Daily Topical US Economic Sentiment Indices
The added advantage of text- and news-based measures as sources of information for forecasting and assessing the economy is significant. In a recent paper of ours, we present a general methodology, which constitutes the base of the sentometrics R package, to forecast economic variables from news data. In this project, we have computed several US news sentiment indicator for many topics relevant to the US economy.
To encourage research in this area, we share daily sentiment estimates for those economic topics. We estimate the daily sentiment with several lexicon-based methods. The daily sentiment for each topic is reported from 1993 to 2016. We note that missing dates in the dataset means that no news articles were available at that date.
Check out the paper
- Ardia, D., Bluteau, K., Boudt, K. (2019). Questioning the news about economic growth: Sparse forecasting using thousands of news-based sentiment values. International Journal of Forecasting 35, 1370-1386. Link
Download the data here