News-based Sentiment Indicators
IMF Working Papers, December 6, 2019
Source details
- Canonical URL
- News-based Sentiment Indicators
Other formats
Bibliographic details
- Authors: Chengyu Huang, Sean Simpson, Daria Ulybina, Agustin Roitman
- Published: December 6, 2019
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9781513518374.001
Summary
- Title: News-based Sentiment Indicators
- Authors: Chengyu Huang, Sean Simpson, Daria Ulybina, Agustin Roitman
- Publication date: December 6, 2019
- Core summary: We construct sentiment indices for 20 countries from 1980 to 2019. Relying on computational text analysis, we capture specific language like “fear”, “risk”, “hedging”, “opinion”, and, “crisis”, as well as “positive” and “negative” sentiments, in news articles from the Financial Times. We assess the performance of our sentiment indices as “news-based” early warning indicators (EWIs) for financial crises. We find that sentiment indices spike and/or trend up ahead of financial crises.
Methodology
- Data source: News articles from the Financial Times.
- Sample coverage: 20 countries, 1980 to 2019.
- Text-analysis approach: Computational text analysis capturing specific language including “fear”, “risk”, “hedging”, “opinion”, “crisis”, “positive”, and “negative”.
- Technical terminology preserved from source: seed words, sentiment, sentiment index, sentiment indices, term cluster, vector representation, word vector representation, word-vector models.
Key findings and performance as early warning indicators
- Sentiment indices spike and/or trend up ahead of financial crises.
- Application: Assessment of sentiment indices as “news-based” early warning indicators (EWIs) for financial crises.
Subject areas and keywords
- Subject: Banking crises, Early warning systems, Financial crises, Financial regulation and supervision, Global financial crisis of 2008-2009, Hedging
- Keywords: Banking crises, crisis, crisis sentiment, early warning indicators, Early warning systems, financial crises, Global, Global financial crisis of 2008-2009, Hedging, risk, seed words, sentiment, sentiment index, sentiment indices, term cluster, vector representation, word vector representation, word-vector models, WP
Content in this bundle
- Working Paper