Search Results
Journal Article
Is Optimism for Artificial Intelligence Boosting Investment?
U.S. business spending related to artificial intelligence (AI) grew substantially in 2025 among publicly traded firms, which account for the bulk of overall investment. Analyzing sentiment data from quarterly company earnings calls can help infer current and evolving optimism towards AI. Public firm data show growth in capital spending and research and development funding has come entirely from the largest companies that are positive about AI. While market concentration among large firms raises some challenges, optimism measures suggest that AI investment will continue to contribute to future ...
Journal Article
The Innovation Puzzle: Patents and Productivity Growth
Understanding the pace and nature of technological progress is key for evaluating innovation policy and projecting economic growth.
Journal Article
Uneven Innovation in the U.S.
The San Jose and San Francisco areas don’t make the U.S. top 10 in terms of population, and they each contain merely 1% of the national workforce. But jointly they produce about 20% of all innovation output.
Journal Article
Real-Time Discovery of Corporate Risks
We propose a new methodology to discover emerging corporate risks in real time by analyzing the text of quarterly earnings conference calls from 2008 to 2025. Our approach identifies bigrams (two-word phrases) within risk-related sentences whose usage surges significantly and then groups them into thematic topics. The method successfully recovers a timeline of major economic events, from the credit crisis in 2008 to macroeconomic and tariff uncertainty in 2025. We find that firms manage these risks differently. While macroeconomic uncertainty is associated with reductions in investment and ...
Working Paper
Theory Meets Textual Analysis: Measuring Firm-Level Labor Cost Pressures and Inflation Pass-Through
We develop a novel measure of firm-level marginal labor cost and investigate its inflation pass-through. We apply textual analysis to earnings calls to identify labordiscussions. Leveraging cost-minimization theory that firms equate marginal revenue products across variable inputs, we regress intermediate input revenue shares on labor discussion intensity to recover marginal labor cost shocks. This theory-based approach aggregates multidimensional qualitative information into a single measure. Our aggregate index outperforms conventional slack variables in forecasting inflation. Industry ...
Working Paper
Theory Meets Textual Analysis: Measuring Firm-Level Labor Cost Pressures and Inflation Pass-Through
We develop a novel measure of firm-level marginal labor cost and investigate its pass-through to inflation. To construct this measure, we apply textual analysis to earnings calls to identify discussions of labor-related topics such as higher costs, shortages, and hiring. Leveraging the theoretical principle that cost-minimizing firms equate marginal costs across variable inputs, we project changes in firms intermediate input revenue shares onto the intensity of labor-related discussions to quantify their contributions to marginal labor costs. This approach provides an economically-motivated ...
Working Paper
New Technologies and the College Premium
This paper shows that the pace of technology creation is a key driver of wage inequality. It develops a model where college-educated workers learn how to use new technologies faster than others, and where this advantage dissipates over time as technologies become standardized and easier to use. In equilibrium, the college wage premium is determined by the interplay between the pace of technology creation and standardization. A heightened pace of technology creation causes a long-lasting increase in the college premium. We calibrate the model using novel text-based data on new technologies and ...
Working Paper
The Creativity Decline: Evidence from US Patents
Economists have long struggled to understand why aggregate productivity growth has dropped in recent decades while the number of new patents filed has steadily increased. I offer an explanation for this puzzling divergence: the creativity embodied in US patents has dropped dramatically over time. To separate creative from derivative patents, I develop a novel, text-based measure of patent creativity: the share of technical terminology that did not appear in previous patents. I show that only creative and not derivative patents are associated with significant improvements in firm level ...
Working Paper
Text as Data in Economic Analysis
FULL AND CORRECT ORDER OF AUTHORS: Tarek A. Hassan, Stephan Hollander, Aakash Kalyani, Laurence van Lent, Markus Schwedeler, and Ahmed Tahoun. This article discusses how to apply computational linguistics techniques to analyze largely unstructured corporate-generated text for economic analysis. As a core example, we illustrate how textual analysis of earnings conference call transcripts can provide insights into how markets and individual firms respond to economic shocks, such as a nuclear disaster or a geopolitical event: insights that often elude traditional non-text data sources. This ...
Working Paper
Economic Surveillance using Corporate Text
FULL AND CORRECT ORDER OF AUTHORS: Tarek A. Hassan, Stephan Hollander, Aakash Kalyani, Laurence van Lent, Markus Schwedeler, and Ahmed Tahoun. This article applies simple methods from computational linguistics to analyze unstructured corporate texts for economic surveillance. We apply text-as-data approaches to earnings conference call transcripts, patent texts, and job postings to uncover unique insights into how markets and firms respond to economic shocks, such as a nuclear disaster or a geopolitical event---insights that often elude traditional data sources. This method enhances our ...