Transfer Learning and Textual Analysis of Accounting Disclosures: Applying Big Data Methods to Small(er) Datasets
介绍并应用机器迁移学习方法分析会计披露，以BERT语言模型和季度盈余披露的情感分析为例，展示预训练、微调和上下文捕捉等概念，证明该方法易于实施、成本低且性能优于现有文本分析工具。
SYNOPSIS We introduce and apply machine transfer learning methods to analyze accounting disclosures. We use the examples of the new BERT language model and sentiment analysis of quarterly earnings disclosures to demonstrate the key transfer learning concepts of: (1) pre-training on generic “Big Data,” (2) fine-tuning on small accounting datasets, and (3) using a language model that captures context rather than stand-alone words. Overall, we show that this new approach is easy to implement, uses widely available and low-cost computing resources, and has superior performance relative to existing textual analysis tools in accounting. We conclude with suggestions for opportunities to apply transfer learning to address important accounting research questions. Data Availability: Data are available from the public sources cited in the text. JEL Classifications: G31; G32; M21; M41.