Automated Detection of Emotion in Central Bank Communication: A Warning
.webp)
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
Defending Technological Dynamism & the Freedom to Innovate in the Age of AI
Human flourishing, economic growth, and geopolitical resilience requires innovation—especially in artificial intelligence.
Partisan Trust in the Federal Reserve
This paper examines partisanship in public perceptions of the Federal Reserve.
It’s Not Easy, but We Can All Learn to Think like Adam Smith
To truly understand what a dynamic economy requires, we would do well to recover the 18th-century sensibility that understood dynamism as a social and cultural phenomenon as much as an economic one.
Locked Out of the Dream: Regulation Making Homes Unaffordable Around the World
The first in a two-part series on the global housing crisis.
.webp)
.webp)
Full Business Expensing Is the Key to Growth
Allowing businesses to immediately deduct the full cost of capital investment rather than depreciating it over many years unleashes real economic activity.
Adventures Among the Abundanauts
Can the Abundance theorists overcome an anti-growth, bureaucratic-driven Left?
.webp)
