媒体负面报道与公司财务困境预警——基于文本分析和机器学习

财经论丛 ›› 2023, Vol. 39 ›› Issue (9): 80-90.

媒体负面报道与公司财务困境预警——基于文本分析和机器学习

孙洁, 李能飞, 赵梦茹

天津财经大学会计学院,天津 300222

收稿日期:2022-05-19 出版日期:2023-09-10 发布日期:2023-09-12
通讯作者: 李能飞(1995—),女,甘肃会宁人,天津财经大学会计学院博士生
作者简介:孙洁(1979—),女,浙江瑞安人,天津财经大学会计学院教授;赵梦茹(1995—),女,河北石家庄人,天津财经大学会计学院博士生。
基金资助:
国家自然科学基金面上项目(72271174;71771162);2022年天津市研究生科研创新项目(2022BKY227)

Negative Media Coverage and Corporate Financial Distress Prediction: Based on Text Analysis and Machine Learning

SUN Jie, LI Nengfei, ZHAO Mengru

School of Accounting, Tianjin University of Finance and Economics, Tianjin 300222, China

Received:2022-05-19 Online:2023-09-10 Published:2023-09-12

摘要/Abstract

摘要： 本文运用文本挖掘和自然语言处理技术,对2011—2021年沪深A股上市公司的媒体负面报道进行文本分析,构建了媒体负面报道数量、报道标题/内容文本语调和情感倾向三个维度的变量。基于概念漂移视角,采用集成分类器XGBoost构建了公司财务困境动态预警模型。实证结果表明:在公司特征变量的基础上,融入媒体负面报道变量后,财务困境动态预警模型的总体分类性能增强,模型的第一类错误率明显降低。考虑稀有事件偏差和内生性后,媒体负面报道数量、文本语调和情感倾向与公司是否发生财务困境仍然显著相关。本文的研究结论表明媒体负面报道包含公司财务困境预警的增量信息,媒体负面报道在公司财务困境预警过程中发挥了重要的外部公司治理作用。

关键词: 媒体负面报道, 财务困境预警, 概念漂移, 文本分析, 机器学习

Abstract: This paper firstly uses text mining and natural language processing techniques to analyze the text of negative media coverage of A-share listed companies in Shanghai Stock Exchange and Shenzhen Stock Exchange from 2011 to 2021, and then constructs variables in the following three dimensions: The number of negative media coverage, the textual tone of the headlines/content of the coverage, and the emotional tendency. Based on the concept drift perspective, an ensemble classifier XGBoost is used to construct a dynamic financial distress prediction model. The empirical results show that the dynamic financial distress prediction model that combines negative media coverage variables with firm feature variables can enhance the overall classification performance and reduce the type I error rate. After considering the rare event bias and endogeneity, the study finds that the number of negative media coverage, the text tone and emotional tendency of headlines/content are still significantly correlated with whether a company has financial distress. The conclusion of this paper shows that negative media coverage contains the incremental information of corporate financial distress prediction, and negative media coverage plays an important role in external corporate governance in the process of corporate financial distress prediction.

Key words: Negative Media Coverage, Financial Distress Prediction, Concept Drift, Text Analysis, Machine Learning

中图分类号:

F832.51

孙洁, 李能飞, 赵梦茹. 媒体负面报道与公司财务困境预警——基于文本分析和机器学习[J]. 财经论丛, 2023, 39(9): 80-90.

SUN Jie, LI Nengfei, ZHAO Mengru. Negative Media Coverage and Corporate Financial Distress Prediction: Based on Text Analysis and Machine Learning[J]. Collected Essays on Finance and Economics, 2023, 39(9): 80-90.

参考文献

[1]Beaver W. Financial Ratios as Predictors of Failure[J]. Journal of Accounting Research, 1966, 4(1): 71-111.
[2]熊艳, 李常青, 魏志华. 媒体“轰动效应”: 传导机制、经济后果与声誉惩戒——基于“霸王事件”的案例研究[J]. 管理世界, 2011, (10): 125-140.
[3]饶育蕾, 彭叠峰, 成大超. 媒体注意力会引起股票的异常收益吗? ——来自中国股票市场的经验证据[J]. 系统工程理论与实践, 2010, (2): 287-297.
[4]Guest N. M. The Information Role of the Media in Earnings News[J]. Journal of Accounting Research, 2021, 59(3): 1021-1076.
[5]Burke J., Hoitash R., Hoitash U. Auditor Response to Negative Media Coverage of Client Environmental, Social, and Governance Practices[J]. Accounting Horizons, 2019, 33(3): 1-23
[6]An Z., Chen C., Naiker V., Wang J. Does Media Coverage Deter Firms from Withholding Bad News? Evidence from Stock Price Crash Risk[J]. Journal of Corporate Finance, 2020, 64: 101664.
[7]汪昌云, 武佳薇. 媒体语气、投资者情绪与IPO定价[J]. 金融研究, 2015, (9): 174-189.
[8]李培功. 媒体报道偏差的经济学分析[J]. 经济学动态, 2013, (4): 145-152.
[9]李焰, 王琳. 媒体监督、声誉共同体与投资者保护[J]. 管理世界, 2013, (11): 130-143, 188.
[10]Kelly S., Ahmad K. Estimating the Impact of Domain-Specific News Sentiment on Financial Assets[J]. Knowledge-Based Systems, 2018, 150(JUN. 15): 116-126.
[11]Du H., Hao J., He F., Xi W. Media Sentiment and Cross-Sectional Stock Returns in the Chinese Stock Market[J]. Research in International Business and Finance, 2022, 60: 101590.
[12]应千伟, 呙昊婧, 邓可斌. 媒体关注的市场压力效应及其传导机制[J]. 管理科学学报, 2017, (4): 32-49.
[13]李培功, 沈艺峰. 媒体的公司治理作用: 中国的经验证据[J]. 经济研究, 2010, (4): 14-27.
[14]王昱, 杨珊珊. 考虑多维效率的上市公司财务困境预警研究[J]. 中国管理科学, 2021, (2): 32-41.
[15]Sun J., Fujita H., Zheng Y., Ai W. Multi-Class Financial Distress Prediction Based On Support Vector Machines Integrated with the Decomposition and Fusion Methods[J]. Information Sciences, 2021, 559: 153-170.
[16]刘笑霞, 李明辉, 孙蕾. 媒体负面报道、审计定价与审计延迟[J]. 会计研究, 2017, (4): 88-94, 96.
[17]姚加权, 冯绪, 王赞钧, 等. 语调、情绪及市场影响: 基于金融情绪词典[J]. 管理科学学报, 2021, (5): 26-46.
[18]甘丽凝, 陈思, 胡珉, 等. 管理层语调与权益资本成本——基于创业板上市公司业绩说明会的经验证据[J]. 会计研究, 2019, (6): 27-34.
[19]谢德仁, 林乐. 管理层语调能预示公司未来业绩吗? ——基于我国上市公司年度业绩说明会的文本分析[J]. 会计研究, 2015, (2): 20-27, 93.
[20]Saina H., Purnamiba S. W. Combine Sampling Support Vector Machine for Imbalanced Data Classification[J]. Procedia Computer Science, 2015, 72(1): 59-66.
[21]Brown I., Mues C. An Experimental Comparison of Classification Algorithms for Imbalanced Credit Scoring Data Sets[J]. Expert Systems with Applications, 2012, 39(3): 3446-3453.
[22]Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System[J]. ACM, 2016. DOI:10. 1145/2939672. 2939785.
[23]Petropoulos A., Siakoulis V. Can Central Bank Speeches Predict Financial Market Turbulence? Evidence from an Adaptive NLP Sentiment Index Analysis Using XGBoost Machine Learning Technique[J]. Central Bank Review, 2021, 21(4): 141-153.
[24]Bao Y., Ke B., Li B., Yu Y., Zhang J. Detecting Accounting Fraud in Publicly Traded U. S. Firms Using a Machine Learning Approach[J]. Journal of Accounting Research, 2020, 58(1): 199-235.
[25]孙洁, 李辉, 韩建光. 基于滚动时间窗口支持向量机的财务困境预测动态建模[J]. 管理工程学报, 2010, (4): 174-180, 92.
[26]李成刚, 贾鸿业, 赵光辉, 等. 基于信息披露文本的上市公司信用风险预警——来自中文年报管理层讨论与分析的经验证据[J]. 中国管理科学, 2023, (2): 18-29.
[27]吴璇, 田高良, 司毅, 等. 网络舆情管理与股票流动性[J]. 管理科学, 2017, (6): 51-64.