图书情报工作

图书情报工作 >

2018 , Vol. 62 >Issue 14: 62 - 71

DOI: https://doi.org/10.13266/j.issn.0252-3116.2018.14.008

情报研究

基于主题变迁的领域发展路径智能化识别——以人工智能为例

  • 周源 ,
  • 张超 ,
  • 唐杰 ,
  • 刘宇飞 ,
  • 张宇韬
展开
  • 1. 清华大学公共管理学院 北京 100084;
    2. 华中科技大学机械科学与工程学院 武汉 430074;
    3. 清华大学计算机系 北京 100084;
    4. 中国工程院战略咨询中心 北京 100088
周源(ORCID:0000-0002-9198-6586),副教授,博士生导师;张超(ORCID: 0000-0001-7612-9327),硕士研究生;唐杰(ORCID: 0000-0003-3487-4593),副教授,博士生导师;张宇韬(ORCID:0000-0002-5759-1230),博士研究生。

收稿日期: 2017-11-21

  修回日期: 2018-03-14

  网络出版日期: 2018-07-20

基金资助

本文系国家自然科学基金"支持技术预见的多源异构大数据融合与时序文本预测方法研究"（项目编号：91646102）和国家自然科学基金"面向 2035 的中国工程科技发展路线图绘制理论与方法研究"（项目编号：L1624045）研究成果之一。

收起

Intelligent Identification of Field Development Trajectory Based on Topic Evolution: A Case Study of Artificial Intelligence

  • Zhou Yuan ,
  • Zhang Chao ,
  • Tang Jie ,
  • Liu Yufei ,
  • Zhang Yutao
Expand
  • 1. School of Public Policy and Management, Tsinghua University, Beijing 100084;
    2. School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074;
    3. Department of Computer Science and Technology, Tsinghua University, Beijing 100084;
    4. The CAE Center for Strategic Studies, Chinese Academy of Engineering, Beijing 100088

Received date: 2017-11-21

  Revised date: 2018-03-14

  Online published: 2018-07-20

Fold

摘要

[目的/意义]识别领域发展路径对于科技创新具有重要意义，但现有方法如专家访谈、引文分析等不能适应文献爆发性增长的现状，针对这一问题，提出一种基于主题变迁的领域发展路径识别方法。[方法/过程]该方法可以自动从Aminer平台获取数据，通过构建关键词-学者矩阵，综合使用KMeans++和谱聚类算法识别出研究主题和相关学者；通过相似度计算实现不同主题之间的关联，最终获得研究领域的发展路径并进行可视化展示。[结果/结论]通过对人工智能领域的实证分析，结果表明该方法能够有效反映领域研究主题的变迁，有助于研究者快速定位领域的研究热点和重点，丰富领域发展路径相关的研究方法。

关键词： 领域发展路径; 主题变迁; KMeans++; 谱聚类; 人工智能

本文引用格式

周源 , 张超 , 唐杰 , 刘宇飞 , 张宇韬 . 基于主题变迁的领域发展路径智能化识别——以人工智能为例[J]. 图书情报工作, 2018 , 62(14) : 62 -71 . DOI: 10.13266/j.issn.0252-3116.2018.14.008

Abstract

[Purpose/significance] Identifying the trajectory of development is of great importance to scientific and technological innovations. However, existing methods such as expert interviews and citation analysis cannot meet the current situation of the explosive growth of literature. In response to this problem, this paper proposes a new identification method of filed development trajectory. [Method/process] This method identifies the research topics and related scholars by using Kmeans ++ and spectral clustering algorithms with the keyword-scholar matrix, calculates the correlation between different topics, and finally visualizes the trajectory of developmen. [Result/conclusion] Through the empirical analysis of the field of artificial intelligence, the results show that the method can effectively reflect the evolution of the topic of field research, help researchers quickly locate popular research topics and focuses, and enrich the research methods related to the trajectory of field development.

Key words： field development trajectory; topic evolution; KMeans++; spectral clustering; artificial intelligence

参考文献

[1] RADZIEMSKI L J. From LASER to LIBS, the path of technology development[J]. Spectrochimica Acta part B:atomic spectroscopy, 2002, 57(7):1109-1113.
[2] 王纬. 德尔菲调查法与技术路线图结合的技术预测研究——以太原市"十二五"技术发展预测为例[J]. 中国科技论坛, 2011(4):103-107.
[3] 徐骥, 张卫国, 罗军. 基于技术路线图分析法和AHP的企业技术发展路径规划[J]. 科学学与科学技术管理, 2010, 31(11):13-18.
[4] 潘颖. 基于专利引证强度的关键技术发展路径研究[J]. 情报理论与实践, 2014, 37(12):71-75.
[5] 许冠南, 谢梦娇, 潘美娟,等. 3D打印产业技术的演变与预测研究——基于专利主路径分析[J]. 北京邮电大学学报(社会科学版), 2016, 18(4):77-85.
[6] 韩毅, 金碧辉. 基于连通性的引文网络结构分析新视角:主路径分析[J]. 科学学研究, 2012, 30(11):1634-1640.
[7] 秦晓慧, 乐小虬. 基于LDA主题关联过滤的领域主题演化研究[J]. 现代图书情报技术, 2015, 31(3):18-25.
[8] 赵迎光, 洪娜, 安新颖. 主题模型在主题演化方法中的应用研究进展[J]. 现代图书情报技术, 2014, 30(10):63-69.
[9] 洪宇, 张宇, 刘挺,等. 话题检测与跟踪的评测及研究综述[J]. 中文信息学报, 2007, 21(6):71-87.
[10] 崔雷, 王孝宁. 学科主题演变的深度挖掘分析——以普通外科学为例[J]. 医学信息学杂志, 2009, 30(8):5-10.
[11] 唐果媛, 张薇. 基于共词分析法的学科主题演化研究进展与分析[J]. 图书情报工作, 2015, 59(5):128-136.
[12] 刘志辉, 张志强. 作者关键词耦合分析方法及实证研究[J]. 情报学报, 2010, 29(2):268-275.
[13] 伍若梅, 孔悦凡. 共词分析与共引分析方法的比较研究[J]. 情报资料工作, 2010(1):26-29.
[14] 李纲, 巴志超. 共词分析过程中的若干问题研究[J]. 中国图书馆学报, 2017, 43(4):93-113.
[15] 李湘东, 张娇, 袁满. 基于LDA模型的科技期刊主题演化研究[J]. 情报杂志, 2014(7):115-121.
[16] 倪丽萍, 刘小军, 马驰宇. 基于LDA模型和AP聚类的主题演化分析[J]. 计算机技术与发展, 2016, 26(12):6-11.
[17] BLEI D, LAFFERTY J D. Dynamic topic models[C]//Proceedings of the 23rd international conference on machine learning.Pittsburgh:ACM, 2006:113-120.
[18] ROSEN-ZVI M, GRIFFITHS T, STEYVERS M, et al. The author-topic model for authors and documents[C]//Proceedings of the 20th conference on uncertainty in artificial intelligence.Arlington:AUAI Press, 2004:487-494.
[19] 史庆伟, 乔晓东, 徐硕,等. 作者主题演化模型及其在研究兴趣演化分析中的应用[J]. 情报学报, 2013, 32(9):912-919.
[20] CHANG J, BLEI D. Relational topic models for document networks[C]//Proceedings of the artificial intelligence and statistics.Clearwater Beach:JMLR.org,2009:81-88.
[21] 李杰,陈超美. Citespace:科技文本挖掘及可视化[M]. 北京:首都经济贸易大学出版社, 2016.
[22] HAVRE S, HETZLER E, WHITNEY P, et al. ThemeRiver:visualizing thematic changes in large document collections[J]. IEEE transactions on visualization & computer graphics, 2002, 8(1):9-20.
[23] CUI W, LIU S, TAN L, et al. TextFlow:towards better understanding of evolving topics in text[J]. IEEE transactions on visualization & computer graphics, 2011, 17(12):2412-2421.
[24] 刘萍, 郭月培, 郭怡婷. 利用作者关键词网络探测作者相似性[J]. 现代图书情报技术, 2013(12):62-69.
[25] LI H, ABE N. Word clustering and disambiguation based on co-occurrence data[C]//International conference on computational linguistics. Montreal:Association for Computational Linguistics, 1998:749-755.
[26] TANG J. AMiner:mining deep knowledge from big scholar data[C]//International conference companion on world wide Web.San Francisco:International World Wide Web Conferences Steering Committee, 2016:373-373.
[27] ROSE S,ENGEL D, CRAMER N, et al.Automatic Keyword Extraction from Individual Documents[M]//BERRY M W, KOGAN J.Text mining:applications and theory. Chichester:John Wiley & Sons,Ltd, 2010:1-20.
[28] ARTHUR D, VASSILVITSKⅡ S. k-means++:The advantages of careful seeding[C]//Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms.Philadelphia:Society for Industrial and Applied Mathematics, 2007:1027-1035.
[29] 周爱武, 于亚飞. K-Means聚类算法的研究[J]. 计算机技术与发展, 2011, 21(2):62-65.
[30] NG A Y, JORDAN M I, WEISS Y. On spectral clustering:analysis and an algorithm[C]//Advances in neural information processing systems. Vancouver:NIPS Foundation,2002:849-856.
[31] 刘志伟. 谱聚类中的相似度矩阵研究[J]. 现代计算机, 2010(15):67-69.
[32] 吕泽宇. 人工智能的历史、现状与未来[J]. 信息与电脑, 2016(13):166-167.
[33] 王丽雅. 基于CNKI的计算机科学学科半衰期分析[J]. 图书与情报, 2015(1):100-105.
[34] 田金萍. 人工智能发展综述[J]. 科技广场, 2007(1):230-232.
[35] LINDSAY R K, BUCHANAN B G, FEIGENBAUM E A, et al. DENDRAL:a case study of the first expert system for scientific hypothesis formation[J]. Artificial intelligence, 1993, 61(2):209-261.
[36] SAMPLE S, DJERASSI C. Mass spectrometry in structural and stereochemical problems[J].Journal of the American Chemical Society, 1966, 88(9):1937-1943.
[37] SUWA M, SCOTT A C, SHORTLIFFE E H. An approach to verifying completeness and consistency in a rule-based expert system[J]. AI magazine, 1982, 3(4):16.
[38] FARRENY H, PRADE H, WYSS E. Approximate reasoning in a rule-based expert system using posibility theory:a case study[M]. Paris:Laboratoire des Langages et systèmesinformatiques,1985:407-414.
[39] KJELDSEN R, COHEN P R. Evolution and performance of the grant system[J]. IEEE Expert-intelligent systems and their applications, 1987, 2(2):73-79.
[40] JENNINGS N R. On agent-based software engineering[J]. Artificial intelligence, 2000, 117(2):277-296.
[41] PAEK T, HORVITZ E. Uncertainty, Utility, and misunderstanding:a decision-theoretic perspective on grounding in conversational systems[J]. Proceedings of the aaai fall symposium on psychological models of communication in collaborative systems.Cape Cod:AAAI Press,1999:85-92.
[42] CRAVEN M, DIPASQUO D, FREITAG D, et al. Learning to extract symbolic knowledge from the World Wide Web[J]. Coastal management, 1998, 31(2):121-126.
[43] ZHOU H, YU H, HU R. Topic evolution based on the probabilistic topic model:a review[J]. Frontiers of computer science, 2017, 11(5):786-802.
Options
文章导航

/

〈 〉