Twitter-based Uncertainty Indices

Download Twitter-based Uncertainty Data

We are pleased to introduce a new Twitter-based Economic Uncertainty (TEU) Index and a new Twitter-based Market Uncertainty (TMU) Index that runs from January 2010 to the present. It was developed by Thomas Renault (University Paris 1 Panthéon-Sorbonne) in conjunction with Scott R. Baker (Northwestern), Nicholas Bloom (Stanford) and Steve Davis (University of Chicago).

We first extract all messages (tweets) sent on Twitter since January 1, 2010 that contain keywords related to Uncertainty as well as keywords related to the Economy or related to Equity Markets.

The Uncertainty terms are as follows: 'uncertain', 'uncertainly', 'uncertainties', 'uncertainty'. Keywords related to the economy are the following: 'economic', 'economical', 'economically', 'economics', 'economies', 'economist', 'economists', 'economy'. Finally, keywords related to financial or equity markets are made up from the set: 'equities', 'equity', 'equityholder', 'equityholders', 'finance', 'financeable', 'financed', 'finances', 'financial', 'financially', 'financials', 'financier', 'financiers', 'financing', 'financings', 'investment', 'investments', 'investor', 'investors', 'invests', 'market', 'markets', 'trader', 'traders', 'trades', 'trading', 'tradings'.

To construct the TEU and the TMU index, we rescale each series to a mean of 100 from 2010 to 2015. Our database covers all English-language tweets, including from users located outside the United States. However, according to Statista, users in the United States represent more two-thirds of the Twitter users located in English speaking countries (the remaining one third are mostly in the United Kingdom, Canada and Australia). Due to this concentration, our indicators mostly captures US-based uncertainty.