Automated Detection of Emotion in Central Bank Communication: A Warning
.avif)
Can LLMs help us better understand the role of emotion in central bank communication?
Abstract
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.
Economic Dynamism
The Causal Effect of News on Inflation Expectations
This paper studies the response of household inflation expectations to television news coverage of inflation.
.avif)
The Rise of Inflation Targeting
This paper discusses the interactions between politics and economic ideas leading to the adoption of inflation targeting in the United States.
.jpg)
.jpg)
Why Can't the Middle Class Invest Like Mitt Romney?
Why can’t middle-income Americans pay effectively no taxes on investments like the wealthy do?
The Revenge of the Supply-Siders
Trump would do well to heed his supply-side advisers again and avoid the populist Keynesian shortcuts of stimulus checks or easy money.
