TL;DR
Get smart everyday buys delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
A Swiss National Bank working paper by Severin Joho and Enzo Rossi examines 1,063 speeches by senior bank officials from 1928 through 2024. It reports more frequent speeches, shorter and more accessible language, and greater emphasis on inflation during the flexible-exchange-rate era.
Severin Joho and Enzo Rossi have published a Swiss National Bank working paper analyzing 1,063 speeches by high-ranking officials from 1928 to 2024. The study finds that speeches became more frequent, shorter and more accessible over time, while inflation gained prominence in the bank’s public discussion during the flexible-exchange-rate era.
The paper, published on the SNB website, examines the frequency, length, readability and themes of officials’ speeches across nearly a century. The authors say annual speech frequency followed an upward trajectory from the mid-1950s, with a stronger rise after Switzerland moved to flexible exchange rates. They also report a clear shift toward shorter speeches.
On language, the analysis finds that speeches became increasingly accessible from the 1960s onward. In thematic terms, inflation moved to the forefront of policy discourse in the flexible-rate period, while cyclical economic development and unemployment received less emphasis. These are patterns in the speech corpus; the study does not, in the supplied summary, quantify the size of each change or establish why it occurred.
To compare analytical approaches, Joho and Rossi benchmarked conventional Python-based text mining against ChatGPT. Their report describes the methods as complementary and discusses methodological lessons, algorithmic pitfalls and open questions for future research. The supplied summary does not provide detailed model settings or the results of individual benchmark tests.
How SNB Communication Changed
The findings offer a long-run view of how a central bank’s public communication has changed in form as well as subject matter. More frequent, briefer and more accessible speeches could affect how audiences encounter policy explanations, while the increased focus on inflation points to a change in the issues most prominent in official rhetoric. The paper describes patterns in communication, not evidence that those changes directly altered policy or public understanding.
The methodological comparison also matters beyond this one speech archive. Researchers increasingly use large language models to analyze text, but the authors’ emphasis on pairing ChatGPT with deterministic Python methods highlights the need to check generated interpretations against reproducible analysis. The report flags potential algorithmic pitfalls rather than presenting AI-generated results as a substitute for validation.
Python data science books for text analysis and natural language processing
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
A Century of SNB Speeches
The dataset covers speeches delivered by senior Swiss National Bank officials between 1928 and 2024. That span includes distinct monetary-policy settings, allowing the authors to compare communication before and after the transition to flexible exchange rates. The source summary identifies the mid-1950s as the start of a general rise in annual speech frequency and says the increase accelerated after that transition.
The research is a working paper published by the SNB, rather than a policy announcement. Its subject is how officials communicated and which themes appeared in their speeches. The authors’ use of both text-mining frameworks is part of the paper’s investigation into how such historical material can be analyzed, as well as a discussion of limitations in applying language models to central-bank communication.
“The frequency of annual speeches has followed an upward trajectory since the mid-1950s, accelerating notably after the transition to flexible exchange rates.”
— Severin Joho and Enzo Rossi, in the working paper summary
natural language processing with Python books NLTK spaCy
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Limits of the Reported Findings
The SNB’s supplied summary does not give the precise year of the exchange-rate transition, numerical measures of changes in speech frequency or length, or the readability metrics used. It also does not show how the authors classified themes or detail how closely the Python and ChatGPT results agreed. Those details are needed to assess the size and robustness of the reported patterns.
The findings describe the language and topics in speeches; they do not, on the information provided, establish the reasons for the shifts or their effects on monetary decisions, markets or public audiences. The paper itself identifies algorithmic pitfalls and open research questions, but the summary does not specify every limitation or provide further results from the comparison.
computational text analysis research methods books
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Further Testing of Text Methods
The paper points to future research questions about applying large language models to central-bank communication and stresses that probabilistic models should be used alongside deterministic methods. Its publication does not announce a policy change or a specific follow-up study. Further assessment would depend on the paper’s full methods and results, including the benchmarks and validation procedures behind its headline findings.
large language models for social science research books
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Key Questions
What did the SNB working paper study?
It analyzed 1,063 speeches by high-ranking Swiss National Bank officials from 1928 through 2024, looking at frequency, length, readability and themes.
What changes did the authors report?
The authors report more frequent speeches from the mid-1950s, a stronger rise after the move to flexible exchange rates, shorter speeches, and more accessible language from the 1960s. They also say inflation became more prominent in the flexible-rate era.
How did the researchers use ChatGPT?
They benchmarked ChatGPT against Python-based text-mining methods to analyze the speech corpus. The supplied summary says the approaches can complement one another and notes algorithmic risks, but does not give detailed benchmark results.
Does the study explain why speech topics changed?
Not in the supplied summary. It reports shifts in speech frequency and themes, but does not establish why those changes happened or whether they affected policy or public understanding.
Source: primary
Fall Picks
fall essentials
As an affiliate, we earn on qualifying purchases.
