{"title":"Can the text features of regulatory inquiry letters predict companies’ financial restatements? Evidence from China","authors":"Chao Zhang, Zenghao Cao, Zhimin Li, Weidong Zhu, Yong Wu","doi":"10.1108/k-12-2023-2605","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>Since the implementation of the regulatory inquiry system, research on its impact on information disclosure in the capital market has been increasing. This article focuses on a specific area of study using Chinese annual report inquiry letters as the basis. From a text mining perspective, we explore whether the textual information contained in these inquiry letters can help predict financial restatement behavior of the inquired companies.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>Python was used to process the data, nonparametric tests were conducted for hypothesis testing and indicator selection, and six machine learning models were employed to predict financial restatements.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>Some text feature indicators in the models that exhibit significant differences are useful for predicting financial restatements, particularly the proportion of formal positive words and stopwords, readability, total word count and certain textual topics. Securities regulatory authorities are increasingly focusing on the accounting and financial aspects of companies' annual reports.</p><!--/ Abstract__block -->\n<h3>Research limitations/implications</h3>\n<p>This study explores the textual information in annual report inquiry letters, which can provide insights for other scholars into research methods and content. Besides, it can assist with decision making for participants in the capital market.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>We use information technology to study the textual information in annual report inquiry letters and apply it to forecast financial restatements, which enriches the research in the field of regulatory inquiries.</p><!--/ Abstract__block -->","PeriodicalId":49930,"journal":{"name":"Kybernetes","volume":"121 1","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Kybernetes","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1108/k-12-2023-2605","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, CYBERNETICS","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose
Since the implementation of the regulatory inquiry system, research on its impact on information disclosure in the capital market has been increasing. This article focuses on a specific area of study using Chinese annual report inquiry letters as the basis. From a text mining perspective, we explore whether the textual information contained in these inquiry letters can help predict financial restatement behavior of the inquired companies.
Design/methodology/approach
Python was used to process the data, nonparametric tests were conducted for hypothesis testing and indicator selection, and six machine learning models were employed to predict financial restatements.
Findings
Some text feature indicators in the models that exhibit significant differences are useful for predicting financial restatements, particularly the proportion of formal positive words and stopwords, readability, total word count and certain textual topics. Securities regulatory authorities are increasingly focusing on the accounting and financial aspects of companies' annual reports.
Research limitations/implications
This study explores the textual information in annual report inquiry letters, which can provide insights for other scholars into research methods and content. Besides, it can assist with decision making for participants in the capital market.
Originality/value
We use information technology to study the textual information in annual report inquiry letters and apply it to forecast financial restatements, which enriches the research in the field of regulatory inquiries.
期刊介绍:
Kybernetes is the official journal of the UNESCO recognized World Organisation of Systems and Cybernetics (WOSC), and The Cybernetics Society.
The journal is an important forum for the exchange of knowledge and information among all those who are interested in cybernetics and systems thinking.
It is devoted to improvement in the understanding of human, social, organizational, technological and sustainable aspects of society and their interdependencies. It encourages consideration of a range of theories, methodologies and approaches, and their transdisciplinary links. The spirit of the journal comes from Norbert Wiener''s understanding of cybernetics as "The Human Use of Human Beings." Hence, Kybernetes strives for examination and analysis, based on a systemic frame of reference, of burning issues of ecosystems, society, organizations, businesses and human behavior.