一种基于重叠社区标签传播的学科划分方法

doi:10.13998/j.cnki.issn1002-1248.20-0307

农业图书情报学报 ›› 2021, Vol. 33 ›› Issue (1): 41-52.doi: 10.13998/j.cnki.issn1002-1248.20-0307

一种基于重叠社区标签传播的学科划分方法

遆慧颖, 耿骞, 靳健^*

北京师范大学政府管理学院,北京 100875

收稿日期:2020-04-23 出版日期:2021-01-05 发布日期:2021-02-05
通讯作者: ^*靳健（ORCID：0000-0002-3239-22942）,副教授,博士。Email：jinjian.jay@bnu.edu.cn
作者简介:遆慧颖（ORCID：0000-0003-2885-7252）,女,本科,北京师范大学政府管理学院。耿骞（ORCID：0000-0001-5064-49962）,教授,博士。
基金资助:
国家自然科学基金项目“差异化客户需求的提取及比较研究：基于产品在线评论的挖掘分析”（71701019）

A COPRA Based Algorithm for Subject Division

TI Huiying, GENG Qian, JIN Jian^*

School of Government, Beijing Normal University, Beijing 100875

Received:2020-04-23 Online:2021-01-05 Published:2021-02-05

摘要/Abstract

摘要： [目的/意义]以Wikipedia为代表的网络百科全书收录了海量的概念。但在此类百科全书中,概念与概念之间、概念与学科之间以及学科与学科之间的关系缺乏明确的划分。这使得初步接触某一学科的查询者很难高效地系统性地获取该领域相关知识。[方法/过程]为获取某特定学科领域信息,更好地组织知识,本研究提出一种用于对各学科边界进行划分的方法。本研究将复杂网络分析方法引入文本主题划分领域,利用主题模型构建了主题文本网络,并在此基础上改进了重叠社区标签传播算法,实现学科领域的边界划分。[结果/结论]本研究以300个Wikipedia词条文本为样本,证明了该方法的有效性。通过多组实验,分析了词条网络的相关社团结构以及学科领域的复杂性,为构建学科构建领域知识库奠定基础。

关键词: 学科领域, 复杂网络, 重叠社团, 主题模型

Abstract: [Purpose/Significance] Online encyclopedias such as Wikipedia include a large number of concepts. However, in such encyclopedias, there are no clear divisions between concepts and concepts, between concepts and disciplines, and between disciplines and disciplines. It embarrasses junior researchers regarding a certain discipline to obtain domain relevant knowledge in a systematic and low-efficiency manner. [Method/Process] To obtain information in a specific subject area and organize knowledge better, a new algorithm is designed for subject division. Specifically, approaches in complex network analysis are introduced for subject division, which helps to build a topic text network by the classical topic model. Then, the overlapping community label propagation algorithm is improved to identify the boundaries of different subject divisions. [Results/Conclusions] Finally, 300 Wikipedia entry texts were investigated as samples to evaluate the effectiveness of the proposed algorithm. Categories of experiments were conducted to analyze the community structure of the entry network and the complexity of the subject division, which helps to provide a corpus to build a subject knowledge base.

Key words: subject division, complex network, overlapping community, topic model

中图分类号:

G302

遆慧颖, 耿骞, 靳健. 一种基于重叠社区标签传播的学科划分方法[J]. 农业图书情报学报, 2021, 33(1): 41-52.

TI Huiying, GENG Qian, JIN Jian. A COPRA Based Algorithm for Subject Division[J]. Journal of Library and Information Science in Agriculture, 2021, 33(1): 41-52.

参考文献

[1] 陈文勇. 情报学:学科还是领域[J]. 情报科学, 2007, 25(8): 1135-1140.
CHEN W Y.Informatics: A discipline or all area?[J]. Information science, 2007, 25(8): 1135-1140.
[2] 程军. 基于统计的文本分类技术研究[D]. 北京: 中国科学院研究生院, 2003.
CHENG J.Statistics-based text classification[D]. Beijing: A dissertation for the doctoral degree of management in the library of Chinese academy of science, 2003.
[3] PAVLINEK M, PODGORELEC V.Text classification method based on self-training and LDA topic models[J]. Expert systems withapplications, 2017, 28(80): 83-93.
[4] LILLEBERG J, ZHU Y, ZHANG Y.Support vector machines and word2vec for text classification with semantic features[C]//IEEE, 2015 IEEE 14th international conference on cognitive informatics & cognitive computing (ICCI*CC), Beijing: IEEE, 2015: 136-140.
[5] 邓三鸿, 傅余洋子, 王昊. 基于模型的中文图书多标签分类研究[J]. 数据分析与知识发现, 2017, 1(7): 52-60.
DENG S H, FU Y Y Z, WANG H. Multi-label classification of Chinese books with LSTM model[J]. Data analysis and knowledge discovery, 2017, 1(7): 52-60.
[6] 刘晋宏. 基于用户生成内容的多标签文本分类方法的研究与实现[D]. 北京: 北京邮电大学, 2018.
LIU J H.Research and implementation of multi-label text classification based on user generated content[D]. Beijing: Beijing University of Posts and Telecommunications, 2018.
[7] 刘心惠, 陈文实, 周爱, 等. 基于LSTM模型的中文图书多标签分类研究[J]. 计算机工程与应用, 2020, 1(1): 1-10.
LIU X H, CHEN W S, ZHOU A, et al.Multi-label text classification based on joint model[J]. Computer engineering and applications, 2020, 1(1): 1-10.
[8] 曹一家, 陈晓刚, 孙可. 基于复杂网络理论的大型电力系统脆弱线路辨识[J]. 电力自动化设备, 2006, 13(12): 1-5.
CAO Y J, CHEN X G, SUN K.Identification of vulnerable lines in power gridbased on complex network theory[J]. Electric power automation equipment, 2006, 13(12): 1-5.
[9] 张彦超, 刘云, 张海峰, 等. 基于在线社交网络的信息传播模型[J]. 物理学报, 2011, 60(5): 66-72.
ZHANG Y C, LIU Y, ZHANG H F, et al.The research of information dissemination model on online social network[J]. Acta physica
10 sinica, 2011, 60(5): 66-72.
[10] 高自友, 赵小梅, 黄海军, 等. 复杂网络理论与城市交通系统复杂性问题的相关研究[J]. 交通运输系统工程与信息, 2006, 6(3): 41-47.
GAO Z Y, ZHAO X M, HUANG H J, et al.Research on problems related to complex networks and urban traffic systems[J]. Journal of transportation systems engineering and information technology, 2006, 6(3): 41-47.
[11] 段文奇, 刘宝全, 季建华. 国际贸易网络拓扑结构的演化[J]. 系统工程理论与实践, 2008, 28(10): 71-75.
DUAN W Q, LIU B Q, JI J H.Topological structure evolution of world trade network[J]. Systems engineering-theory & practice, 2008, 28(10): 71-75.
[12] 郭迟. 基于复杂网络的Internet脆弱性研究[D]. 武汉: 武汉大学, 2010.GUO C. Research on internet vulnerability based on complex networks theory[D]. Wuhan: Wuhan university, 2010.
[13] 赵辉, 刘怀亮, 范云杰. 复杂网络理论在中文文本特征选择中的应用研究[J]. 现代图书情报技术, 2012, 33(9): 23-28.
ZHAO H, LIU H L, FAN Y J.Study on the application of complex network theory in Chinese text feature selection[J]. Data analysis
14 and knowledge discovery, 2012, 33(9): 23-28.
[14] 尹丽英, 赵捧未. 基于语义网络社团划分的中文文本分类研究[J]. 图书情报工作, 2014, 58(19): 124-128.
YI L Y, ZHAO P W.A Chinese text classification algorithm based on partitioning community in semantic network[J]. Library and information service, 2014, 58(19): 124-128.
[15] LANDAUER T K, DUMAIS S T.A solution to Plato's problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge[J]. Psychological review, 1997, 104(2): 211-240.
[16] DEERWESTER S, DUMAIS S T, FURNAS G W, et al.Indexing by latent semantic analysis[J]. Journal of the American society for information science, 1990, 41(6): 391-407.
[17] BLEI D M, NG A Y, JORDAN M I, et al.Latent dirichlet allocation[J]. Journal of machine learning research, 2003, 3(1): 993-1022.
[18] 陈秀平. 基于Markov随机游走的渐进式半监督文本分类研究[D]. 南昌: 江西师范大学, 2012.
CHEN X P.Research on progressively semi-supervised text classification based on Markov random walk[D]. Nanchang: Jiangxi normal university, 2012.
[19] 付常雷. 一种基于NEWMAN快速算法改进的社团划分算法[J]. 计算机技术与发展, 2018, 28(1): 33-35.
FU C L.A community partitioning algorithm based on improved Fast-Newman algorithm[J]. Computer technology and development, 2018, 28(1): 33-35.
[20] 边青全. 基于动力学模型的网络社团检测算法研究[D]. 西安: 西安电子科技大学, 2018.
BIAN Q Q.Research on network community detection algorithm based on dynamic model[D]. Xi'an: Xidian university, 2018.
[21] KOTHARI R, JAIN V.Learning from labeled and unlabeled data[C]//IEEE proceedings of the 2002 international joint conference on neural networks, IJCNN' 02 (cat, No, 02CH37290), Honolulu, HI, USA: IEEE, 2002: 2803-2808.
[22] RAGHAVAN U N, ALBERT, RéKA, KUMARA S. Near linear time algorithm to detect community structures in large-scale networks[J]. Physical review e, 2007, 76(3): 036106-11.
[23] GREGORY, STEVE.Finding overlapping communities in networks by label propagation[J]. New journal of physics, 2010, 12(10): 103018-26.
[24] 饶仁杰. 改进的多标签传播算法在重叠社团挖掘中的研究[D]. 西安: 西安理工大学, 2018.
RAO R J.Research of improved multi-label propagation algorithm used in overlapping community detection[D]. Xi'an: Xi'an university of technology, 2018.
[25] 杜长江, 王志晓, 邢贞明. 基于多标签传播的重叠社区发现优化算法[J]. 数据采集与处理, 2018, 33(2): 288-298.
DU C J, WANG Z X, XING Z M.Overlapping community detection algorithm based on improved Multi-Label propagation[J]. Journal of data acquisition and processing, 2018, 33(2): 288-298.

一种基于重叠社区标签传播的学科划分方法

A COPRA Based Algorithm for Subject Division

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	王威威, 化柏林. 公共文化智慧化描述信息抽取与挖掘[J]. 农业图书情报学报, 2021, 33(8): 13-23.
[2]	赵磊, 章成志. 基于不同内容层面的特定领域研究主题差异分析研究[J]. 农业图书情报学报, 2021, 33(5): 14-27.
[3]	黄山, 蒲泓宇, 马捷. 基于复杂网络的智慧政务信息协同效应测度[J]. 农业图书情报学报, 2020, 32(5): 19-30.
[4]	叶春蕾, 宁璐. 基于文献计量和主题模型的近十年中国现代农业科学技术研究态势分析[J]. 农业图书情报学刊, 2016, 28(10): 77-82.