Luca Barbaglia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Luca Barbaglia has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Sergio Consoli
European Commission, Joint Research Centre (JRC), Ispra, Italy
6 shared publications - Sebastiano Manzan
City University of New York, Baruch College - Zicklin School of Business - Department of Economics and Finance
4 shared publications Christophe Croux
3 shared publications- Lorenzo Frattarolo
University of Verona
3 shared publications Luca Onorante
European Commission, Joint Research Centre (JRC) , Ispra
3 shared publicationsSebastiano Manzan
3 shared publications
Latest Publications
- Open Access
- 17 September 2026
- Published by Oxford University Press (OUP) in Journal of Financial Econometrics
- Vol. 24 (5)
Interpretable Bayesian Machine Learning for Assessing the Effects of Climate News Shocks on Firm-Level Returns
We propose a novel Bayesian asset pricing framework that uses machine learning to capture nonlinear interactions between firm exposures to climate risks and several possible effect modifiers. Our model assumes that heterogeneous coefficients measuring the climate risk exposures are unknown functions of firm-level characteristics, such as sector classification and CO2 emissions, which act as effect modifiers. These functions are estimated through sums of regression trees. We measure climate risks using two indicators obtained through textual analysis. Our analysis using a portfolio of 433 US stocks reveals that climate risks trigger a nonlinear and asymmetric impact on stock returns. Sectors with high pollution intensities are disproportionately affected, particularly by natural disaster news, with the highest polluting firms experiencing the strongest impact. The impacts are economically and statistically significant, and consistent with the “investor overreaction hypothesis.”
- 17 September 2026
- Published by Oxford University Press (OUP) in Journal of Financial Econometrics
- Vol. 24 (5)
Open AccessInterpretable Bayesian Machine Learning for Assessing the Effects of Climate News Shocks on Firm-Level Returns
We propose a novel Bayesian asset pricing framework that uses machine learning to capture nonlinear interactions between firm exposures to climate risks and several possible effect modifiers. Our model assumes that heterogeneous coefficients measuring the climate risk exposures are unknown functions of firm-level characteristics, such as sector classification and CO2 emissions, which act as effect modifiers. These functions are estimated through sums of regression trees. We measure climate risks using two indicators obtained through textual analysis. Our analysis using a portfolio of 433 US stocks reveals that climate risks trigger a nonlinear and asymmetric impact on stock returns. Sectors with high pollution intensities are disproportionately affected, particularly by natural disaster news, with the highest polluting firms experiencing the strongest impact. The impacts are economically and statistically significant, and consistent with the “investor overreaction hypothesis.”
- Open Access
- 4 February 2026
- Published by Elsevier in Energy Economics
- Vol. 155
A climate stress testing exercise on loans to European small and medium enterprises
- 4 February 2026
- Published by Elsevier in Energy Economics
- Vol. 155
Open AccessA climate stress testing exercise on loans to European small and medium enterprises
- Open Access
- 7 October 2025
- Published by Elsevier in International Journal of Forecasting
- Vol. 42 (2) , 657-672
Nowcasting economic activity in European regions using a mixed-frequency dynamic factor model
- 7 October 2025
- Published by Elsevier in International Journal of Forecasting
- Vol. 42 (2) , 657-672
Open AccessNowcasting economic activity in European regions using a mixed-frequency dynamic factor model
- Open Access
Sentiment Analysis of Economic Text: A Lexicon-Based Approach
We propose an Economic Lexicon (EL) specifically designed for textual applications in economics. We construct the dictionary with two important characteristics: 1) to have a wide coverage of terms used in documents discussing economic concepts, and 2) to provide a human-annotated sentiment score in the range [-1,1]. We illustrate the use of the EL in the context of a simple sentiment measure and consider several applications in economics. The comparison to other lexicons shows that the EL is superior due to its wider coverage of domain relevant terms and its more accurate categorization of the word sentiment.
Open AccessSentiment Analysis of Economic Text: A Lexicon-Based Approach
We propose an Economic Lexicon (EL) specifically designed for textual applications in economics. We construct the dictionary with two important characteristics: 1) to have a wide coverage of terms used in documents discussing economic concepts, and 2) to provide a human-annotated sentiment score in the range [-1,1]. We illustrate the use of the EL in the context of a simple sentiment measure and consider several applications in economics. The comparison to other lexicons shows that the EL is superior due to its wider coverage of domain relevant terms and its more accurate categorization of the word sentiment.
- Open Access
Nowcasting economic activity in European regions using a mixed-frequency dynamic factor model
Timely information about the state of regional economies can be essential for planning, implementing and evaluating locally targeted economic policies. However, European regional accounts for output are published at an annual frequency and with a two-year delay. To obtain robust and more timely measures in a computationally efficient manner, we propose a mixed-frequency dynamic factor model that accounts for national information to produce high-frequency estimates of the regional gross value added (GVA). We show that our model produces reliable nowcasts of GVA in 162 regions across 12 European countries.
Open AccessNowcasting economic activity in European regions using a mixed-frequency dynamic factor model
Timely information about the state of regional economies can be essential for planning, implementing and evaluating locally targeted economic policies. However, European regional accounts for output are published at an annual frequency and with a two-year delay. To obtain robust and more timely measures in a computationally efficient manner, we propose a mixed-frequency dynamic factor model that accounts for national information to produce high-frequency estimates of the regional gross value added (GVA). We show that our model produces reliable nowcasts of GVA in 162 regions across 12 European countries.
- Open Access
Forecasting GDP in Europe with Textual Data
We evaluate the informational content of news-based sentiment indicators for forecasting Gross Domestic Product (GDP) and other macroeconomic variables of the five major European economies. Our data set includes over 27 million articles for 26 major newspapers in 5 different languages. The evidence indicates that these sentiment indicators are significant predictors to forecast macroeconomic variables and their predictive content is robust to controlling for other indicators available to forecasters in real-time.
Open AccessForecasting GDP in Europe with Textual Data
We evaluate the informational content of news-based sentiment indicators for forecasting Gross Domestic Product (GDP) and other macroeconomic variables of the five major European economies. Our data set includes over 27 million articles for 26 major newspapers in 5 different languages. The evidence indicates that these sentiment indicators are significant predictors to forecast macroeconomic variables and their predictive content is robust to controlling for other indicators available to forecasters in real-time.
- Open Access
- 31 January 2023
- Published by Springer Nature
- p. 38-43
On the Development of a European Tracker of Societal Issues and Economic Activities Using Alternative Data
We provide an overview on the development of a tracker of economic activities and societal issues across EU member states mining alternative data sources, that can be used to complement official statistics. Considered alternative datasets include Google Searches, Dow Jones Data, News and Analytics (DNA), and the Global Dataset of Events, Language and Tone (GDELT). After providing an overview on the methodology under current development, some preliminary findings are also given.
- 31 January 2023
- Published by Springer Nature
- p. 38-43
Open AccessOn the Development of a European Tracker of Societal Issues and Economic Activities Using Alternative Data
We provide an overview on the development of a tracker of economic activities and societal issues across EU member states mining alternative data sources, that can be used to complement official statistics. Considered alternative datasets include Google Searches, Dow Jones Data, News and Analytics (DNA), and the Global Dataset of Events, Language and Tone (GDELT). After providing an overview on the methodology under current development, some preliminary findings are also given.
- Open Access
- 4 November 2022
- Published by Elsevier in International Journal of Forecasting
- Vol. 39 (4) , 1548-1563
Testing big data in a big crisis: Nowcasting under Covid-19
- 4 November 2022
- Published by Elsevier in International Journal of Forecasting
- Vol. 39 (4) , 1548-1563
Open AccessTesting big data in a big crisis: Nowcasting under Covid-19
- Top Cited PapersOpen Access
- 9 May 2022
- Published by Taylor & Francis in Journal of Business & Economic Statistics
- Vol. 41 (3) , 708-719
Forecasting with Economic News
The goal of this paper is to evaluate the informational content of sentiment extracted from news articles about the state of the economy. We propose a fine-grained aspect-based sentiment analysis that has two main characteristics: 1) we consider only the text in the article that is semantically dependent on a term of interest (aspect-based) and, 2) assign a sentiment score to each word based on a dictionary that we develop for applications in economics and finance (fine-grained). Our data set includes six large US newspapers, for a total of over 6.6 million articles and 4.2 billion words. Our findings suggest that several measures of economic sentiment track closely business cycle fluctuations and that they are relevant predictors for four major macroeconomic variables. We find that there are significant improvements in forecasting when sentiment is considered along with macroeconomic factors. In addition, we also find that sentiment matters to explains the tails of the probability distribution across several macroeconomic variables.
- 9 May 2022
- Published by Taylor & Francis in Journal of Business & Economic Statistics
- Vol. 41 (3) , 708-719
Top Cited PapersOpen AccessForecasting with Economic News
The goal of this paper is to evaluate the informational content of sentiment extracted from news articles about the state of the economy. We propose a fine-grained aspect-based sentiment analysis that has two main characteristics: 1) we consider only the text in the article that is semantically dependent on a term of interest (aspect-based) and, 2) assign a sentiment score to each word based on a dictionary that we develop for applications in economics and finance (fine-grained). Our data set includes six large US newspapers, for a total of over 6.6 million articles and 4.2 billion words. Our findings suggest that several measures of economic sentiment track closely business cycle fluctuations and that they are relevant predictors for four major macroeconomic variables. We find that there are significant improvements in forecasting when sentiment is considered along with macroeconomic factors. In addition, we also find that sentiment matters to explains the tails of the probability distribution across several macroeconomic variables.
- Open Access
- 18 April 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 247
Fine-grained, aspect-based sentiment analysis on economic and financial lexicon
- 18 April 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 247
Open AccessFine-grained, aspect-based sentiment analysis on economic and financial lexicon