Curated Measures

Cardinal Risk Comparison

Explore the seven topic-specific Risk measures used in Hassan et al. (2025) — AI, Brexit, COVID-19, Inflation, Russia, Supply Chain, and Trade — through a maintained implementation of the paper's sentence-level methodology.

Updated Jul 11, 2026 5 series 483 viewers 10 downloaders

Sign in to download curated-measure data

Preview

You can browse series and charts without an account. Downloads become available after you sign in, based on your plan.

  • Plans at a glance: Free: selected Curated Measures included. Standard: time-series for every series, firm panels at 1 credit per series. Research: time-series and firm panels for every series.

Overview

The Key Business Risks Monitor contains the seven topic-specific Risk measures used in the cardinal risk decomposition in Figure 3 of Hassan et al. (2025), "Text as Data in Economic Analysis":

  • AI Risk
  • Brexit Risk
  • COVID-19 Risk
  • Inflation Risk
  • Russia Risk
  • Supply Chain Risk
  • Trade Risk

The measures retain the paper’s topic definitions and sentence-level construction. The dataset is updated using the currently available corpus, so its current values may differ from the published figure unless the paper's sample, period, and aggregation choices are also applied.

This curated dataset is intentionally limited to the seven measures used in the JEP analysis.

Why comparability matters

Risk indicators are often constructed using different units and baselines. Their movements can be compared, but their magnitudes usually cannot.

The seven JEP measures share the same sentence-level construction. The paper compares their contribution to overall risk discussion by dividing each topic-specific Risk measure by Overall Risk.

This makes it possible to ask questions such as:

  • Was Supply Chain risk more prominent than Inflation risk?
  • When did COVID-19 become the dominant source of risk discussion?
  • How did AI risk compare with established business risks?
  • How did the relative ranking of business risks change around a specific shock?
  • Which firms, sectors, or countries experienced the largest increase in Trade or Russia risk?

This is what we mean by cardinal risk decomposition: each topic's contribution is expressed as a share of all risk-related discussion for the selected sample and period.

How to interpret the measures

The downloadable call-level Risk measure is a raw sentence count.

A higher value means that more sentences in the call contained both:

  1. Language matching the topic query.
  2. Language associated with risk or uncertainty.

The raw Risk measure is not itself a percentage, probability, forecast, or estimate of financial losses.

When the data are presented as a JEP-style risk decomposition, the value is calculated as:

> Topic share of risk (%) = 100 × Topic Risk ÷ Overall Risk

Here:

  • Topic Risk is the number of sentences matching both the topic query and the Risk dictionary.
  • Overall Risk is the number of sentences containing Risk-dictionary language, whether or not they match a particular topic.

For example, if 20 sentences discuss Supply Chain risk and 200 sentences contain risk or uncertainty language overall, Supply Chain accounts for 10% of overall risk discussion.

The seven topics are not intended to exhaust every source of corporate risk. A sentence may also match more than one topic, so the topic shares do not necessarily sum to 100%.

Measures included

AI Risk

Tracks sentences that match the AI query and also contain language associated with risk or uncertainty.

Brexit Risk

Tracks sentences that match the Brexit query and also contain language associated with risk or uncertainty.

COVID-19 Risk

Tracks sentences that match the COVID-19 query and also contain language associated with risk or uncertainty.

Inflation Risk

Tracks sentences that match the Inflation query and also contain language associated with risk or uncertainty.

Russia Risk

Tracks sentences that match the Russia query and also contain language associated with risk or uncertainty.

Supply Chain Risk

Tracks sentences that match the Supply Chain query and also contain language associated with risk or uncertainty.

Trade Risk

Tracks sentences that match the Trade query and also contain language associated with risk or uncertainty.

What researchers can study

The dataset can support applications including:

  • Reproducing and extending the cardinal risk decomposition in the JEP paper.
  • Tracking which business risks dominate corporate discussion.
  • Identifying changes in the relative ranking of risks.
  • Comparing risk discussions across firms, sectors, countries, and time.
  • Studying how the prominence of individual risks changes around economic shocks.
  • Connecting aggregate changes to the underlying corporate text.
  • Using the call-level measures in statistical and economic analysis.

Explore the data

Series

5 total

Browse the related series and open any series for its full query, filters, and methodology notes.

Methodology and data

The measures follow the sentence-level construction documented by NL Analytics and used for the corresponding topic-specific Risk measures in Hassan et al. (2025).

1. Define the topic query

Each measure has a documented query containing keywords and phrases associated with its topic.

For a given topic k, define:

> Topic match(s, k) = 1 when sentence s contains at least one term matching topic query k.

Otherwise:

> Topic match(s, k) = 0

The complete query for each measure is available on its individual page.

2. Identify risk-related sentences

The Risk dictionary is the deduplicated union of Oxford Thesaurus synonyms for:

  • risk
  • risky
  • uncertain
  • uncertainty

The terms question, questions, and venture are excluded.

For these measures, the topic match and Risk-dictionary language must occur in the same sentence.

Define:

> Risk match(s) = 1 when sentence s contains at least one Risk-dictionary term.

Otherwise:

> Risk match(s) = 0

3. Calculate the call-level Risk measure

For earnings call c and topic k:

> Risk(c, k) = Σ Topic match(s, k) × Risk match(s)
> for all sentences s in call c

In plain language:

> Topic Risk is the number of sentences in an earnings call that contain at least one topic-query match and at least one risk or uncertainty synonym.

Each sentence is counted at most once for a given topic, even if it contains multiple query terms or multiple Risk-dictionary terms.

Overall Risk is calculated as:

> Overall Risk(c) = Σ Risk match(s)
> for all sentences s in call c

In plain language:

> Overall Risk is the number of sentences in an earnings call that contain at least one risk or uncertainty synonym, regardless of topic.

4. Calculate the JEP-style risk decomposition

For a selected firm, group of firms, or period:

> Topic share of risk (%) = 100 × Topic Risk ÷ Overall Risk

The numerator and denominator must be aggregated over the same calls and period.

This is the construction used for the cardinal risk decomposition in Figure 3 of Hassan et al. (2025). That figure compares AI, Brexit, COVID-19, Inflation, Russia, Supply Chain, and Trade.

Research considerations

The measures capture topic-linked risk discussion. They do not estimate the probability of an event, its objective severity, or its expected financial cost.

Results depend on the topic queries and selected sample. Researchers should inspect matched sentences, document the queries used, retain calls with zero matches, and account for changes in sample composition.

To reproduce the JEP figure, researchers must also match the paper’s sample, date range, aggregation, and smoothing choices.

The maintained dataset extends the measures to currently available data. It should therefore be described as a maintained implementation of the paper’s measures, not as an exact replication of the published figure.

Academic foundation

All seven measures in this curated dataset are used in the cardinal risk decomposition in:

Tarek A. Hassan, Stephan Hollander, Aakash Kalyani, Laurence van Lent, Markus Schwedeler, and Ahmed Tahoun. “Text as Data in Economic Analysis.” Journal of Economic Perspectives 39(3), 2025, pp. 193–220.

Figure 3 of the paper compares AI, Brexit, COVID-19, Inflation, Russia, Supply Chain, and Trade as shares of overall corporate risk discussion.

For exact replication of the published results, use the paper’s replication package and follow its sample and aggregation choices.

References

Kalyani, A. & Hassan, T. & Hollander, S. & van Lent, L. & Schwedeler, M. & Tahoun, A., "Text as Data in Economic Analysis," Journal of Economic Perspectives, 39(3):193-220 (2025)

NL Analytics. (2026). Cardinal Risk Comparison [Data set]. NL Analytics. https://apps.nlanalytics.tech/curated-measures/cardinal-risk-comparison/