Findes ikke på dansk
Giampiero M. Gallo
- 17 September 2026
- WORKING PAPER SERIES - No. 3283Details
- Abstract
- Measuring sentiment from financial news is a central task in economics and finance, yet most existing indicators rely on dictionary-based approaches that infer sentiment from word counts and only partially capture context, negation, and semantic structure. This paper proposes a framework for constructing daily news mood indices using transformer-based language models and evaluates whether they better represent sentiment than dictionary-based alternatives. Using 143,755 financial news articles from Factiva, we classify sentiment at the sentence level with FinBERT and aggregate these predictions into article-level and daily sentiment measures through alternative normalization schemes. We compare the resulting indices with benchmark measures based on Shapiro et al., 2022 and Barbaglia et al., 2025. A central contribution is the validation of alternative sentiment measures against human judgments. We conducted an incentivized annotation exercise in which 444 participants evaluated a validation subsample of 588 financial news articles. Consensus ratings from independent human evaluations serve as an external benchmark for assessing the quality of automated sentiment measures. Across correlation, regression, and classification exercises, transformer-based measures show stronger agreement with human judgments than vocabulary-based alternatives and perform substantially better in distinguishing positive, neutral, and negative articles. Overall, the results suggest that incorporating contextual information through transformer-based language models produces sentiment measures that more closely reflect human assessments of financial news.
- JEL Code
- C55 : Mathematical and Quantitative Methods→Econometric Modeling→Modeling with Large Data Sets?
C81 : Mathematical and Quantitative Methods→Data Collection and Data Estimation Methodology, Computer Programs→Methodology for Collecting, Estimating, and Organizing Microeconomic Data, Data Access
E32 : Macroeconomics and Monetary Economics→Prices, Business Fluctuations, and Cycles→Business Fluctuations, Cycles
E37 : Macroeconomics and Monetary Economics→Prices, Business Fluctuations, and Cycles→Forecasting and Simulation: Models and Applications
G14 : Financial Economics→General Financial Markets→Information and Market Efficiency, Event Studies, Insider Trading
- 8 November 2024
- WORKING PAPER SERIES - No. 2999Details
- Abstract
- In 1936, John Maynard Keynes proposed that emotions and instincts are pivotal in decision-making, particularly for investors. Both positive and negative moods can influence judgments and decisions, extending to economic and financial choices. Intuitions, emotional states, and biases significantly shape how people think and act. Measuring mood or sentiment is challenging, but surveys and data collection methods, such as confidence indices and consensus forecasts, offer some solutions. Recently, the availability of web data, including search engine queries and social media activity, has provided high-frequency sentiment measures. For example, the Italian National Statistical Institute’s Social Mood on Economy Index (SMEI) uses Twitter data to assess economic sentiment in Italy. The relationship between SMEI and financial market activity, specifically the FTSE MIB index and its volatility, is examined using a trivariate Vector Autoregressive model, taking into account the impact of the COVID-19 pandemic.
- JEL Code
- C1 : Mathematical and Quantitative Methods→Econometric and Statistical Methods and Methodology: General
C32 : Mathematical and Quantitative Methods→Multiple or Simultaneous Equation Models, Multiple Variables→Time-Series Models, Dynamic Quantile Regressions, Dynamic Treatment Effect Models, Diffusion Processes
C53 : Mathematical and Quantitative Methods→Econometric Modeling→Forecasting and Prediction Methods, Simulation Methods
G4 : Financial Economics