基于时间加权的生物医学文献知识发现的应用模型  

A Study of the Application of Publication Dates on Biomedical Literature-based Knowledge Discovery

作　　者：闵波[1] 张莉[1] 张云宏[1] 杨帆[1] 许文娟[1] 

机构地区：[1]新疆军区总医院,乌鲁木齐830000

出　　处：《情报学报》2017年第6期574-577,共4页Journal of the China Society for Scientific and Technical Information

基　　金：2015-2016年度中国图书馆学会医院图书馆委员会科研项目(Ytwkyxm15001)

摘　　要：科学假设的获取是文献知识发现研究的重要内容,目前主要通过挖掘文献集中潜在的间接关联来实现,而最新的文献通常更有助于科研工作者获得新的假设。因此,通过在文献知识发现过程中考虑时间因素对形成新关联的影响,建立基于时间加权的文献知识发现方法,测试发现选择近期文献富集而形成的热点词项作为种子词项,可以显著提高间接关联发现的准确率。Literature-based knowledge discovery can assist researchers in formulating scientific hypotheses by dis- covering potentially indirect associations, and the latest literature can help to track development in research. In this paper, we built a literature-based knowledge discovery model by integrating the effect of publication date and dem- onstrated the better performance of uncovering potential associations with terms-in-demand as seed terms. The results showed that the time-weighed literature-based discovery model improves the accuracy of knowledge discovery and facilitates the formulation of scientific hypotheses.

关 键 词：知识发现 文献挖掘 发表时间 复杂网络 

分 类 号：G353.1[文化科学—情报学] R-05[医药卫生]