Firm-level Risk

We just released a paper with early evidence on the firm-level impact of exposure to the coronavirus. The corresponding data is available on this website. The data contain measures of a given firm's exposure, sentiment and risk to epidemic diseases (covid-19, SARS, H1N1, Ebola, etc.) for a sample of firms from 81 countries between January 2002 and March 2020. Use our email sign-up if you wish to be notified of updates.

This website aggregates firm-level measures of exposure, risk, and sentiment constructed using textual analysis of quarterly earnings conference calls held by more than 11,000 listed firms in 81 countries. The data draws on work in three papers:

In our paper “Firm-Level Political Risk: Measurement and Effects,” as published in the Quarterly Journal of Economics , we construct measures of political sentiment and risk ranging from 2002 to 2020q1.


Reference & details

In "The Global Impact of Brexit Uncertainty," we extend this methodology to construct measures of the costs, benefits, and risks associated with specific shocks, such as the UK's decision to leave the EU. Our measures of Brexit exposure, risk, and sentiment are currently updated through the first quarter of 2019.


Reference & details

In a third paper, "Firm-level Exposure to Epidemic Disease: Covid-19, SARS, and H1N1," we apply the same methodology to construct measures of costs, benefits, and risks individual firms associate with the spread of Covid-19, SARS, H1N1, Ebola, Zika, and MERS, ranging 2002 to 2020q1.


Reference & details

Measures of Risk

Our measures of risk use simple tools from computational linguistics to quantify the share of the earnings call devoted to discussing risk in general, risks associated with politics, and risks associated with particular political topics, such as health care and economic policy.


Overall risk

Political risk

Non-political risk

Topic-specific political risk

Brexit risk

Risk related to the spread of epidemic diseases

Measures of Sentiment

Our measures of sentiment count positive and negative tone words used during the earnings call to measure the overall tone of the conversation, as well as call participants' optimism or pessimism associated with political and non-political topics.


Overall sentiment

Political sentiment

Non-political sentiment

Brexit sentiment

Sentiment related to the spread of epidemic diseases


Measures of Exposure

Our exposure measures count the frequency of keywords related to Brexit and the spread of epidemic diseases like Covid-19, SARS, and H1N1 in conference call transcripts.