首页 | 官方网站   微博 | 高级检索  
     

基于文本信息的上市中小企业财务困境预测研究
引用本文:陈艺云.基于文本信息的上市中小企业财务困境预测研究[J].运筹与管理,2022,31(4):136-143.
作者姓名:陈艺云
作者单位:华南理工大学 经济与金融学院,广东 广州 510006
基金项目:国家社会科学基金一般项目(15BJY149);广东省科技计划项目(2018A070712007);广东省哲学社科基金项目(GD18CGL15,GD17XYJ25);广州市哲学社科项目(2018GZGJ01,2018GZGJ03);华南理工大学中央高校基本科研业务费专项资金资助项目(ZKXM202108)
摘    要:本文通过网络爬虫获取上市中小企业相关的文本信息,包括以年报为代表的信息披露报告和互联网新闻媒体报道的文本内容,采用词袋方法基于不同特征词词表对这些文本内容进行了量化分析,并以财务变量模型为基础对文本信息量化指标在财务困境预测中的作用进行了实证检验,结果表明由信息披露报告构建的管理层语调变量以及由新闻媒体报道构建的报道倾向变量、负面报道比例变量确实可以提高财务困境模型的拟合度和预测能力,而且在对不同类型文本信息的分析应有不同的侧重点。尽管本文针对的是上市中小企业,但并未考虑市场交易信息,因而可以推广到未上市交易的中小企业。

关 键 词:财务困境  文本分析  管理层语调  报道倾向  
收稿时间:2020-04-03

Financial Distress Prediction for Listed SME Based on the Text Information
CHEN Yi-yun.Financial Distress Prediction for Listed SME Based on the Text Information[J].Operations Research and Management Science,2022,31(4):136-143.
Authors:CHEN Yi-yun
Affiliation:School of Economics and Finance, South China University of Technology, Guangzhou 510006, China
Abstract:Massive textual information about the listed small and medium-sized enterprises (SME) has been obtained from the Internet with the web crawler, including information disclosure by the enterprises and online news media reports. All the textual information has been quantified with the bag of words method, and added to the financial distress prediction model based on financial variables. The empirical results show the management tone based on the information disclosure, the media sentiment and the proportion of negative reports based on the online news media reports can be used to improve the fitness and predictive power of the financial distress prediction model. Additionally, different sources of textual information should be analyzed with different lists of words. Although only focusing on listed SME, no market information has been included in the analysis, so that the results can be extended to non-listed SME.
Keywords:financial distress  textual analysis  management tone  media sentiment  
点击此处可从《运筹与管理》浏览原始摘要信息
点击此处可从《运筹与管理》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号