文本挖掘下的话语认知与构建——以人工智能和5G领域白宫新闻文本为例

doi:10.13998/j.cnki.issn1002-1248.20-0715

摘要/Abstract

摘要： [目的/意义]政府新闻文本是政策文本的表达形式之一。对政府新闻文本进行挖掘分析,能直观的展现表面动态,揭示对话事件的立场及其背后关系,能对情报分析工作、中国新型智库的发展建设,提供有效的助力。[方法/过程]文章利用TextRank算法进行核心句提取,并结合批评话语分析理论框架来做评估,以语料驱动从关键句、关键词两个宏观角度讨论政府决策态度,以词性从话语策略的微观角度总结美国官方对人工智能和5G领域的话语认知形象。[结果/结论]通过分析可以看出,美国政府对于人工智能和5G领域的态度将持续保持在“政府引领下的美国需优先”这一局面,面对发展中国家的科技竞争,增加政府政策性文本的指导无疑是最好的对策建议。

关键词: 智库, 文本挖掘, TextRank算法, 批评话语, 人工智能

Abstract: [Purpose/Significance] Government news text is one of the expression forms of [Purpose/Significance] Government news text is one of the forms of policy text. Text mining and analyzing the government news text can intuitively show the dynamics, reveal the position of dialogue events and the relationship between them, and improve the intelligence analysis work and promote the development and construction of China's new think tanks. [Method/Process] This paper uses the TextRank algorithm to extract core sentences, and evaluates it with the theoretical framework of critical discourse analysis (CDA). Using the corpus, the paper discusses the government's decision-making attitude from two macro perspectives of key sentences and keywords, and sums up the American official discourse cognitive image in the field of artificial intelligence and 5G from the micro perspective of discourse strategy. [Results/Conclusions] The analysis shows that the attitude of the US government towards artificial intelligence and 5G will continue to maintain the situation that "a priority to the United States under the guidance of the government needs ". In the face of technological competition in developing countries, depending on the guidance of the government in policy text is undoubtedly the best countermeasure.

Key words: think tank, text mining, TextRank algorithm, critical discourse, artificial intelligence

中图分类号:

G249.2

张誉曜, 陈媛媛. 文本挖掘下的话语认知与构建——以人工智能和5G领域白宫新闻文本为例[J]. 农业图书情报学报, 2021, 33(4): 35-44.

ZHANG Yuyao, CHEN Yuanyuan. Discourse Cognition and Construction Based on Text Mining: Taking the White House News Text in the Field of Artificial Intelligence and 5G as an Example[J]. Journal of Library and Information Science in Agriculture, 2021, 33(4): 35-44.

参考文献

[1] 段尧清, 何思奇, 林平. 基于新闻文本挖掘的政府态度识别实证研究[J]. 情报理论与实践, 2019(9): 86-92, 63.
DUAN Y Q, HE S Q, LIN P.Empirical research on government atti-tude recognition based on news text mining[J]. Intelligence theory and practice, 2019(9): 86-92, 63.
[2] 王世伟. 略论国家高端科技智库的功能定位[J]. 情报学报, 2018, 37(6): 590-599.
WANG S W.On the functional orientation of national high-end science and technology think tanks[J]. Journal of information, 2018, 37(6): 590-599.
[3] CONWAY B A, KENSKi K, WANG D.The rise of Twitter in the political campaign: searching for intermedia agenda-setting effects in the presidential primary[J]. Journal of computer-mediated com-munication, 2019.
[4] 常耀成. 基于多特征融合的图模型关键词提取方法研究[D]. 天津: 中国民航大学, 2018.
CHANG Y C.Research on keyword extraction method of graph model based on multi feature fusion[D]. Tianjin: Civil aviation uni-versity of China, 2018.
[5] 刘奇飞, 沈炜域. 基于Word2Vec和TextRank的时政类新闻关键词抽取方法研究[J]. 情报探索, 2018(6): 22-27.
LIU Q F, SHEN W Y.Research on keyword extraction method of current political news based on word2vec and textrank[J]. Intelli-gence exploration, 2018(6): 22-27
[6] 杨保军. 新闻文本的个性特征[J]. 当代传播, 2004(2): 10-11.
YANG B J.Personality of news text[J]. Contemporary communica-tion, 2004(2): 10-11.
[7] 田海龙. 语篇研究的批评视角: 从批评语言学到批评话语分析[J]. 山东外语教学, 2006(2): 40-47.
TIAN H L.Critical perspective of discourse research: From critical linguistics to critical discourse analysis[J]. Shandong foreign lan-guage teaching, 2006 (2): 40-47.
[8] 周锦章, 崔晓晖. 基于词向量与TextRank的关键词提取方法[J]. 计算机应用研究, 2019, 36(4): 1051-1054.
ZHOU J Z, CUI X H.Keyword extraction method based on word vector and textrank[J]. Computer application research, 2019, 36(4): 1051-1054.
[9] 宁建飞, 刘降珍. 融合Word2vec与TextRank的关键词抽取研究[J]. 现代图书情报技术, 2016(6): 20-27.
NING J F, LIU J Z.Research on keyword extraction integrating word2vec and textrank[J]. Modern library and information technology, 2016(6): 20-27.
[10] 夏天. 词向量聚类加权TextRank的关键词抽取[J]. 数据分析与知识发现, 2017, 1(2): 28-34.
XIA T.Keyword extraction of word vector clustering weighted textrank[J]. Data analysis and knowledge discovery, 2017, 1(2): 28-34.
[11] 李尚昊, 朝乐门. 文本挖掘在中文信息分析中的应用研究述评[J]. 情报科学, 2016, 34(8): 153-159.
LI S H, CHAO L M.Review on the application of text mining in Chinese information analysis[J]. Information science, 2016, 34(8): 153-159.
[12] 徐立. 基于加权TextRank的文本关键词提取方法[J]. 计算机科学, 2019, 46(s1): 142-145.
XU L.Text keyword extraction method based on weighted textrank[J]. Computer science, 2019, 46(S1): 142-145.
[13] 李志强, 潘苏含, 戴娟, 等. 一种改进的TextRank关键词提取算法[J]. 计算机技术与发展, 2020, 30(3): 77-81.
LI Z Q, PAN S H, DAI J, et al.An improved Textrank keyword ex-traction algorithm[J]. Computer technology and development, 2020, 30(3): 77-81.
[14] 赵芃. 2016年国内批评话语分析研究综述[J]. 天津外国语大学学报, 2017(4): 72-79.
ZHAO P. A review of critical discourse analysis in China in2016[J]. Journal of Tianjin foreign studies university, 2017(4): 72-79.
[15] 刘如, 张惠娜, 杜丽萍, 等. 基于情报3.0工作思路的自动简报系统设计与实现[J]. 情报学报, 2018, 37(2): 172-182.
LIU R, ZHANG H N, DU L P, et al.Design and implementation of automatic briefing system based on intelligence 3.0[J]. Journal of the China society for scientific and technical information, 2018, 37(2): 172-182.
[16] 杨敏, 符小丽. 基于语料库的"历史语篇分析"(DHA)的过程与价值——以美国主流媒体对希拉里邮件门的话语建构为例[J]. 外国语(上海外国语大学学报), 2018, 41(2): 77-85.
YANG M, FU X L.The process and value of corpus based "historical discourse analysis" (DHA): A case study of the discourse construction of Hillary Clinton's e-mail gate in American mainstream media[J]. Foreign languages (Journal of Shanghai foreign studies university), 2018, 41(2): 77-85.
[17] 李占芳, 彭梦莹. 美国主流新闻媒体对"中美贸易战"中双方形象的刻画——以《华盛顿邮报》为例[J]. 华北电力大学学报(社会科学版), 2019(5): 107-114.
LI Z F, PENG M Y.The portrayal of the images of the two sides in the "Sino US trade war" by the mainstream news media in the United States - Taking the Washington Post as an example[J]. Journal of north China electric power university (Social science edition), 2019 (5): 107-114.
[18] 刘文宇, 胡颖. 基于文本挖掘的非传统文本批评话语研究[J]. 天津外国语大学学报, 2020, 27(4): 29-41, 158-159.
LIU W Y, HU Y. Research on non-traditional text critical discourse based on text mining[J]. Journal of Tianjin foreign studies university, 2020, 27 (4): 29-41, 158-159.
[19] 彭红梅, 刘忠. 人工智能对国家安全的影响——基于美国四家智库的观点分析[J]. 社会科学文摘, 2020(8): 115-118.
PENG H M, LIU Z.The impact of artificial intelligence on national security: An analysis based on the views of four American think tanks[J]. Social science abstracts, 2020(8): 115-118.
[20] TEPEL T, GREGORY C.Allen: Understanding China's AI Strategy: Clues to Chinese strategic thinking on artificial intelligence and national security. Washington, D.C.: Center for a new American security February 2019[J]. SIRIUS - Ztschrift für strategische analysen, 2019, 3(3): 305-306.
[21] 赵洪, 王芳, 王晓宇, 等. 基于大规模政府公文智能处理的知识发现及应用研究[J]. 情报学报, 2018, 37(8): 805-812.
ZHAO H, WANG F, WANG X Y, et al.Research on knowledge discovery and application based on intelligent processing of large-scale government documents[J]. Journal of information, 2018, 37(8): 805-812.
[22] 段伟文. 控制的危机与人工智能的未来情境[J]. 探索与争鸣, 2017(10): 7-10.
DUAN W W.Crisis of control and future situation of artificial intelligence[J]. Exploration and contention, 2017(10): 7-10.
[23] Amandeep Singh Gill.Artificial intelligence and international security: The long view[J]. Ethics & international affairs, 2019, 33(2): 12-20.
[24] GUO L, VARGO C.The power of message networks: A big-data analysis of the network agenda setting model and issue ownership[J]. Mass communication & society, 2015, 18(5): 557-576.
[25] ZHENG P, LI X.Is social media for everyone?: The role of social capital and communication anxiety in structuring use of social networking sites[J]. Journal of social media studies, 2016: 2.