System for Scanning and Monitoring Science and Technology Policy Texts of US and EU

Authors

Dahai YU, Department of Information Management, Peking University, Beijing 100871
Aofei CHANG, Department of Information Management, Peking University, Beijing 100871
Bolin HUA, Department of Information Management, Peking University, Beijing 100871
Hongguang WANG, Department of Information Management, Peking University, Beijing 100871
Wenjiao ZHENG, HongKong University Business School, Hongkong 999077

Keywords

science and technology policy; web crawler; machine learning; text mining; information extraction

Abstract

[Purpose/significance]Science and technology policy plays a guiding role in the development of science and technology. Whether science and technology policies are efficient and reasonable has an important impact on the rapid development of science and technology. In order to help decision-makers grasp the latest international scientific and technological layout, planning and policy guidance more quickly, especially to track and analyze the scientific, and technological policies of major developed countries in Europe and the United States, grab analyze and mine the corresponding scientific and technological policy texts in real time, has of great significance in the current international environment.[Method/process]This research designed and implemented a scanning and monitoring system for science and technology policy texts in Europe and the United States, which mainly includes a four-tier architecture of database layer, data entity layer, business logic layer and interface layer. It realizes the functions of regular collection, translation, keyword extraction, technology entity extraction,automatic summary, policy text classification and evolution analysis, and provides important decision support for the formulation and planning of science and technology policies.[Result/conclusion]The text scanning and monitoring system of European and American S&T policies is helpful to monitor the latest update, grasp the evolution trend, and spy on the planning and layout of European and American science and technology policies, and provide complete information support and decision-making reference for the formulation, planning and improvement of China's S&T policies.

First Page

43

Recommended Citation

YU, Dahai; CHANG, Aofei; HUA, Bolin; WANG, Hongguang; and ZHENG, Wenjiao (2023) "System for Scanning and Monitoring Science and Technology Policy Texts of US and EU," Scientific Information Research: Vol. 5: Iss. 1, Article 4.
Available at: https://eng.kjqbyj.com/journal/vol5/iss1/4

Reference

[1] National Science and Technology Council.The Science of Science Policy：A Federal Research Roadmap Report on the Science of Science Policy to the Subcommittee on Social，Behavioral and Economic Sciences，Committee on Science，National Science and Technology Council，Office of Science and Technology Policy[R].Washington，DC：Subcommittee on Social，Behavioral and Economic Sciences，2008.
[2] MITSUMORI S.Report on the AAAS Forum on Science and Technology Policy[R].Washington，DC：American Association for the Advancement of Science，2007.
[3] 杜建，武夷山.我国科技政策学研究态势及国际比较[J].科学学研究，2017，35（09）：1289-1300.
[4] 丁洁兰，刘细文，杨立英，等.科学计量方法在科技政策研究中应用的实证研究[J].图书情报工作，2017，61（24）：77-86.
[5] 曾利，李自力，李洋.国际科技政策计量与可视化分析[J].科研管理，2020，41（02）：11-25.
[6] 吴瑜，袁野，龚振炜.人工智能背景下中美科技政策比较研究：基于文本挖掘与可视化分析的视角[J].中国电子科学研究院学报，2019，14（08）：891-896.
[7] 刘建华，张智雄，张琴.基于多维政策实体及其关系的科技政策演化路径揭示方法研究[J].数据分析与知识发现，2019，3（05）：57-67.
[8] 赵绘存，高峰，闫杰.2007—2017年国际科技政策研究热点与前沿：基于科学知识图谱视角[J].科技管理研究，2018，38（03）：42-49.
[9] 陈瑜，李广建.科技政策效果评价及其发展趋势[J].图书与情报，2021（06）：96-106.
[10] 颜慧超，林洪，涂瑜，等.面向科技智库的科技创新政策监测体系构建研究[J].科技进步与对策，2020，37（24）：29-36.
[11] 张智雄，张晓林，刘建华，等.网络科技信息结构化监测的思路和技术方法实现[J].中国图书馆学报，2014，40（04）：4-15.
[12] 夏立新，杨金庆，程秀峰.基于情境感知技术的移动数据自动采集系统设计与实现[J].数据分析与知识发现，2017，1（05）：82-93.
[13] 马雨萌，黄金霞，王昉，等.基于政策文本量化研究的科技政策分析服务平台建设[J].情报科学，2022，40（07）：169-176，185.
[14] 孙壮珍.风险感知视域下科技政策调适机制分析[J].中国科技论坛，2018（10）：23-30，38.
[15] 于伟，王忠军.面向科技信息服务的人工智能技术应用[J].中国科技信息，2021（10）：68-70.
[16] 马雨萌，黄金霞，王昉，等.融合BERT与多尺度CNN的科技政策内容多标签分类研究[J].情报杂志，2022，41（11）：157-163.
[17] 许乾坤，刘耀.科技政策隐性扩散路径自组织研究[J].情报资料工作，2022，43（01）：61-70.
[18] 郑新曼，董瑜.基于科技政策文本的程度词典构建研究[J].数据分析与知识发现，2021，5（10）：81-93.
[19] KADHIM A I.Term weighting for feature extraction on Twitter：A comparison between BM25 and TF-IDF[C]//2019 International Conference on Advanced Science and Engineering，Zakho-Duhok：IEEE， 2019：124-128.
[20] 国务院.中国制造2025[EB/OL].（2015-5-8）[2022-10-28].http://www.gov.cn/zhengce/content/2015-05/19/content_9784.htm.
[21] CHANG A，HUA B L，YU D.Keyword Extraction and Technology Entity Extraction for Disruptive Technology Policy Texts[C]//USA：2nd EEKE@ JCDL.2021：36-40.Â
[22] ZHUANG L，WAYNE L，YA S，et al.A Robustly Optimized BERT Pre-training Approach with Post-training[C]//Proceedings of the 20th Chinese National Conference on Computational Linguistics，Hohhot：2021，12869：471-484.
[23] ZHENG W，HUA B.Named Entity Recognition for Science and Technology Policy Dynamics[C]//CEUR Workshop Proceedings，Shenyang：2022，3210：138-141.
[24] LEWIS M，LIU Y, GOYAL N，et al.Bart：Denoising Sequence-to-Sequence Pre-training for Natural Language Generation，Translation，and Comprehension[J/OL].（2019-10-29）[2022-10-28].https://arxiv.org/pdf/1910.13461.pdf.
[25] HINTON G，VINYALS O，DEAN J.Distilling the Knowledge in a Neural Network[J/OL].（2015-03-09）[2022-10-28].https://arxiv.org/pdf/1503.02531.pdf.
[26] SANH V，DEBUT L，CHAUMOND J，et al.DistilBERT，a distilled version of BERT：smaller，faster，cheaper and lighter[J/OL].（2019-10-02）[2022-10-28].https://arxiv.org/pdf/1910.01108v1.pdf.