Macroeconomic forecasting through news, emotions and narrative

Tilly, Sonja; Ebner, Martin; Livan, Giacomo

doi:10.1016/j.eswa.2021.114760

Cited by 16 publications

(16 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply the filtering methodology introduced by Tilly et al (Tilly et al, 2021) to extract observations from GDELT's GKG that are pertinent to economic growth. The methodology consists of three steps -first, a thematic keyword filter, second, a fine-grained filter using a neural network and third, data aggregation.…”

Section: Filtering Methodologymentioning

confidence: 99%

Macroeconomic forecasting with statistically validated knowledge graphs

Tilly¹,

Livan²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This study leverages narrative from global newspapers to construct theme-based knowledge graphs about world events, demonstrating that features extracted from such graphs improve forecasts of industrial production in three large economies compared to a number of benchmarks. Our analysis relies on a filtering methodology that extracts "backbones" of statistically significant edges from large graph data sets. We find that changes in the eigenvector centrality of nodes in such backbones capture shifts in relative importance between different themes significantly better than graph similarity measures. We supplement our results with an interpretability analysis, showing that the theme categories "disease" and "economic" have the strongest predictive power during the time period that we consider. Our work serves as a blueprint for the construction of parsimonious -yet informative -theme-based knowledge graphs to monitor in real time the evolution of relevant phenomena in socio-economic systems.

show abstract

Section: Filtering Methodologymentioning

confidence: 99%

Macroeconomic forecasting with statistically validated knowledge graphs

Tilly¹,

Livan²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are also works of Fraiberger et al (2021) andFronzetti Colladon et al (2020) in which they used the sentiment from Reuters and Italian news articles to predict emerging stock markets and Italian stocks market respectively. And finally, we also have the work of Fronzetti Colladon and Elshendy (2017) and Tilly et al (2021) where they analyzed news data from the GDELT project to forecast the macroeconomic indices. Several other studies have tried to apply sentimental analysis to the field of trading such as the work of Kazemian et al (2016) and Mudinas et al (2019).…”

Section: Literature Reviewmentioning

confidence: 99%

“…We can scrap news directly from newspaper websites, we can get them from RSS feed or we can get them from news data providers. In this study, we follow the work of Fronzetti Colladon and Elshendy (2017) and Tilly et al (2021) where we use the GDELT project as the source of our news data.…”

Section: Datasetmentioning

confidence: 99%

ESG Investing: A Sentiment Analysis Approach

et al. 2023

View full text Add to dashboard Cite

“…Only a few studies have quantitatively examined emotions shared in actual news content. For instance, using affect-coded news data from the Global Database of Events, Language, and Tone (GDELT; Leetaru and Schrodt, 2013 ), a recent study showed that affect in the news predicted macro-economic indicators ( Tilly et al., 2021 ). Ebola-related sentiment follows similar trajectories in the news and in social media (Kim, Jeong, Kim et al., 2015).…”

Section: Emotions In the Newsmentioning

confidence: 99%