Search Results
Working Paper
Measuring News Sentiment
This paper demonstrates state-of-the-art text sentiment analysis tools while developing a new time-series measure of economic sentiment derived from economic and financial newspaper articles from January 1980 to April 2015. We compare the predictive accuracy of a large set of sentiment analysis models using a sample of articles that have been rated by humans on a positivity/negativity scale. The results highlight the gains from combining existing lexicons and from accounting for negation. We also generate our own sentiment-scoring model, which includes a new lexicon built specifically to ...
Working Paper
News, sovereign debt maturity, and default risk
Leading into a debt crisis, interest rate spreads on sovereign debt rise before the economy experiences a decline in productivity, suggesting that news about future economic developments may play an important role in these episodes. In a VAR estimation, a news shock has a larger contemporaneous impact on sovereign credit spreads than a comparable shock to labor productivity. A quantitative model of news and sovereign debt default with endogenous maturity choice generates impulse responses and a variance decomposition similar to the empirical VAR estimates. The dynamics of the economy after a ...
Working Paper
Jointly Estimating Macroeconomic News and Surprise Shocks
This paper clarifies the conditions under which the state-of-the-art approach to identifying TFP news shocks in Kurmann and Sims (2021, KS) identifies not only news shocks but also surprise shocks. We examine the ability of the KS procedure to recover responses to these shocks from data generated by a conventional New Keynesian DSGE model. Our analysis shows that the KS response estimator tends to be strongly biased even in the absence of measurement error. This bias worsens in realistically small samples, and the estimator becomes highly variable. Incorporating a direct measure of TFP news ...
Working Paper
News Selection and Household Inflation Expectations
We examine the impact of systematic media reporting on household inflation expectations, focusing on how selective news coverage influences household responses to inflation news. In a model where monitoring all economic developments is costly, households will account for news selection when forming inflation expectations. The model implies an asymmetry: news about high inflation influences inflation expectations more than news about low inflation. Using micro panel data, we find support for this hypothesis. Exposure to news about higher prices increases household inflation expectations by ...
Working Paper
Low Frequency Effects of Macroeconomic News on Government Bond Yields
This study analyzes the reaction of the U.S. Treasury bond market to innovations in macroeconomic fundamentals. We identify these innovations with macroeconomic news, defined as differences between the actual releases and their market expectations. We show that macroeconomic news explain about one-third of the low frequency (quarterly) fluctuations of long-term bond yields. When focusing on the high frequency (daily) movements this share decreases to one-tenth. This result is due to the fact that macro news have a persistent effect on the yield curve. Non-fundamental factors, instead, ...
Briefing
How Expectations About Future Productivity Drive Inventories
To what extent do expectations about future productivity developments drive business cycles? This Economic Brief reviews the state of the literature and discusses how new research by the authors establishes a novel method to answer. We specifically focus on firms' inventories, which stock goods available for future sales. We find that these inventories expand strongly to news about future productivity developments. This confirms that expectations about future productivity are a powerful force behind aggregate fluctuations, a finding with important implications for widely used economic models.
Working Paper
Integrating Prediction and Attribution to Classify News
Recent modeling developments have created tradeoffs between attribution-based models, models that rely on causal relationships, and “pure prediction models†such as neural networks. While forecasters have historically favored one technology or the other based on comfort or loyalty to a particular paradigm, in domains with many observations and predictors such as textual analysis, the tradeoffs between attribution and prediction have become too large to ignore. We document these tradeoffs in the context of relabeling 27 million Thomson Reuters news articles published between 1996 ...
Working Paper
News, sovereign debt maturity, and default risk
Leading into a debt crisis, interest rate spreads on sovereign debt rise before the economy experiences a decline in productivity, suggesting that news about future economic developments may play an important role in these episodes. In a VAR estimation, a news shock has a larger contemporaneous impact on sovereign credit spreads than a comparable shock to labor productivity. A quantitative model of news and sovereign debt default with endogenous maturity choice generates impulse responses and a variance decomposition similar to the empirical VAR estimates. The dynamics of the economy after a ...
Working Paper
News, sovereign debt maturity, and default risk
Leading into a debt crisis, interest rate spreads on sovereign debt rise before the economy experiences a decline in productivity, suggesting that news about future economic developments may play an important role in these episodes. In a VAR estimation, a news shock has a larger contemporaneous impact on sovereign credit spreads than a comparable shock to labor productivity. A quantitative model of news and sovereign debt default with endogenous maturity choice generates impulse responses and a variance decomposition similar to the empirical VAR estimates. The dynamics of the economy after a ...
Working Paper
News versus Sentiment : Predicting Stock Returns from News Stories
This paper uses a dataset of more than 900,000 news stories to test whether news can predict stock returns. We measure sentiment with a proprietary Thomson-Reuters neural network. We find that daily news predicts stock returns for only 1 to 2 days, confirming previous research. Weekly news, however, predicts stock returns for one quarter. Positive news stories increase stock returns quickly, but negative stories have a long delayed reaction. Much of the delayed response to news occurs around the subsequent earnings announcement.