Search Results
Working Paper
PEAD.txt: Post-Earnings-Announcement Drift Using Text
We construct a new numerical measure of earnings announcement surprises, standardized unexpected earnings call text (SUE.txt), that does not explicitly incorporate the reported earnings value. SUE.txt generates a text-based post-earnings announcement drift (PEAD.txt) larger than the classic PEAD and can be used to create a profitable trading strategy. Leveraging the prediction model underlying SUE.txt, we propose new tools to study the news content of text: paragraph-level SUE.txt and paragraph classification scheme based on the business curriculum. With these tools, we document many ...
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
Sentiment in Central Banks' Financial Stability Reports
Using the text of financial stability reports (FSRs) published by central banks, we analyze the relation between the financial cycle and the sentiment conveyed in these official communications. To do so, we construct a dictionary tailored specifically to a financial stability context, which assigns positive and negative connotations based on the sentiment conveyed by words in FSRs. With this dictionary, we construct a financial stability sentiment (FSS) index. Using a panel of 35 countries for the sample period between 2005 and 2015, we find that central banks' FSS indexes are mostly driven ...
Working Paper
The Interactions of Social Norms about Climate Change: Science, Institutions and Economics
We study the evolution of interest in climate change among different actors within the population and how the interest of these actors affects one another. First, we document the evolution of interest for each actor individually, and then we provide a model of cross-influences between them. We estimate this model using a Vector Autoregression (VAR). We measure interest among the general public, the European Parliament, central banks, general interest science journals, and economics journals by creating a Climate Change Index (CCI) based on mentions of climate change in these domains. Except ...
Report
The Pay and Non-Pay Content of Job Ads
How informative are job ads about the actual pay and amenities offered by employers? Using a comprehensive database of job ads posted by Norwegian employers, we develop a methodology to systematically classify the information on both pay and non-pay job attributes advertised in vacancy texts. We link this information to measures of employer attractiveness, which we derive from a job search model estimated on observed wages and worker mobility flows. About 55 percent of job ads provide information related to pay and nearly all ads feature information on non-pay attributes. We show that ...
Discussion Paper
A Peek behind the Curtain of Bank Supervision
Since the financial crisis, bank regulatory and supervisory policies have changed dramatically both in the United States (Dodd-Frank Wall Street Reform and Consumer Protection Act) and abroad (Third Basel Accord). While these shifts have occasioned much debate, the discussion surrounding supervision remains limited because most supervisory activity? both the amount of supervisory attention and the demands for corrective action by supervisors?is confidential. Drawing on our recent staff report ?Parsing the Content of Bank Supervision,? this post provides a peek behind the scenes of bank ...
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.
Working Paper
Deciphering Federal Reserve Communication via Text Analysis of Alternative FOMC Statements*
We present a text-based metric for monetary policy stance using official and alternative Federal Open Market Committee statements. Our advanced natural language processing, with numeric property detection, jointly evaluates quantitative decisions like interest rates and qualitative explanations for these choices from texts. Monetary policy stance is decomposed into expected stance and surprise components by leveraging high-frequency bond futures data around FOMC announcements. We examine responses of stock returns to counterfactual (more dovish or hawkish) policy surprises through alternative ...
Working Paper
Deciphering Federal Reserve Communication via Text Analysis of Alternative FOMC Statements
We propose a text-based measure of monetary policy stance that models FOMC statements as convex combinations of dovish and hawkish alternatives, providing a tractable representation of the Committee's position along the policy spectrum. Leveraging staff-drafted alternative statements, we fine-tune a pre-trained language model to capture both quantitative precision and semantic tone. Stance is defined as the product of tone and novelty, and decomposed into expected and surprise components using high-frequency financial data. Surprises arise from shifts in tone relative to expectations or from ...
Working Paper
The Power of Narratives in Economic Forecasts
We apply textual analysis tools to the narratives that accompany Federal Reserve Board economic forecasts to measure the degree of optimism versus pessimism expressed in those narratives. Text sentiment is strongly correlated with the accompanying economic point forecasts, positively for GDP forecasts and negatively for unemployment and inflation forecasts. Moreover, our sentiment measure predicts errors in FRB and private forecasts for GDP growth and unemployment up to four quarters out. Furthermore, stronger sentiment predicts tighter than expected monetary policy and higher future stock ...