Textual Analysis in Accounting: What's Next?

• 成果类型: Article
• 署名作者: Bochkay, Khrystyna; Brown, Stephen V.; Leone, Andrew J.; Tucker, Jennifer Wu
• 署名单位: Northwestern University; University of Connecticut; State University System of Florida; University of Florida; University of Miami
• 刊物名称: CONTEMPORARY ACCOUNTING RESEARCH
• ISSN/ISSBN: 0823-9150
• DOI: 10.1111/1911-3846.12825
• 发表日期: 2023
• 页码: 765-805
• 关键词: md-and-a; information-content; neural-networks; earnings; disclosure; READABILITY; management; COMPETITION; EMBEDDINGS; prediction

摘要

Natural language is a key form of business communication. Textual analysis is the application of natural language processing (NLP) to textual data for automated information extraction or measurement. We survey publications in top accounting journals and describe the trend and current state of textual analysis in accounting. We organize available NLP methods in a unified framework. Accounting researchers have often used textual analysis to measure disclosure sentiment, readability, and disclosure quantity; to compare disclosures to determine similarities or differences; to identify forward-looking information; and to detect themes. For each of these tasks, we explain the conventional approach and newer approaches, which are based on machine learning, especially deep learning. We discuss how to establish the construct validity of text-based measures and the typical decisions researchers face in implementing NLP models. Finally, we discuss opportunities for future research. We conclude that (i) textual analysis has grown as an important research method and (ii) accounting researchers should increase their knowledge and use of machine learning, especially deep learning, for textual analysis.