基于自动分词技术的国家宏观科技创新政策发展量化评价研究  

Research on Quantitative Evaluation of the Development of National Macro Science and Technology Innovation Policy Based on Automatic Word Segmentation Technology

作　　者：刘旭 LIU Xu(Institute of Science and Technology Information of China,Beijing 100038)

机构地区：[1]中国科学技术信息研究所,北京100038

出　　处：《全球科技经济瞭望》2020年第10期66-76,共11页Global Science，Technology and Economy Outlook

摘　　要：本研究基于自动分词技术,通过对一段时间内国家科技管理部门发布的具有代表性的规范性文件进行量化评价研究,在词频统计的基础上,引入资讯检索与文本挖掘常用加权技术TF-IDF,评估单一字词对于文本整体的重要程度,从而进一步整理出科技部党组1号文件中常年出现的高频词、体现时代特点的高频词和近年新出现的高频词,对比具有特点的高频词,从而深入梳理国家宏观科技创新政策的发展脉络,对我国宏观科技创新政策进行深入研究。The study is based on automatic word segmentation technologies to have quantitative evaluation research on the typical regulation documents issued by national managing bodies of science and technology.Based on word frequency statistics,information retrieval,text mining,and TF-IDF(a very common weighted technology)are adopted to evaluate the importance of a single word on the text as a whole.Then it summarizes the No.1 Documents of the Ministry of Science and Technology,hence figuring out the high-frequency words seen in past years,the high-frequency words indicative of the characteristics of times,and the high-frequency words newly emerged in recent years.By comparing the high-frequency words with special characteristics,it probes into the development history and current status of national macroscopic technological innovative policies.

关 键 词：自动分词技术 科技创新政策 高频词 量化评价研究 

分 类 号：G311[文化科学]