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  

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

作　　者：张誉曜 陈媛媛 ZHANG Yuyao;CHEN Yuanyuan(College of computer science and technology,Xinjiang normal university,Urumqi 830001)

机构地区：[1]新疆师范大学计算机科学技术学院,乌鲁木齐830001

出　　处：《农业图书情报学报》2021年第4期35-44,共10页Journal of Library and Information Science in Agriculture

基　　金：2019年度国家社科基金项目“美国著名智库网络影响力及其启示研究”(19BTQ067)。

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。[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.

关 键 词：智库 文本挖掘 TextRank算法 批评话语 人工智能 

分 类 号：G249.2[文化科学]