Central banks have increased their official communications. Previous literature measures complexity, clarity, tone and sentiment. Less explored is the use of fact versus emotion in central bank communication. We test a new method for classifying factual versus emotional language, applying a pretrained transfer learning model, fine-tuned with manually coded, task-specific and domain-specific data sets. We find that the large language models outperform traditional models on some occasions; however, the results depend on a number of choices. We therefore caution researchers from depending solely on such models even for tasks that appear similar. Our findings suggest that central bank communications are not only technically but also subjectively difficult to understand.
