图书情报工作

图书情报工作 >

2024 , Vol. 68 >Issue 21: 133 - 144

DOI: https://doi.org/10.13266/j.issn.0252-3116.2024.21.012

知识组织

引用功能感知的知识单元引用网络构建与多维分析

  • 王佳敏 ,
  • 房子辰 ,
  • 窦永香
展开
  • 西安电子科技大学经济与管理学院 西安 710126
王佳敏,讲师,博士,硕士生导师,提出研究思路,设计实验方案,撰写和修订论文,E-mail:wangjiamin@xidian.edu.cn;房子辰,硕士研究生,资料收集,修订论文;窦永香,教授,博士,博士生导师,修订论文。

收稿日期: 2024-03-11

  修回日期: 2024-06-21

  网络出版日期: 2024-11-09

基金资助

本文系国家自然科学基金青年项目“基于文本语义理解的跨学科知识结构识别与演进路径研究”（项目编号：72304218）和教育部人文社科研究青年基金项目“语义功能感知的科学知识网络建模与多维分析研究”（项目编号：22YJC870015）研究成果之一。

收起

Construction and Multidimensional Analysis of a Citation Function-aware Knowledge Unit Citation Network

  • Wang Jiamin ,
  • Fang Zichen ,
  • Dou Yongxiang
Expand
  • School of Economics and Management, Xidian University, Xi'an 710126

Received date: 2024-03-11

  Revised date: 2024-06-21

  Online published: 2024-11-09

Supported by

This work is supported by the National Natural Science Foundation of China project titled “Research on the Identification and Evolution Path of Interdisciplinary Knowledge Structure Based on Text Semantic Understanding” (Grant No. 72304218) and Humanities and Social Science Foundation of the Ministry of Education of China titled “Research on Modeling and Multidimensional Analysis of Semantic Function-aware Scientific Knowledge Network” (Grant No. 22YJC870015).

Fold

摘要

[目的/意义] 针对知识单元引用网络中关联关系单一的局限，本文通过引用功能增强网络节点之间语义关联类型，提出一种引用功能感知的知识单元引用网络，并进行领域知识多维分析。[方法/过程] 首先对学术文本进行解析，抽取文献间引用关系、引文上下文以及引用对象等信息，并对引用功能和引用对象进行自动识别。在此基础上，采用复杂网络图方法构建引用功能感知的知识单元引用网络，从网络结构分析与可视化、知识单元多维引用关联分析、知识群落分析3个方面进行领域知识多维分析，并以国际计算语言学协会会议论文数据集为例进行实证研究。[结果/结论] 结果验证了本文所提出方法的有效性，发现了特定领域知识间使用、扩展和对比模式，丰富了知识群落的语义信息。本文扩展了知识单元引用网络的研究方法，深层次揭示了学科知识之间的语义关联，为学科知识结构分析提供了一种新的路径。

关键词： 知识单元引用网络; 引用功能; 引用对象; 知识群落; 知识关联

本文引用格式

王佳敏 , 房子辰 , 窦永香 . 引用功能感知的知识单元引用网络构建与多维分析[J]. 图书情报工作, 2024 , 68(21) : 133 -144 . DOI: 10.13266/j.issn.0252-3116.2024.21.012

Abstract

[Purpose/Significance] Aiming at the limitation of single associations in knowledge unit citation network, this paper enhances the semantic association types between network nodes through citation function, proposes a citation function-aware knowledge unit citation network, and conducts multi-dimensional analysis of domain knowledge. [Method/Process] Firstly, the academic text was parsed to extract information such as citation links, citation context and citation objects, and their citation functions were identified. On this basis, the complex network method was used to construct a citation function-aware knowledge unit citation network, and the multidimensional analysis of domain knowledge was carried out from the citation network structure and visualization, multidimensional citation relationship of knowledge units, and knowledge community. The proceedings of ACL (Association for Computational Linguistics) were used as an example for empirical research. [Result/Conclusion] The results verify the effectiveness of the proposed method, discover the usage, extension and comparison patterns among domain knowledge, and enrich the semantic information of knowledge communities. This study extends the research method of knowledge unit citation network, deeply reveals the semantic relationships between discipline knowledge, and provides a new path for analyzing discipline knowledge structure.

Key words： knowledge unit citation network; citation function; citation object; knowledge community; knowledge associations

参考文献

[1] WANG X, HE J, HUANG H, et al. MatrixSim: a new method for detecting the evolution paths of research topics[J]. Journal of informetrics, 2022, 16(4): 101343.
[2] 陈果, 彭家彬, 肖璐. 基于“问题—方法”知识抽取的科研领域知识演化研究：以人工智能为例[J]. 情报理论与实践, 2022, 45(6): 32-38. (CHEN G, PENG J B, XIAO L. Knowledge evolution of scientific research domains based on problem-solution knowledge extraction: a case study of artificial intelligence[J]. Information studies: theory & application, 2022, 45(6): 32-38.)
[3] 赵一鸣, 尹嘉颖. 语义增强型全文本共词网络的构建与分析[J]. 情报学报, 2023, 42(10): 1187-1198. (ZHAO Y M, YIN J Y. Construction and analysis of semantic-enhanced full-text co-occurrence network[J]. Journal of the China Society for Scientific and Technical Information, 2023, 42(10): 1187-1198.)
[4] WANG J, CHENG Q, LU W, et al. A term function–aware keyword citation network method for science mapping analysis[J]. Information processing & management, 2023, 60(4): 103405.
[5] YANG J, WU L, LYU L. Research on scientific knowledge evolution patterns based on ego-centered fine-granularity citation network[J]. Information processing & management, 2024, 61(4): 103766.
[6] 黄文彬, 王冰璐, 步一, 等. 关键词共引分析的科学计量方法研究[J]. 情报资料工作, 2018(2): 37-42. (HUANG W B, WANG B L, BU Y, et al. A study on scientometrics of co-citation analysis of keywords[J]. Information and documentation services, 2018(2): 37-42.)
[7] HSIAO T, CHEN K. The dynamics of research subfields for library and information science: an investigation based on word bibliographic coupling[J]. Scientometrics, 2020, 125(1): 717-737.
[8] CHENG Q, WANG J, LU W, et al. Keyword-citation-keyword network: a new perspective of discipline knowledge structure analysis[J]. Scientometrics, 2020, 124(3): 1923-1943.
[9] 王佳敏, 陆伟, 程齐凯, 等. 基于细粒度关键词引用网络的领域知识多维分析[J]. 情报学报, 2022, 41(7): 733-744. (WANG J M, LU W, CHENG Q K, et al. Multi-dimensional analysis of domain knowledge based on a fine-grained keyword citation network[J]. Journal of the China Society for Scientific and Technical Information, 2022, 41(7): 733-744.)
[10] ZHANG X, XIE Q, SONG C, et al. Mining the evolutionary process of knowledge through multiple relationships between keywords[J]. Scientometrics, 2022, 127(4): 2023-2053.
[11] DING Y, SONG M, HAN J, et al. Entitymetrics: measuring the impact of entities[J]. PloS one, 2013, 8(8): e71416.
[12] SONG M, HAN N, KIM Y, et al. Discovering implicit entity relation with the gene-citation-gene network[J]. Plos one, 2013, 8(12): e84639.
[13] 毛进, 侯博文, 王依蒙. 基于知识元引用网络的细分领域演化特征研究[J]. 情报理论与实践, 2024, 47(2): 107-115. (MAO J, HOU B W, WANG Y M. Research on the evolution characteristics of subdivision fields based on knowledge unit citation networks[J]. Information studies: theory & application, 2024, 47(2): 107-115.)
[14] LEE K, JUNG H, SONG M. Subject–method topic network analysis in communication studies[J]. Scientometrics, 2016, 109(3): 1761-1787.
[15] 周萌, 陈果. 科技文本中术语细粒度共现关系抽取与可视化分析[J]. 情报科学, 2019, 37(3): 81-87. (ZHOU M, CHEN G. Fine-grained co-occurrence relations extraction and visualization analysis in technical texts[J]. Information science, 2019, 37(3): 81-87.)
[16] 吴蕾, 梁晓贺, 宋红燕. 基于超网络的科技论文关键词关联分析[J]. 情报学报, 2020, 39(3): 253-258. (WU L, LIANG X H, SONG H Y. A method of keywords association analysis of scientific papers based on super-network[J]. Journal of the China Society for Scientific and Technical Information, 2020, 39(3): 253-258.)
[17] 章成志, 谢雨欣, 宋云天. 学术文本中细粒度知识实体的关联分析[J]. 图书馆论坛, 2021, 41(3): 12-20. (ZHANG C Z, XIE Y X, SONG Y T. Association analysis of fine-grained knowledge entities in academic texts[J]. Library tribune, 2021, 41(3): 12-20.)
[18] 陈翔, 黄璐, 倪兴兴, 等. 基于动态语义网络分析的主题演化路径识别研究[J]. 情报学报, 2021, 40(5): 500-512. (CHEN X, HUANG L, NI X X, et al. Identifying topic evolutionary pathways through dynamic semantic network analytics[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(5): 500-512.)
[19] 杨金庆, 庞业佳, 刘智锋, 等. “问题—方法”关联视角下领域知识创新网络演化机制研究——以信息资源管理学科群为例[J]. 图书情报工作, 2024, 68(10): 97-108. (YANG J Q, PANG Y J, LIU Z F, et al. Research on the evolution mechanism of domain knowledge innovation network from the perspective of “issue-method” correlation: taking the discipline group of information resources management as an example[J]. Library and information service, 2024, 68(10): 97-108.)
[20] 陆伟, 孟睿, 刘兴帮. 面向引用关系的引文内容标注框架研究[J]. 中国图书馆学报, 2014, 40(6): 93-104. (LU W, MENG R, LIU X B. A deep scientific literature mining-oriented framework for citation content annotation[J]. Journal of library science in China, 2014, 40(6): 93-104.)
[21] NANBA H, KANDO N, OKUMURA M. Classification of research papers using citation links and citation types: towards automatic review article generation[C]//Proceedings of the 11th ASIS SIG/CR Classification Research Workshop. Chicago: ASIS, 2000: 117-134.
[22] HERNANDEZ-ALVAREZ M, SORIANO J, MARTINEZ-BARCO P. Citation function, polarity and influence classification[J]. Natural language engineering, 2017, 23(4): 561-588.
[23] ROMAN M, SHAHID A, KHAN S, et al. Citation intent classification using word embedding[J]. IEEE Access, 2021(9): 9982-9995.
[24] BUDI I, YANIASIH Y. Understanding the meanings of citations using sentiment, role, and citation function classifications[J]. Scientometrics, 2023, 128(1): 735-759.
[25] ZHANG Y, ZHAO R, WANG Y, et al. Towards employing native information in citation function classification[J]. Scientometrics, 2022, 127(11): 6557-6577.
[26] 马娜, 张智雄, 于改红. 科技论文引用对象研究综述[J]. 图书情报工作, 2019, 63(23): 139-145. (MA N, ZHANG Z X, YU G H. A review of citation object research[J]. Library and information service, 2019, 63(23): 139-145.)
[27] SMALL H. Cited documents as concept symbols[J]. Social studies of science, 1978, 8(3): 327-340.
[28] ANDERSON M, SUN P. What have scholars retrieved from Walsh and Ungson (1991)? A citation context study[J]. Management learning, 2010, 41(2): 131-145.
[29] KHALID A, KHAN F, IMRAN M, et al. Reference terms identification of cited articles as topics from citation contexts[J]. Computers & electrical engineering, 2019, 74: 569-580.
[30] 马娜, 张智雄, 吴朋民. 基于特征融合的术语型引用对象自动识别方法研究[J]. 数据分析与知识发现, 2020, 4(1): 89-98. (MA N, ZHANG Z X, WU P M. Automatic identification of term citation object with feature fusion[J]. Data analysis and knowledge discovery, 2020, 4(1): 89-98.)
[31] 唐晓波, 彭映寒. 科技论文引用对象和引文功能的联合自动识别方法研究[J]. 现代情报, 2022, 42(6): 38-48. (TANG X B, PENG Y H. Research on joint automatic recognition method of citation objects and their relationship in scientific papers[J]. Journal of modern information, 2022, 42(6): 38-48.)
[32] LOPEZ P. GROBID: combining automatic bibliographic data recognition and term extraction for scholarship publications[C]//Proceedings of international conference on theory and practice of digital libraries. Berlin: Springer, 2009: 473-474.
[33] BLONDEL V, GUILLAUME J, LAMBIOTTE R, et al. Fast unfolding of communities in large networks[J]. Journal of statistical mechanics: theory and experiment, 2008(10): P10008.
[34] HU Y. Efficient, high-quality force-directed graph drawing[J]. The mathematica journal, 2006, 10(1): 37-71.
Options
文章导航

/

〈 〉