The exploration of information extraction and analysis about science and technology policy in China

Author:

Zeng Wen,Yao Changqing,Li Hui

Abstract

Purpose Science and technology policy plays an important role in promoting the development of economic and social development in China. At present, the research on science and technology policy is mainly focused on the basic theories and some quantitative research. The analyses for contents of massive science and technology policies are relatively less. This paper makes use of semantic technologies to extract and analyze the relatively important information from massive science and technology policies. The purpose of this paper is to facilitate users to quickly and effectively obtain valuable information from the massive science and technology policies. The key methods and study results are presented in the paper. The study results can provide references for further study and application in China. Design/methodology/approach The paper presented the analysis model and method for science and technology policy in China. The terms and sentences are the important information in the science and technology policy. The study adopted the technology of natural language processing to analyze the linguistics characteristics of terms and combined with statistical analyses to extract the terms from Chinese science and technology policy. Then, the authors designed an algorithm, calculated and analyzed the important sentences in Chinese science and technology policies. The experiments were run on the Java test platform. Findings This paper put forward the analysis model and method for science and technology policy in China. The study obtained the following conclusions: term extraction of science and technology policy: the paper analyzed characteristic of terms in Chinese science and technology policy and designed a method of extracting a term that was suitable for the science and technology policy. The calculation of important sentences for science and technology policy: the paper designed an algorithm and calculated the importance of the sentences to obtain valuable information from the massive science and technology policies. Research limitations/implications In our methods, there are some defects to be improved or solved in the future. For example, the precision of algorithm needs to be improved. The significance of this paper is to propose and use the analysis model to process Chinese science and technology policy; we can provide an auxiliary tool to help policy beneficiaries. Enterprises and individuals can be more effective to extraction and mining information from massive science and technology policy and find the target policy. Practical implications To verify the effectiveness of the method, the paper selected the real policies about the new energy vehicles as experimental data; at the same time, the paper added uncorrelated policies. It used the proposed analysis model of science and technology policy to calculate and find out the relatively important sentences. The results of study showed that the proposed method can obtain better performance. It verified the validity of this method. The model and method have been applied to actual retrieval system. Social implications The proposed model and method in the paper have been applied to actual retrieval system for users. Originality/value The paper proposed the new analysis model and method to analyze science and technology policies in China. The presented model and method are a new attempt. According to the experimental results, this exploration and study are valuable. In addition, the idea and method will give a good start for improving information services of massive science and technology policies in China.

Publisher

Emerald

Subject

Library and Information Sciences,Computer Science Applications

Reference12 articles.

1. Creating a test corpus for term extractors through term annotation;Terminology,2014

2. Research on the methodology of science and technology policy;Science,2014

3. Science and technology policy based on the policy index;Science and Technology Progress and Countermeasures,2013

4. Automatic recognition of multi-word terms: the C-value/NC-value method;International Journal on Digital Libraries,2000

5. Research progress on automatic extraction of terms in Chinese domain;Computer Knowledge and Technology,2014

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Mining Scientific and Technical Literature;Trends and Applications of Text Summarization Techniques;2020

2. Study on Chinese Term Extraction Method Based on Machine Learning;Communications in Computer and Information Science;2018

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3