- 无标题文档
查看论文信息

中文题名:

 基于文献的领域主题识别与层次构建方法研究    

姓名:

 邵明玥    

保密级别:

 公开    

论文语种:

 中文    

学科代码:

 120102    

学科专业:

 信息管理与信息系统    

学生类型:

 学士    

学位:

 管理学学士    

学位年度:

 2018    

学校:

 北京师范大学    

校区:

 北京校区培养    

学院:

 政府管理学院    

第一导师姓名:

 陈翀    

第一导师单位:

 北京师范大学政府管理学院    

提交日期:

 2018-05-31    

答辩日期:

 2018-05-17    

外文题名:

 Research on Topic Identification and Topic Hierarchy Construction Based on Literature    

中文关键词:

 领域主题识别 ; 关键词提取 ; 领域层次构建 ; 标签树    

中文摘要:
随着当下学术环境的不断发展,学科交叉、学科跨领域以及学科细化逐渐增加,在各学科领域不断细分和融合的趋势下,衍生出许多新兴领域、学科以及研究方向。通过正确的识别领域的主题和领域层次结构,来扩展当下已有的典型领域分类体系,使其更加准确和完备,有助于各行各业对各领域的研究前沿有更直观的了解。因此,本研究基于前人对于领域划分方法的研究以及目前常用的典型领域划分体系的调研,提出一种基于文献的领域主题识别、领域关键词提取和领域层次划分的方法;同时,本研究以典型的领域划分体系作为评价依据,通过类似标签树的方式实现领域主题和层次的可视化呈现,以期为项目成果及专家成果的分类和管理提供基础。
外文摘要:
With the continuous development of the current academic environment, the cross-disciplines, cross-domain-disciplines and subject refinement have gradually increased. Under the trend of continuous subdivision and integration in various disciplines, many emerging fields, disciplines, and research directions have been derived. Through the correct identification of domain themes and domain hierarchies, the existing typical domain classification system is expanded to make it more accurate and complete, which will help all walks of life to have a more intuitive understanding of the research frontier in various fields. Therefore, this study is based on previous research on the method of domain division and the investigation of the commonly used typical field division system, and proposes a method based on literature for domain topic identification, domain keyword extraction, and domain hierarchy classification. Meanwhile, in the research, a typical domain division system is used as an evaluation basis to achieve a visual presentation of domain topics and levels through a similar tag tree approach, with a view to provide a basis for the classification and management of project achievements and expert results.
参考文献总数:

 44    

作者简介:

 北京师范大学信息管理与信息系统系本科生    

插图总数:

 12    

插表总数:

 13    

馆藏号:

 本120102/18003    

开放日期:

 2019-07-09    

无标题文档

   建议浏览器: 谷歌 360请用极速模式,双核浏览器请用极速模式