基于自动构建术语分类体系的公司划分研究——以新三板公司主营业务概念为例

doi:10.3772/j.issn.1000-0135.2021.05.005

情报学报

2021, Vol. 40

Issue (5): 479-488 DOI: 10.3772/j.issn.1000-0135.2021.05.005

情报分析方法与技术

本期目录 | 过刊浏览 | 高级检索

基于自动构建术语分类体系的公司划分研究——以新三板公司主营业务概念为例

黄文彬, 白浩东

北京大学信息管理系，北京 100871

The Study of Company Screening Method Based on Automatic Taxonomy Construction

Huang Wenbin, Bai Haodong

Department of Information Management, Peking University, Beijing 100871

摘要
图/表
参考文献
相关文章 (5)

全文: PDF (1416 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要在股权交易市场中，投资人对科学有效地发现新三板市场中，从事特定业务的公司集合的需求日益增长。新三板挂牌公司具有业务范围小、创新性高和交叉性强的特性，投资人依据主营业务找出业务相关或相似的公司集合，并进行对比分析是极为困难的工作。本文提出基于自动构建术语分类体系的方法，得到具有层次结构的公司划分结果，帮助投资人快速找到投资标的与理解公司间业务的关联。本文利用半监督方法从新三板公司年度报告的商业模式文本数据中抽取出业务术语，并根据术语相似度聚类建立术语分类体系，最后，利用公司所含业务术语决定所有公司划分的结果。本文的研究结果可以服务投资人发现股权交易市场中主流业务概念，明确概念与业务之间的映射关联，并作为选股的依据。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	黄文彬
	白浩东

关键词 ：投资分析, 术语分类体系, 文本挖掘

收稿日期: 2019-02-28

基金资助:国家社会科学基金一般项目“基于全文本分析的数据科学范式及其演化研究”（20BTQ054）。

作者简介: 黄文彬，男，1977年生，博士，长聘副教授，博士生导师，主要研究领域为数据分析、信息计量；白浩东，男，1995年生，硕士，主要研究领域为数据分析，E-mail：hbai@pku.edu.c；

引用本文:

黄文彬, 白浩东. 基于自动构建术语分类体系的公司划分研究——以新三板公司主营业务概念为例[J]. 情报学报, 2021, 40(5): 479-488.
Huang Wenbin, Bai Haodong. The Study of Company Screening Method Based on Automatic Taxonomy Construction. 情报学报, 2021, 40(5): 479-488.

链接本文:

http://qbxb.istic.ac.cn/CN/10.3772/j.issn.1000-0135.2021.05.005 或 http://qbxb.istic.ac.cn/CN/Y2021/V40/I5/479

1 Alford A W. The effect of the set of comparable firms on the accuracy of the price-earnings valuation method[J]. Journal of Accounting Research, 1992, 30(1): 94-108.
2 Bhojraj S, Lee C M C. Who is my peer? A valuation-based approach to the selection of comparable firms[J]. Journal of Accounting Research, 2002, 40(2): 407-439.
3 Phillips R L, Ormsby R. Industry classification schemes: an analysis and review[J]. Journal of Business & Finance Librarianship, 2016, 21(1): 1-25.
4 Barra M. Global industry classification standard (GICS)[R]. New York: Standard & Poor’s, 2009.
5 Bhojraj S, Lee C M C, Oler D K. What’s my line? A comparison of industry classification schemes for capital market research[J]. Journal of Accounting Research, 2003, 41(5): 745-774.
6 上海申银万国证券研究所有限公司. 申银万国行业分类标准[EB/OL]. [2018-12-08]. http://www.swsindex.com/idx0530.aspx.
7 全国中小公司股份转让系统有限责任公司. 挂牌公司投资型行业分类指引[EB/OL]. (2018-01-03) [2018-12-08]. http://www.neeq.com.cn/uploads/1/file/public/201801/20180103150009_p13ukun0hq.docx.
8 De Franco G, Kothari S P, Verdi R S. The benefits of financial statement comparability[J]. Journal of Accounting Research, 2011, 49(4): 895-931.
9 郭峰, 徐玉生, 陈晓云, 等. 基于信息提取的面向行业应用文本分类算法[J]. 清华大学学报(自然科学版), 2005, 45(S1): 1810-1813.
10 Hoberg G, Phillips G. Product market synergies and competition in mergers and acquisitions: a text-based analysis[J]. The Review of Financial Studies, 2010, 23(10): 3773-3811.
11 Hoberg G, Phillips G. Text-based network industries and endogenous product differentiation[J]. Journal of Political Economy, 2016, 124(5): 1423-1465.
12 Tetlock P C, Saar-Tsechansky M, Macskassy S. More than words: quantifying language to measure firms' fundamentals[J]. The Journal of Finance, 2008, 63(3): 1437-1467.
13 曹四华. 基于LDA主题模型上市公司年报文本知识发现[D]. 北京: 中国地质大学, 2016.
14 Wang C Y, He X F, Zhou A Y. A short survey on taxonomy learning from text corpora: issues, resources and recent advances[C]// Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2017: 1190-1203.
15 Hearst M A. Automatic acquisition of hyponyms from large text corpora[C]// Proceedings of the 14th Conference on Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 1992, 2: 539-545.
16 Vivaldi J, Màrquez L, Rodríguez H. Improving term extraction by system combination using boosting[C]// Proceedings of the European Conference on Machine Learning. Heidelberg: Springer, 2001: 515-526.
17 Fu R J, Guo J, Qin B, et al. Learning semantic hierarchies via word embeddings[C]// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2014, 1: 1199-1209.
18 de Knijff J, Frasincar F, Hogenboom F. Domain taxonomy learning from text: the subsumption method versus hierarchical clustering[J]. Data & Knowledge Engineering, 2013, 83: 54-69.
19 杜慧平, 何琳, 侯汉清. 基于聚类分析的自然语言叙词表的自动构建[J]. 国家图书馆学刊, 2007, 16(3): 44-49.
20 Meijer K, Frasincar F, Hogenboom F. A semantic approach for extracting domain taxonomies from text[J]. Decision Support Systems, 2014, 62: 78-93.
21 Choi M J, Tan V Y F, Anandkumar A, et al. Learning latent tree graphical models[J]. Journal of Machine Learning Research, 2011, 12(4): 1771-1812.
22 Elkan C, Noto K. Learning classifiers from only positive and unlabeled data[C]// Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2008: 213-220.
23 du Plessis M C, Niu G, Sugiyama M. Analysis of learning from positive and unlabeled data[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014, 1: 703-711.
24 Givoni I E, Chung C, Frey B J. Hierarchical affinity propagation[C]// Proceeding of the 27th Conference on Uncertainty in Artificial Intelligence. Barcelona: AUAI Press, 2011: 238-246.