SAFE working paper
https://safe-frankfurt.de/de/publikationen/working-papers.html
Refine
Year of publication
- 2021 (32) (remove)
Document Type
- Working Paper (32)
Language
- English (32)
Has Fulltext
- yes (32)
Is part of the Bibliography
- no (32)
Keywords
- COVID-19 (4)
- ESG (4)
- ETFs (2)
- ambiguity (2)
- climate change (2)
- green finance (2)
- volatility (2)
- Algorithmic transparency (1)
- Bank Bailout (1)
- Bank Recapitalization (1)
- Belief up-dating (1)
- Beliefs (1)
- Board Appointments (1)
- Bond risk premia (1)
- C corporations (1)
- Capital Purchase Program (1)
- Centrality (1)
- China (1)
- Corporate Social Responsibility (1)
- Covid-19 (1)
- DCC-GARCH (1)
- DSGE models (1)
- Dictionary (1)
- Digitalized Markets (1)
- Disposition Effect (1)
- Dividend Payments (1)
- ESG Rating Agencies (1)
- Equity Premium (1)
- Expectations (1)
- Explainable machine learning (1)
- Financial Crises (1)
- Financial Market Cycles (1)
- Fiscal theory of the price level (1)
- Formative experiences (1)
- Fund Flows (1)
- Government debt (1)
- Granger Causality (1)
- High Frequency Data (1)
- High-frequency event study (1)
- Hong test (1)
- Household Finance (1)
- Information processing (1)
- International Finance (1)
- Investor sentiment (1)
- LSTM neural networks (1)
- Machine learning (1)
- Market efficiency (1)
- Monetary Policy Surprises (1)
- NLP (1)
- Network theory (1)
- Nonlinear solution methods (1)
- Obfuscation (1)
- Oil market (1)
- Portfolio Rebalancing (1)
- Portfolio choice (1)
- Price Competition (1)
- Price Pressures (1)
- Public financial news (1)
- Rational Inattention (1)
- Responsible investment (1)
- Retail Investor (1)
- Risk taking (1)
- S corporations (1)
- S&P 500 (1)
- Social media (1)
- Socially responsible investing (1)
- Stock market (1)
- Sustainable Investments (1)
- TARP (1)
- Tax Cuts and Jobs Act (1)
- Twitter (1)
- XAI (1)
- age (1)
- ambiguity premium (1)
- anomalies (1)
- asset pricing (1)
- bank (1)
- banks (1)
- behavioral economics (1)
- belief effect (1)
- belief estimation (1)
- belief updating (1)
- benchmarks (1)
- bid-ask spread (1)
- bubbles (1)
- call auctions (1)
- climate risk (1)
- compliance behavior (1)
- confirmatory biases (1)
- consumer protection (1)
- corporate governance (1)
- corporate taxation (1)
- credence goods (1)
- designated market makers (1)
- discrimination (1)
- employees (1)
- endogenous information acquisition (1)
- erm structure of interest rates (1)
- factor timing (1)
- financial advice (1)
- financial market (1)
- financial risk-taking (1)
- financing (1)
- fintech (1)
- health (1)
- household finance (1)
- institutional investors (1)
- investment biases (1)
- investor behavior (1)
- labels (1)
- laboratory experiment (1)
- laboratory experiments (1)
- lending (1)
- lottery-type assets (1)
- mandatory disclosure (1)
- marginal propensity to consume (1)
- market discipline (1)
- market price (1)
- market-based (1)
- measure of ambiguity (1)
- media polarization (1)
- motivated beliefs (1)
- net zero transition (1)
- option prices (1)
- patents (1)
- persistence (1)
- saving (1)
- sentiment (1)
- source dependence (1)
- spillover effects (1)
- stock market crisis (1)
- sustainability (1)
- sustainable finance (1)
- tax cut (1)
- tax intervention (1)
- taxonomies (1)
- time series momentum (1)
- trading activity (1)
- trend chasing (1)
- valuation ratios (1)
- workforce (1)
- financial literacy (1)
Institute
- House of Finance (HoF) (32) (remove)
322
Recent advances in natural language processing have contributed to the development of market sentiment measures through text content analysis in news providers and social media. The effectiveness of these sentiment variables depends on the imple- mented techniques and the type of source on which they are based. In this paper, we investigate the impact of the release of public financial news on the S&P 500. Using automatic labeling techniques based on either stock index returns or dictionaries, we apply a classification problem based on long short-term memory neural networks to extract alternative proxies of investor sentiment. Our findings provide evidence that there exists an impact of those sentiments in the market on a 20-minute time frame. We find that dictionary-based sentiment provides meaningful results with respect to those based on stock index returns, which partly fails in the mapping process between news and financial returns.
314
We focus on the role of social media as a high-frequency, unfiltered mass information transmission channel and how its use for government communication affects the aggregate stock markets. To measure this effect, we concentrate on one of the most prominent Twitter users, the 45th President of the United States, Donald J. Trump. We analyze around 1,400 of his tweets related to the US economy and classify them by topic and textual sentiment using machine learning algorithms. We investigate whether the tweets contain relevant information for financial markets, i.e. whether they affect market returns, volatility, and trading volumes. Using high-frequency data, we find that Trump’s tweets are most often a reaction to pre-existing market trends and therefore do not provide material new information that would influence prices or trading. We show that past market information can help predict Trump’s decision to tweet about the economy.