper provides a method named PaperRank for ranking scientific papers based on Google＇s PageRank, and then validates it by an experiment. PaperRank method synthetically considers those factors which reflecting the reading value of the papers such as content, journal, author and published time, and it can be used to obtain not only the ranking results of the papers, but also the knowledge of the important authors and papers in a certain problem or field.

关 键 词：文献排序 PaperRank方法 PAGERANK算法 知识服务 

分 类 号：G255.75[文化科学—图书馆学] F204[经济管理—国民经济]