Business Cycle Narratives

Larsen, Vegard H.; Thorsrud, Leif Anders

doi:10.2139/ssrn.3338822

Cited by 13 publications

(22 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Narratives are not captured by the terms in isolation, but rather by how different terms are used in context and together. To capture this, we apply factor modeling techniques to construct numerical approximations to the narratives conveyed in the texts (Larsen and Thorsrud, 2018). In the NLP literature, such factors are commonly referred to as topics, which summarizes the themes of documents in a parsimonious manner.…”

Section: Methodsmentioning

confidence: 99%

“…Because we are interested in capturing differences in narrative focus, we do not follow this route. SeeLarsen and Thorsrud (2018) for a richer discussion about how factors/topics derived from textual data can be interpreted as narratives.7 Likewise, newer popular methods involving neural network architectures and word embeddings, like, e.g.,Le and Mikolov (2014) andKusner et al (2015), are mostly unsupervised algorithms which in addition require large corpora for training.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Narrative Monetary Policy Surprises and the Media

Ellen¹,

Larsen²,

Thorsrud³

2021

J of Money Credit Banking

Self Cite

View full text Add to dashboard Cite

We propose a simple method to quantify narratives from textual data, and identify "narrative monetary policy surprises" as the difference in narrative focus in central bank communication accompanying interest rate meetings and economic media coverage prior to those meetings. Identifying narrative surprises, using Norwegian data, provides surprise measures that are uncorrelated with conventional monetary policy surprises, and, in contrast to such surprises, have a significant effect on subsequent media coverage. Narrative monetary policy surprises lead to macroeconomic responses similar to what recent monetary policy literature associates with the information component of monetary policy communication, highlighting media's role as information intermediaries.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Narrative Monetary Policy Surprises and the Media

Ellen¹,

Larsen²,

Thorsrud³

2021

J of Money Credit Banking

Self Cite

View full text Add to dashboard Cite

show abstract

“…We instead use topic models to capture narratives by leveraging the theoretical insight that DAGs with the same skeletons are observationally equivalent. Closely related to our methodology of topic models, Larsen and Thorsrud (2019) study the effects of narratives on business cycle fluctuations, defining narratives as significant economic events that are extracted using topic models on the corpus of newspaper articles. We instead capture narratives as news media's competing interpretations of the same underlying economic event, which is motivated by our theoretical framework and models of competing narratives (Eliaz and Spiegler, 2020).…”

Section: Introductionmentioning

confidence: 99%

Narrative-Driven Fluctuations in Sentiment: Evidence Linking Traditional and Social Media

Macaulay

Song

2022

SSRN Journal

View full text Add to dashboard Cite

“…There is a growing body of research exploring the role of news narrative and its implications on financial markets and the economy. In particular, developments in natural language processing and the ever-increasing ability to process large volumes of data have made it possible to operationalize the concept of narrative, and to quantitatively link it with economic fundamentals (V. Larsen & Thorsrud, 2019) and economic fluctuations (Kalamara et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Predicting market inflation expectations with news topics and sentiment

Tilly¹,

Livan²

2021

Preprint

View full text Add to dashboard Cite

This study presents a novel approach to incorporating news topics and their associated sentiment into predictions of breakeven inflation rate (BEIR) movements for eight countries with mature bond markets. We calibrate five classes of machine learning models including narrative-based features for each country, and find that they generally outperform corresponding benchmarks that do not include such features. We find Logistic Regression and XGBoost classifiers to deliver the best performance across countries. We complement these results with a feature importance analysis, showing that economic and financial topics are the key performance drivers in our predictions, with additional contributions from topics related to health and government. We examine cross-country spillover effects of news narrative on BEIR via Graphical Granger Causality and confirm their existence for the US and Germany, while five other countries considered in our study are only influenced by local narrative.

show abstract

Business Cycle Narratives

Cited by 13 publications

References 39 publications

Narrative Monetary Policy Surprises and the Media

Narrative Monetary Policy Surprises and the Media

Narrative-Driven Fluctuations in Sentiment: Evidence Linking Traditional and Social Media

Predicting market inflation expectations with news topics and sentiment

Contact Info

Product

Resources

About