Manufacturing Sentiment
Forecasting Industrial Production With Text Analysis
Bibliographic Data
| ID | 21653349 |
|---|---|
| Authors | Tomaz Cajner (Federal Reserve Board of Governors Washington DC USA), Leland D Crane (Federal Reserve Board of Governors Washington DC USA), Christopher Kurz (0000-0002-7263-258X, Federal Reserve Board of Governors Washington DC USA), Norman Morin (Federal Reserve Board of Governors Washington DC USA), Paul E Soto (Federal Reserve Board of Governors Washington DC USA, corresponding author), Betsy Vrankovich (Federal Reserve Board of Governors Washington DC USA) |
| Year | 2026 |
| Volume | 41 |
| Issue | 4 |
| Pages | 377-393 |
| Publication date | 2026-06-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Journal of Applied Econometrics (JOURNAL) |
| Journal identifiers | ISSN: 1099-1255 • E-ISSN: 0883-7252 |
| Publisher | Wiley (PUBLISHER • GB) |
| DOI | 10.1002/jae.70046 |
| OpenAlex | W7134185785 |
| Language | EN |
| References cited | 36 |
This paper leverages free‐form textual responses from a key manufacturing survey to create sentiment indexes that mirror categorical measures from the same survey and also contain predictive content—both in and out‐of‐sample—for manufacturing output. We use textual data from the Institute for Supply Management to compare sentiment metrics based on dictionary and deep learning natural language processing methods. The best performing sentiment measures classify comments based on fine‐tuned deep learning models. To add interpretability, we apply Shapley decompositions to show that a relatively small number of words—associated with very positive and very negative sentiment—account for much of the variation in the aggregate sentiment index
Categorical variable · Deep learning · Sentiment analysis · Forecasting Techniques and Applications · Sentiment Analysis and Opinion Mining · Stock Market Forecasting Methods
The General Theory of Employment
Measuring Economic Policy Uncertainty
Nowcasting Euro area GDP with news sentiment
Making text count
A Value for n-Person Games
Text as Data
Transparency and Deliberation Within the Fomc
Out-of-Sample Forecast Tests Robust to the Choice of Window Size
Reality Checks and Comparisons of Nested Predictive Models
| Citation velocity | historical |
|---|---|
| Highly cited | No |